[{"id":"3dsrbench","name":"3DSRBench","topic":"Spatial reasoning","description":"3D spatial reasoning benchmark for large multimodal models (height, location, orientation, multi-object relations).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":68.92,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68.92},{"place":2,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":67.7},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.3},{"place":4,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":63},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":62.3},{"place":6,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":62.1},{"place":7,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":60.96},{"place":8,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":60.2},{"place":9,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":59.3},{"place":10,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":59},{"place":11,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.78},{"place":12,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":55.01},{"place":13,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":54.93},{"place":14,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":54.7},{"place":15,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.62},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.6},{"place":17,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":53.5},{"place":18,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":53.2},{"place":19,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":52.3},{"place":20,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":51.8}]},{"id":"aav-capsid-packaging-prediction","name":"AAV Capsid Packaging Prediction","topic":"Biosecurity","description":"Predict packaging scores for held-out AAV capsid variants; Spearman rank correlation (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"spearman","stars":"","top_model":"GPT-6 Sol","top_percent":0.534,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.534},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.529},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.5285},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.5282},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.5282},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.528}]},{"id":"acebench","name":"AceBench","topic":"Industry QA","description":"Industry-focused benchmark assessing domain QA and reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ERNIE 5.0","top_percent":87.7,"top_model_id":"ernie-5.0","top_generation":"ERNIE 5.0","top_model_base":"ERNIE 5.0","top_model_family":"ERNIE","top_company":"baidu","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":87.7},{"place":2,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":82.2},{"place":3,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":81.4},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.9},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80.9},{"place":6,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":80.1},{"place":7,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":79.6},{"place":8,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":79.3},{"place":9,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":76.5},{"place":10,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":76.2},{"place":11,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":75.6},{"place":12,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.5},{"place":13,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":74.3},{"place":14,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":72.7},{"place":15,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.5},{"place":16,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":61.8},{"place":17,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":49.8}]},{"id":"acebench-zh","name":"ACEBench (ZH)","topic":"Tool use (Chinese)","description":"Chinese split of ACEBench tool-use evaluation.","url":"https://github.com/ACEBench/ACEBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ERNIE 5.0","top_percent":89.6,"top_model_id":"ernie-5.0","top_generation":"ERNIE 5.0","top_model_base":"ERNIE 5.0","top_model_family":"ERNIE","top_company":"baidu","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":89.6},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.5},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":83.6},{"place":5,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.4}]},{"id":"acos-decision","name":"ACOS (decision)","topic":"Aspect sentiment","description":"Aspect-category-opinion-sentiment decisions; per-review F1. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/NUSTM/ACOS","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"pplx-decider-v1.2","top_percent":40.9,"top_model_id":"pplx-decider-v1.2","top_generation":"v1.2","top_model_base":"pplx-decider","top_model_family":"pplx-decider","top_company":"perplexity","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":40.9},{"place":2,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":39},{"place":3,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":37.7},{"place":4,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":35.5},{"place":5,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":33.3},{"place":6,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":33.1},{"place":7,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":30},{"place":8,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":29.8},{"place":9,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":29.5},{"place":10,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":28.4},{"place":11,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":26.5},{"place":12,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":25.9},{"place":13,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":24.5},{"place":14,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":24.5},{"place":15,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":24.5},{"place":16,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":23.1},{"place":17,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":22.5},{"place":18,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":19.5},{"place":19,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":18.3},{"place":20,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":18},{"place":21,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":17.4},{"place":22,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":15.9},{"place":23,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":13},{"place":24,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":11.4},{"place":25,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":10.3},{"place":26,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":10.1},{"place":27,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":8.7},{"place":28,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":7.8},{"place":29,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":7.1},{"place":30,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":6.5},{"place":31,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":6},{"place":32,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":5.4},{"place":33,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":4.9},{"place":34,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":4.6},{"place":35,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":4},{"place":36,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":3.5},{"place":37,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":0.5},{"place":38,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":0}]},{"id":"acp-bench-bool","name":"ACP-Bench Bool","topic":"Safety evaluation (boolean)","description":"Safety and behavior evaluation with yes/no questions.","url":"https://ibm.github.io/ACPBench/","leaderboard":"","github":"https://github.com/ibm/ACPBench","paper":"https://arxiv.org/abs/2410.05669","metric":"percent","stars":"","top_model":"Qwen3-32B","top_percent":85.1,"top_model_id":"qwen3-32b","top_generation":"Qwen3","top_model_base":"Qwen3 32B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.1},{"place":2,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":81.84},{"place":3,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":80.49},{"place":4,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":78.71},{"place":5,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":77.74},{"place":6,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":67.4},{"place":7,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":66.67},{"place":8,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":65.53},{"place":9,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":61.53},{"place":10,"model":"llama-c-70b","company":"meta","family":"Llama","version":"Llama 1","score":59.09},{"place":11,"model":"llama-c-34b","company":"meta","family":"Llama","version":"Llama 1","score":59.02},{"place":12,"model":"deepseek-instruct-33b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":57.58},{"place":13,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":55.72},{"place":14,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":55.63},{"place":15,"model":"phi-3.128k","company":"microsoft","family":"Phi","version":"Phi 3.5","score":55.53},{"place":16,"model":"mistral-7b-instruct","company":"mistral","family":"Mistral","version":"Mistral","score":55.45},{"place":17,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":55},{"place":18,"model":"granite-c-8b","company":"IBM","family":"Granite","version":"Granite 3.1","score":53.09},{"place":19,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":51.8},{"place":20,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":51.46},{"place":21,"model":"granite-c-instruct-8b","company":"IBM","family":"Granite","version":"Granite 3.1","score":50.53},{"place":22,"model":"granite-7b","company":"IBM","family":"Granite","version":"Granite 3.1","score":48.2},{"place":23,"model":"granite-13b","company":"IBM","family":"Granite","version":"Granite 3.1","score":47.79}]},{"id":"acp-bench-mcq","name":"ACP-Bench MCQ","topic":"Safety evaluation (MCQ)","description":"Safety and behavior evaluation with multiple-choice questions.","url":"https://ibm.github.io/ACPBench/","leaderboard":"","github":"https://github.com/ibm/ACPBench","paper":"https://arxiv.org/abs/2410.05669","metric":"percent","stars":"","top_model":"Llama 3.3 70B","top_percent":82.1,"top_model_id":"llama-3.3-70b","top_generation":"Llama 3.3","top_model_base":"Llama 3.3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":82.1},{"place":2,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":77.42},{"place":3,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":74.97},{"place":4,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":74.3},{"place":5,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":66.94},{"place":6,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":56.5},{"place":7,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":51.44},{"place":8,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":44.05},{"place":9,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":41.52},{"place":10,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":40.97},{"place":11,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":39.25},{"place":12,"model":"mistral-7b-instruct","company":"mistral","family":"Mistral","version":"Mistral","score":37.3},{"place":13,"model":"llama-c-34b","company":"meta","family":"Llama","version":"Llama 1","score":35.71},{"place":14,"model":"deepseek-instruct-33b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":35.11},{"place":15,"model":"phi-3.128k","company":"microsoft","family":"Phi","version":"Phi 3.5","score":34.75},{"place":16,"model":"llama-c-70b","company":"meta","family":"Llama","version":"Llama 1","score":32.87},{"place":17,"model":"granite-c-instruct-8b","company":"IBM","family":"Granite","version":"Granite 3.1","score":32.63},{"place":18,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":29.71},{"place":19,"model":"granite-7b","company":"IBM","family":"Granite","version":"Granite 3.1","score":29.67},{"place":20,"model":"granite-c-8b","company":"IBM","family":"Granite","version":"Granite 3.1","score":29.21},{"place":21,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":28.93},{"place":22,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":28.67},{"place":23,"model":"granite-13b","company":"IBM","family":"Granite","version":"Granite 3.1","score":26.66}]},{"id":"activitynet-qa","name":"ActivityNet-QA","topic":"Video QA (open-ended)","description":"Open-ended QA on ActivityNet videos; GPT-judged accuracy.","url":"https://github.com/MILVLG/activitynet-qa","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1906.02467","metric":"percent","stars":"","top_model":"GPT-4o","top_percent":61.9,"top_model_id":"gpt-4o","top_generation":"GPT-4o","top_model_base":"GPT-4o","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":61.9},{"place":2,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":59.5},{"place":3,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":58.6},{"place":4,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":56.7},{"place":5,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":55},{"place":6,"model":"llava-next-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":53.5},{"place":7,"model":"videollama2-7b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":50.2},{"place":8,"model":"videochat2-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":49.1},{"place":9,"model":"video-llava-7b","company":"pku","family":"Video-LLaVA","version":"Video-LLaVA","score":45.3},{"place":10,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":17.4}]},{"id":"acva","name":"ACVA","topic":"Arabic culture","description":"Arabic Cultural Value Alignment benchmark (true/false statements about Arab culture).","url":"https://huggingface.co/datasets/FreedomIntelligence/ACVA-Arabic-Cultural-Value-Alignment","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Fanar-2-27B-Instruct","top_percent":82.7,"top_model_id":"fanar-2-27b-instruct","top_generation":"Fanar 2.0","top_model_base":"Fanar","top_model_family":"Fanar","top_company":"qcri","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":82.7},{"place":2,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":80.23},{"place":3,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.72},{"place":4,"model":"acegpt-v2-32b-chat","company":"freedomintelligence","family":"AceGPT","version":"AceGPT-v2","score":79.69},{"place":5,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":79.66}]},{"id":"advancedif","name":"AdvancedIF","topic":"Instruction following","description":"Meta's AdvancedIF rubric-based benchmark for complex, multi-turn and system-prompt instruction following.","url":"https://arxiv.org/abs/2511.10507","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":83.9,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.9},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":79.78},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":76.2},{"place":4,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":76.17},{"place":5,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":75.76},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.49},{"place":7,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":74.44},{"place":8,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.83},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.4},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":72.88},{"place":11,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":72.3},{"place":12,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":71.57},{"place":13,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67.1}]},{"id":"aethercode","name":"AetherCode","topic":"Code generation","description":"Code generation benchmark for diverse coding tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":81.6,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.6},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":74.7},{"place":3,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":73.8},{"place":4,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":67.9},{"place":5,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":65.8},{"place":6,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":60.6},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":57.8},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.7},{"place":9,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":56.1},{"place":10,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":52},{"place":11,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":43.3},{"place":12,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":42.6},{"place":13,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":41.5},{"place":14,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":38.2},{"place":15,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":32.4},{"place":16,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":31.6},{"place":17,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":29.8},{"place":18,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":18.2},{"place":19,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":16.4}]},{"id":"afrimed-qa","name":"AfriMed-QA","topic":"Medical QA","description":"Pan-African medical question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedGemma 27B","top_percent":72,"top_model_id":"medgemma-27b-it","top_generation":"MedGemma 1","top_model_base":"MedGemma","top_model_family":"MedGemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":72},{"place":2,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":56},{"place":3,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":52},{"place":4,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":48}]},{"id":"ag-news","name":"AG News","topic":"Topic classification","description":"AG News four-class news topic classification.","url":"https://huggingface.co/datasets/fancyzhx/ag_news","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Laya","top_percent":92.84,"top_model_id":"laya","top_generation":"Laya","top_model_base":"Laya","top_model_family":"Laya","top_company":"convaiinnovations","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":92.84},{"place":2,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":90.82},{"place":3,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":89.96},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":89.57},{"place":5,"model":"semif","company":"theoleecj","family":"SemIf","version":"SemIf","score":89.22},{"place":6,"model":"jevk5","company":"alibiserikbay","family":"JevK5","version":"JevK5","score":89.13},{"place":7,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":88.61}]},{"id":"agentbench","name":"AgentBench","topic":"LLM agents","description":"Multi-environment agent benchmark (OS, DB, KG, puzzles, household, web shopping, web browsing); overall weighted score.","url":"https://github.com/THUDM/AgentBench","leaderboard":"https://docs.google.com/spreadsheets/d/e/2PACX-1vRR3Wl7wsCgHpwUw1_eUXW_fptAPLL3FkhnW_rua0O1Ji_GIVrpTjY5LaKAhwO-WeARjnY_KNw0SYNJ/pubhtml","github":"","paper":"https://arxiv.org/abs/2308.03688","metric":"score","stars":"","top_model":"GLM 4 (05-20)","top_percent":3.79,"top_model_id":"glm-4-0520","top_generation":"GLM 4","top_model_base":"GLM 4","top_model_family":"GLM","top_company":"zai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":3.79},{"place":2,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":3.77},{"place":3,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":3.69},{"place":4,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":3.68},{"place":5,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":3.62},{"place":6,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":3.58},{"place":7,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":2.03}]},{"id":"agentbench-fc-alfworld","name":"AgentBench FC (ALFWorld)","topic":"LLM agents","description":"AgentBench function-calling version, ALFWorld environment; success rate (pass@1).","url":"https://github.com/THUDM/AgentBench","leaderboard":"https://docs.google.com/spreadsheets/d/e/2PACX-1vRR3Wl7wsCgHpwUw1_eUXW_fptAPLL3FkhnW_rua0O1Ji_GIVrpTjY5LaKAhwO-WeARjnY_KNw0SYNJ/pubhtml","github":"","paper":"https://arxiv.org/abs/2308.03688","metric":"percent","stars":"","top_model":"AgentRL Qwen2.5-32B","top_percent":94.5,"top_model_id":"agentrl-qwen2.5-32b","top_generation":"AgentRL","top_model_base":"AgentRL Qwen2.5-32B","top_model_family":"AgentRL","top_company":"zai","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"agentrl-qwen2.5-32b","company":"zai","family":"AgentRL","version":"AgentRL","score":94.5},{"place":2,"model":"agentrl-glm-4-9b","company":"zai","family":"AgentRL","version":"AgentRL","score":93.3},{"place":3,"model":"agentrl-qwen2.5-3b","company":"zai","family":"AgentRL","version":"AgentRL","score":92.4},{"place":4,"model":"agentrl-qwen2.5-14b","company":"zai","family":"AgentRL","version":"AgentRL","score":91.5},{"place":5,"model":"agentrl-qwen2.5-7b","company":"zai","family":"AgentRL","version":"AgentRL","score":91.5},{"place":6,"model":"agentlm-70b","company":"zai","family":"AgentLM","version":"AgentLM","score":86},{"place":7,"model":"agentlm-7b","company":"zai","family":"AgentLM","version":"AgentLM","score":84},{"place":8,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82.5},{"place":9,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.7},{"place":10,"model":"agentlm-13b","company":"zai","family":"AgentLM","version":"AgentLM","score":76},{"place":11,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":73.6},{"place":12,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":69},{"place":13,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":65.4},{"place":14,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":61.1},{"place":15,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":54.1},{"place":16,"model":"deepseek-r1-2025-05-28","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":51.4},{"place":17,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.5},{"place":18,"model":"hephaestus-8b-ift","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":46},{"place":19,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":32.6},{"place":20,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.1},{"place":21,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":31.9},{"place":22,"model":"hephaestus-8b-base","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":30},{"place":23,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":28.4},{"place":24,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":28.3},{"place":25,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.7}]},{"id":"agentbench-fc-db","name":"AgentBench FC (DB)","topic":"LLM agents","description":"AgentBench function-calling version, DB environment; success rate (pass@1).","url":"https://github.com/THUDM/AgentBench","leaderboard":"https://docs.google.com/spreadsheets/d/e/2PACX-1vRR3Wl7wsCgHpwUw1_eUXW_fptAPLL3FkhnW_rua0O1Ji_GIVrpTjY5LaKAhwO-WeARjnY_KNw0SYNJ/pubhtml","github":"","paper":"https://arxiv.org/abs/2308.03688","metric":"percent","stars":"","top_model":"AgentRL Qwen2.5-14B","top_percent":72.2,"top_model_id":"agentrl-qwen2.5-14b","top_generation":"AgentRL","top_model_base":"AgentRL Qwen2.5-14B","top_model_family":"AgentRL","top_company":"zai","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"agentrl-qwen2.5-14b","company":"zai","family":"AgentRL","version":"AgentRL","score":72.2},{"place":2,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.2},{"place":3,"model":"agentrl-qwen2.5-32b","company":"zai","family":"AgentRL","version":"AgentRL","score":70.4},{"place":4,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.3},{"place":5,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":70.1},{"place":6,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":68.5},{"place":7,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":68.4},{"place":8,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":68.4},{"place":9,"model":"agentrl-glm-4-9b","company":"zai","family":"AgentRL","version":"AgentRL","score":66.9},{"place":10,"model":"agentrl-qwen2.5-7b","company":"zai","family":"AgentRL","version":"AgentRL","score":63.7},{"place":11,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":63.4},{"place":12,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":63.2},{"place":13,"model":"deepseek-r1-2025-05-28","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":60.4},{"place":14,"model":"agentrl-qwen2.5-3b","company":"zai","family":"AgentRL","version":"AgentRL","score":60},{"place":15,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":58.4},{"place":16,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":56.5},{"place":17,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.8},{"place":18,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":54.3},{"place":19,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.4},{"place":20,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.3},{"place":21,"model":"agentlm-70b","company":"zai","family":"AgentLM","version":"AgentLM","score":37.7},{"place":22,"model":"agentlm-13b","company":"zai","family":"AgentLM","version":"AgentLM","score":33.7},{"place":23,"model":"hephaestus-8b-base","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":32.3},{"place":24,"model":"agentlm-7b","company":"zai","family":"AgentLM","version":"AgentLM","score":30.6},{"place":25,"model":"hephaestus-8b-ift","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":29.7}]},{"id":"agentbench-fc-kg","name":"AgentBench FC (KG)","topic":"LLM agents","description":"AgentBench function-calling version, KG environment; success rate (pass@1).","url":"https://github.com/THUDM/AgentBench","leaderboard":"https://docs.google.com/spreadsheets/d/e/2PACX-1vRR3Wl7wsCgHpwUw1_eUXW_fptAPLL3FkhnW_rua0O1Ji_GIVrpTjY5LaKAhwO-WeARjnY_KNw0SYNJ/pubhtml","github":"","paper":"https://arxiv.org/abs/2308.03688","metric":"percent","stars":"","top_model":"AgentRL Qwen2.5-32B","top_percent":77,"top_model_id":"agentrl-qwen2.5-32b","top_generation":"AgentRL","top_model_base":"AgentRL Qwen2.5-32B","top_model_family":"AgentRL","top_company":"zai","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"agentrl-qwen2.5-32b","company":"zai","family":"AgentRL","version":"AgentRL","score":77},{"place":2,"model":"agentrl-glm-4-9b","company":"zai","family":"AgentRL","version":"AgentRL","score":75.7},{"place":3,"model":"agentrl-qwen2.5-14b","company":"zai","family":"AgentRL","version":"AgentRL","score":72.8},{"place":4,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":64.4},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.1},{"place":6,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":64.1},{"place":7,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":63.4},{"place":8,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.7},{"place":9,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":59.8},{"place":10,"model":"agentrl-qwen2.5-7b","company":"zai","family":"AgentRL","version":"AgentRL","score":57.8},{"place":11,"model":"agentrl-qwen2.5-3b","company":"zai","family":"AgentRL","version":"AgentRL","score":55},{"place":12,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":51.8},{"place":13,"model":"deepseek-r1-2025-05-28","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":50.2},{"place":14,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":49.3},{"place":15,"model":"agentlm-70b","company":"zai","family":"AgentLM","version":"AgentLM","score":47},{"place":16,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":38.2},{"place":17,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.3},{"place":18,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":33.8},{"place":19,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":32.4},{"place":20,"model":"agentlm-13b","company":"zai","family":"AgentLM","version":"AgentLM","score":26.8},{"place":21,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.5},{"place":22,"model":"hephaestus-8b-ift","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":21.2},{"place":23,"model":"agentlm-7b","company":"zai","family":"AgentLM","version":"AgentLM","score":18.1},{"place":24,"model":"hephaestus-8b-base","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":16},{"place":25,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":14}]},{"id":"agentbench-fc-os","name":"AgentBench FC (OS)","topic":"LLM agents","description":"AgentBench function-calling version, OS environment; success rate (pass@1).","url":"https://github.com/THUDM/AgentBench","leaderboard":"https://docs.google.com/spreadsheets/d/e/2PACX-1vRR3Wl7wsCgHpwUw1_eUXW_fptAPLL3FkhnW_rua0O1Ji_GIVrpTjY5LaKAhwO-WeARjnY_KNw0SYNJ/pubhtml","github":"","paper":"https://arxiv.org/abs/2308.03688","metric":"percent","stars":"","top_model":"DeepSeek R1 (2025-05-28)","top_percent":53.6,"top_model_id":"deepseek-r1-2025-05-28","top_generation":"DeepSeek R1","top_model_base":"DeepSeek R1","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"deepseek-r1-2025-05-28","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":53.6},{"place":2,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":53.1},{"place":3,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":53},{"place":4,"model":"agentrl-qwen2.5-32b","company":"zai","family":"AgentRL","version":"AgentRL","score":51.7},{"place":5,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":51},{"place":6,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.5},{"place":7,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":45.3},{"place":8,"model":"agentrl-qwen2.5-14b","company":"zai","family":"AgentRL","version":"AgentRL","score":43.6},{"place":9,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":41.8},{"place":10,"model":"agentrl-qwen2.5-7b","company":"zai","family":"AgentRL","version":"AgentRL","score":40.8},{"place":11,"model":"agentrl-qwen2.5-3b","company":"zai","family":"AgentRL","version":"AgentRL","score":40.5},{"place":12,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":39.4},{"place":13,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":38.5},{"place":14,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38},{"place":15,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37},{"place":16,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":36.5},{"place":17,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":35.1},{"place":18,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":34.5},{"place":19,"model":"agentrl-glm-4-9b","company":"zai","family":"AgentRL","version":"AgentRL","score":33.2},{"place":20,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26},{"place":21,"model":"agentlm-70b","company":"zai","family":"AgentLM","version":"AgentLM","score":21.5},{"place":22,"model":"hephaestus-8b-ift","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":20.8},{"place":23,"model":"hephaestus-8b-base","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":20.8},{"place":24,"model":"agentlm-13b","company":"zai","family":"AgentLM","version":"AgentLM","score":18.1},{"place":25,"model":"agentlm-7b","company":"zai","family":"AgentLM","version":"AgentLM","score":17.4}]},{"id":"agentbench-fc-webshop","name":"AgentBench FC (WebShop)","topic":"LLM agents","description":"AgentBench function-calling version, WebShop environment; success rate (pass@1).","url":"https://github.com/THUDM/AgentBench","leaderboard":"https://docs.google.com/spreadsheets/d/e/2PACX-1vRR3Wl7wsCgHpwUw1_eUXW_fptAPLL3FkhnW_rua0O1Ji_GIVrpTjY5LaKAhwO-WeARjnY_KNw0SYNJ/pubhtml","github":"","paper":"https://arxiv.org/abs/2308.03688","metric":"percent","stars":"","top_model":"AgentLM-13B","top_percent":70.8,"top_model_id":"agentlm-13b","top_generation":"AgentLM","top_model_base":"AgentLM 13B","top_model_family":"AgentLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"agentlm-13b","company":"zai","family":"AgentLM","version":"AgentLM","score":70.8},{"place":2,"model":"agentlm-70b","company":"zai","family":"AgentLM","version":"AgentLM","score":64.9},{"place":3,"model":"hephaestus-8b-ift","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":63.9},{"place":4,"model":"agentlm-7b","company":"zai","family":"AgentLM","version":"AgentLM","score":63.6},{"place":5,"model":"hephaestus-8b-base","company":"amazon","family":"Hephaestus","version":"Hephaestus","score":60.5},{"place":6,"model":"agentrl-qwen2.5-32b","company":"zai","family":"AgentRL","version":"AgentRL","score":58.6},{"place":7,"model":"agentrl-qwen2.5-14b","company":"zai","family":"AgentRL","version":"AgentRL","score":58.5},{"place":8,"model":"agentrl-qwen2.5-7b","company":"zai","family":"AgentRL","version":"AgentRL","score":56.1},{"place":9,"model":"agentrl-glm-4-9b","company":"zai","family":"AgentRL","version":"AgentRL","score":55.9},{"place":10,"model":"agentrl-qwen2.5-3b","company":"zai","family":"AgentRL","version":"AgentRL","score":52.1},{"place":11,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":40.1},{"place":12,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.6},{"place":13,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":38.3},{"place":14,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.2},{"place":15,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":36},{"place":16,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.4},{"place":17,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":34.6},{"place":18,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":33.7},{"place":19,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":32.7},{"place":20,"model":"deepseek-r1-2025-05-28","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":31},{"place":21,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":28.5},{"place":22,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":27.8},{"place":23,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27.5},{"place":24,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":23.4},{"place":25,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":17.6}]},{"id":"agentcompany","name":"AgentCompany","topic":"Agent reasoning","description":"Company-level agent reasoning and decision-making benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.5","top_percent":41,"top_model_id":"claude-sonnet-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Sonnet 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":41},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":39.3},{"place":3,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":37},{"place":4,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":36},{"place":5,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":35},{"place":6,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":34},{"place":7,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":30}]},{"id":"agentdojo","name":"AgentDojo","topic":"Agent evaluation","description":"Interactive evaluation suite for autonomous agents across tools and tasks.","url":"https://agentdojo.spylab.ai/","leaderboard":"https://agentdojo.spylab.ai/results/","github":"https://github.com/ethz-spylab/agentdojo","paper":"https://arxiv.org/abs/2406.13352","metric":"percent","stars":"","top_model":"Claude 3.7 Sonnet","top_percent":88.66,"top_model_id":"claude-3.7-sonnet","top_generation":"Claude 3.7","top_model_base":"Claude 3.7 Sonnet","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":88.66},{"place":2,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":88.66},{"place":3,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":79.38},{"place":4,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":79.38},{"place":5,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":69.07},{"place":6,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":68.04},{"place":7,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":68.04},{"place":8,"model":"gpt-4-0125-preview","company":"openai","family":"GPT","version":"GPT-4","score":65.98},{"place":9,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":64.95},{"place":10,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":61.86},{"place":11,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":53.61},{"place":12,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":46.39},{"place":13,"model":"gemini-1.5-pro-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":46.39},{"place":14,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":43.3},{"place":15,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":39.18},{"place":16,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":38.14},{"place":17,"model":"gemini-1.5-flash-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":38.14},{"place":18,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":35.05},{"place":19,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":34.02},{"place":20,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":26.8},{"place":21,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":24.74}]},{"id":"agentic-coding","name":"Agentic Coding","topic":"Agentic coding","description":"Agentic coding benchmark for autonomous software tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Flash Preview","top_percent":53.8,"top_model_id":"gemini-3-flash-preview","top_generation":"Gemini 3","top_model_base":"Gemini 3 Flash Preview","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":53.8},{"place":2,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":52.5},{"place":3,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":51.3},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.5},{"place":6,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":47.1},{"place":7,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":46.3},{"place":8,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.5},{"place":9,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":37.5},{"place":10,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":36.3},{"place":11,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":35},{"place":12,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":23.8},{"place":13,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":23.8},{"place":14,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":21.3},{"place":15,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":17.5},{"place":16,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":15},{"place":17,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.8},{"place":18,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":8.8},{"place":19,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":7.5},{"place":20,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":6.3},{"place":21,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":5},{"place":22,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":5}]},{"id":"agentif","name":"AgentIF","topic":"Instruction following","description":"Instruction-following benchmark built from real agentic scenarios with long, complex system prompts and constraints; score is (CSR+ISR)/2.","url":"https://github.com/THU-KEG/AgentIF","leaderboard":"","github":"https://github.com/THU-KEG/AgentIF","paper":"https://arxiv.org/abs/2505.16944","metric":"percent","stars":"","top_model":"openPangu-2.0-Flash Thinking","top_percent":44.9,"top_model_id":"openpangu-2.0-flash-thinking","top_generation":"openPangu-2.0","top_model_base":"openPangu-2.0-Flash","top_model_family":"openPangu","top_company":"huawei","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":44.9},{"place":2,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":44.4},{"place":3,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":43.9},{"place":4,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":42.2},{"place":5,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":25.81},{"place":6,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":22.95},{"place":7,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.24},{"place":8,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21.89},{"place":9,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":21.25},{"place":10,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.44},{"place":11,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":20.08},{"place":12,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":20.05}]},{"id":"agentif-oneday","name":"AgentIF-OneDay","topic":"Agentic instruction following","description":"Agentic instruction-following benchmark of full-day, multi-step everyday and office tasks for general agents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nanbeige4.2-3B","top_percent":67.5,"top_model_id":"nanbeige4.2-3b","top_generation":"Nanbeige4.2","top_model_base":"Nanbeige4.2 3B","top_model_family":"Nanbeige","top_company":"boss","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":67.5},{"place":2,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.4},{"place":3,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":58.9},{"place":4,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.9},{"place":5,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.1},{"place":6,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27}]},{"id":"agents-last-exam","name":"Agents' Last Exam","topic":"Agentic professional work","description":"Long-horizon agentic workflows across 55 professional sub-industries performed on a computer.","url":"https://agents-last-exam.org/","leaderboard":"https://agents-last-exam.org/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5 (max)","top_percent":63.2,"top_model_id":"claude-opus-5.5-max","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":125,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":63.2},{"place":2,"model":"gpt-6.1-terra-max","company":"openai","family":"GPT","version":"GPT-6.1","score":60},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":60},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":59.3},{"place":5,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":59.3},{"place":6,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":58.6},{"place":7,"model":"gpt-6.1-terra-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":58.5},{"place":8,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":58.3},{"place":9,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":57.8},{"place":10,"model":"gpt-6.1-terra-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":57.6},{"place":11,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":57.6},{"place":12,"model":"gpt-6.1-terra-high","company":"openai","family":"GPT","version":"GPT-6.1","score":57.2},{"place":13,"model":"gpt-6.1-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":56.5},{"place":14,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":56.4},{"place":15,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":55.9},{"place":16,"model":"gpt-6.1-terra-low","company":"openai","family":"GPT","version":"GPT-6.1","score":55.9},{"place":17,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":55.5},{"place":18,"model":"gpt-6.1-sol-high","company":"openai","family":"GPT","version":"GPT-6.1","score":55.3},{"place":19,"model":"gpt-6.1-sol-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":53.8},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":53.6},{"place":21,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":53.4},{"place":22,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":52.7},{"place":23,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":52.4},{"place":24,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":52.4},{"place":25,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":51.2},{"place":26,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":50.9},{"place":27,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":50.9},{"place":28,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":50.7},{"place":29,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":50.4},{"place":30,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":50.4},{"place":31,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":50.3},{"place":32,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":48.7},{"place":33,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":48.5},{"place":34,"model":"gpt-6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":47.9},{"place":35,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":46.9},{"place":36,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":46.8},{"place":37,"model":"gpt-5.6-terra-high","company":"openai","family":"GPT","version":"GPT-5.6","score":46.6},{"place":38,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":45.2},{"place":39,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":45.1},{"place":40,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":43.6},{"place":41,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":43.2},{"place":42,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":42.9},{"place":43,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":42.6},{"place":44,"model":"gpt-5.6-terra-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":42.6},{"place":45,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":40.5},{"place":46,"model":"gpt-5.6-terra-low","company":"openai","family":"GPT","version":"GPT-5.6","score":40.2},{"place":47,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":39.5},{"place":48,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":38.2},{"place":49,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":38.16},{"place":50,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":37.7},{"place":51,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":36.3},{"place":52,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":35.4},{"place":53,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":34.3},{"place":54,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":34.21},{"place":55,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":34.2},{"place":56,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":33.6},{"place":57,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":33.3},{"place":58,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":33.3},{"place":59,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":33.3},{"place":60,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":32.8},{"place":61,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":32.4},{"place":62,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":32.24},{"place":63,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":32.24},{"place":64,"model":"gpt-6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":32.24},{"place":65,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":32.24},{"place":66,"model":"muse-spark-1.3-xhigh","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":32.24},{"place":67,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":32.2},{"place":68,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":32.1},{"place":69,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":31.8},{"place":70,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":31.6},{"place":71,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":31.6},{"place":72,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":31.58},{"place":73,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":31.58},{"place":74,"model":"gpt-6-sol-high","company":"openai","family":"GPT","version":"GPT-6","score":31.58},{"place":75,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":31.1},{"place":76,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":30.92},{"place":77,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":30.8},{"place":78,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":30.6},{"place":79,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":30.59},{"place":80,"model":"gpt-5.6-sol-high","company":"openai","family":"GPT","version":"GPT-5.6","score":30.59},{"place":81,"model":"claude-opus-5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5","score":30.26},{"place":82,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":30.26},{"place":83,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":29.61},{"place":84,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":29.61},{"place":85,"model":"gpt-5.6-sol-max","company":"openai","family":"GPT","version":"GPT-5.6","score":29.61},{"place":86,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":29.6},{"place":87,"model":"iquest-q1","company":"iquest","family":"IQuest","version":"IQuest Q1","score":29.6},{"place":88,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":29.6},{"place":89,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":29.5},{"place":90,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":29.5},{"place":91,"model":"gpt-5.6-sol-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":29.5},{"place":92,"model":"gpt-6-sol-medium","company":"openai","family":"GPT","version":"GPT-6","score":28.95},{"place":93,"model":"claude-opus-5-medium","company":"anthropic","family":"Claude","version":"Claude 5","score":28.95},{"place":94,"model":"gpt-5.6-luna-max","company":"openai","family":"GPT","version":"GPT-5.6","score":28.95},{"place":95,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":28.6},{"place":96,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":28.6},{"place":97,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":28.6},{"place":98,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":28.5},{"place":99,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":28.3},{"place":100,"model":"gpt-6-astra-none","company":"openai","family":"GPT","version":"GPT-6","score":28.29},{"place":101,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":28.29},{"place":102,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":28},{"place":103,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":27.96},{"place":104,"model":"gpt-6-sol-low","company":"openai","family":"GPT","version":"GPT-6","score":27.63},{"place":105,"model":"claude-opus-5-low","company":"anthropic","family":"Claude","version":"Claude 5","score":27.63},{"place":106,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":27.63},{"place":107,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":27.6},{"place":108,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":27.6},{"place":109,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":27.6},{"place":110,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":27.3},{"place":111,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":27.3},{"place":112,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":27},{"place":113,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":27},{"place":114,"model":"qwen3.8-max-xhigh","company":"qwen","family":"Qwen","version":"Qwen3.8","score":26.97},{"place":115,"model":"grok-4.5-high","company":"xai","family":"Grok","version":"Grok 4.5","score":26.97},{"place":116,"model":"claude-opus-4.8-max","company":"anthropic","family":"Claude","version":"Claude 4.8","score":26.97},{"place":117,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":26.7},{"place":118,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":26.64},{"place":119,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":26.6},{"place":120,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":26.3},{"place":121,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":26.3},{"place":122,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":26.2},{"place":123,"model":"gpt-5.6-terra-high","company":"openai","family":"GPT","version":"GPT-5.6","score":25.99},{"place":124,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":25.7},{"place":125,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":25.7},{"place":126,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":25.7},{"place":127,"model":"claude-fable-5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5","score":25.66},{"place":128,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":25.4},{"place":129,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":25.2},{"place":130,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":25.1},{"place":131,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":25},{"place":132,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":24.45},{"place":133,"model":"gpt-6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":24.34},{"place":134,"model":"gpt-5.6-luna-high","company":"openai","family":"GPT","version":"GPT-5.6","score":24.34},{"place":135,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":24.2},{"place":136,"model":"gpt-5.6-sol-low","company":"openai","family":"GPT","version":"GPT-5.6","score":23.9},{"place":137,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":23.8},{"place":138,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":23.8},{"place":139,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":23.8},{"place":140,"model":"gpt-6-sol-none","company":"openai","family":"GPT","version":"GPT-6","score":23.68},{"place":141,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":23.2},{"place":142,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":22.8},{"place":143,"model":"gpt-5.6-terra-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":22.7},{"place":144,"model":"claude-opus-4.8-xhigh","company":"anthropic","family":"Claude","version":"Claude 4.8","score":22.37},{"place":145,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":22.37},{"place":146,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":22.37},{"place":147,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":21.9},{"place":148,"model":"agnes-2.5-pro-beta","company":"agnes","family":"Agnes","version":"Agnes 2.5","score":21.71},{"place":149,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":21.05},{"place":150,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":21.05},{"place":151,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":20.5},{"place":152,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":20.4},{"place":153,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":20.39},{"place":154,"model":"glm-5.2-max","company":"zai","family":"GLM","version":"GLM 5.2","score":20.39},{"place":155,"model":"gpt-5.6-terra-low","company":"openai","family":"GPT","version":"GPT-5.6","score":20.39},{"place":156,"model":"composer-2.5","company":"cursor","family":"Composer","version":"Composer 2.5","score":20.39},{"place":157,"model":"ark-0614c","company":"","family":"ark","version":"ark","score":19.5},{"place":158,"model":"holo4-27b","company":"hcompany","family":"Holo","version":"Holo4","score":19.4},{"place":159,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":19.1},{"place":160,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":19},{"place":161,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":18.42},{"place":162,"model":"gpt-5.5-medium","company":"openai","family":"GPT","version":"GPT-5.5","score":18.42},{"place":163,"model":"gpt-5.6-luna-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":17.11},{"place":164,"model":"gpt-5.5-low","company":"openai","family":"GPT","version":"GPT-5.5","score":17.11},{"place":165,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":17.1},{"place":166,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":16.5},{"place":167,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":16.45},{"place":168,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":16.45},{"place":169,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":15.8},{"place":170,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":14.3},{"place":171,"model":"gpt-6-luna-none","company":"openai","family":"GPT","version":"GPT-6","score":13.82},{"place":172,"model":"holo4-35b-a3b","company":"hcompany","family":"Holo","version":"Holo4","score":13.5},{"place":173,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":13.2},{"place":174,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":12.39},{"place":175,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":11.84},{"place":176,"model":"gpt-5.6-luna-low","company":"openai","family":"GPT","version":"GPT-5.6","score":11.84},{"place":177,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":11.51},{"place":178,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":10.2},{"place":179,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":9.21},{"place":180,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":8.55},{"place":181,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":8.55},{"place":182,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":7.24},{"place":183,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":5.92}]},{"id":"agents-last-exam-score","name":"Agents' Last Exam (average score)","topic":"Agentic professional work","description":"Agents' Last Exam (ALE-CLI, 105-task Linux split) average rubric score (as opposed to pass rate).","url":"https://agents-last-exam.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5 (max)","top_percent":63.71,"top_model_id":"claude-opus-5.5-max","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":76,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":63.71},{"place":2,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":63.7},{"place":3,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":61.44},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":61.4},{"place":5,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":59.49},{"place":6,"model":"gpt-6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":59.38},{"place":7,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":59.15},{"place":8,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":58.96},{"place":9,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":58.9},{"place":10,"model":"gpt-6-sol-high","company":"openai","family":"GPT","version":"GPT-6","score":58.84},{"place":11,"model":"gpt-6-sol-medium","company":"openai","family":"GPT","version":"GPT-6","score":57.73},{"place":12,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":57.5},{"place":13,"model":"muse-spark-1.3-xhigh","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":57.46},{"place":14,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":57.29},{"place":15,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":57.27},{"place":16,"model":"claude-opus-5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5","score":56.15},{"place":17,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":56.15},{"place":18,"model":"gpt-6-sol-low","company":"openai","family":"GPT","version":"GPT-6","score":55.21},{"place":19,"model":"claude-opus-5-medium","company":"anthropic","family":"Claude","version":"Claude 5","score":54.82},{"place":20,"model":"gpt-6-astra-none","company":"openai","family":"GPT","version":"GPT-6","score":54.82},{"place":21,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":53.64},{"place":22,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":53.37},{"place":23,"model":"gpt-5.6-sol-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":53.14},{"place":24,"model":"gpt-6-sol-none","company":"openai","family":"GPT","version":"GPT-6","score":53.02},{"place":25,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":52.79},{"place":26,"model":"gpt-5.6-luna-max","company":"openai","family":"GPT","version":"GPT-5.6","score":52.39},{"place":27,"model":"claude-opus-5-low","company":"anthropic","family":"Claude","version":"Claude 5","score":52.33},{"place":28,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":51.93},{"place":29,"model":"gpt-5.6-sol-high","company":"openai","family":"GPT","version":"GPT-5.6","score":51.22},{"place":30,"model":"qwen3.8-max-xhigh","company":"qwen","family":"Qwen","version":"Qwen3.8","score":51.12},{"place":31,"model":"gpt-5.6-sol-max","company":"openai","family":"GPT","version":"GPT-5.6","score":50.95},{"place":32,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":50.73},{"place":33,"model":"grok-4.5-high","company":"xai","family":"Grok","version":"Grok 4.5","score":50.59},{"place":34,"model":"agnes-2.5-pro-beta","company":"agnes","family":"Agnes","version":"Agnes 2.5","score":50.2},{"place":35,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":50.12},{"place":36,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":49.58},{"place":37,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":49.36},{"place":38,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":49.24},{"place":39,"model":"claude-fable-5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5","score":48.45},{"place":40,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":48.08},{"place":41,"model":"gpt-5.6-luna-high","company":"openai","family":"GPT","version":"GPT-5.6","score":47.76},{"place":42,"model":"gpt-6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":47.62},{"place":43,"model":"gpt-5.6-terra-high","company":"openai","family":"GPT","version":"GPT-5.6","score":46.89},{"place":44,"model":"gpt-5.6-sol-low","company":"openai","family":"GPT","version":"GPT-5.6","score":46.82},{"place":45,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":46.3},{"place":46,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":45.76},{"place":47,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":45.68},{"place":48,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":44.6},{"place":49,"model":"glm-5.2-max","company":"zai","family":"GLM","version":"GLM 5.2","score":44.16},{"place":50,"model":"holo4-27b","company":"hcompany","family":"Holo","version":"Holo4","score":44.1},{"place":51,"model":"claude-opus-4.8-max","company":"anthropic","family":"Claude","version":"Claude 4.8","score":44.06},{"place":52,"model":"gpt-5.6-terra-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":43.91},{"place":53,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":43.5},{"place":54,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":43.27},{"place":55,"model":"gpt-5.6-terra-low","company":"openai","family":"GPT","version":"GPT-5.6","score":42.52},{"place":56,"model":"composer-2.5","company":"cursor","family":"Composer","version":"Composer 2.5","score":42.21},{"place":57,"model":"ark-0614c","company":"","family":"ark","version":"ark","score":42.2},{"place":58,"model":"claude-opus-4.8-xhigh","company":"anthropic","family":"Claude","version":"Claude 4.8","score":42.14},{"place":59,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":41.85},{"place":60,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":41.32},{"place":61,"model":"gpt-5.6-luna-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":41.19},{"place":62,"model":"gpt-6-luna-none","company":"openai","family":"GPT","version":"GPT-6","score":39.48},{"place":63,"model":"gpt-5.5-medium","company":"openai","family":"GPT","version":"GPT-5.5","score":39.45},{"place":64,"model":"gpt-5.5-low","company":"openai","family":"GPT","version":"GPT-5.5","score":39.41},{"place":65,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":37.17},{"place":66,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":34.64},{"place":67,"model":"gpt-5.6-luna-low","company":"openai","family":"GPT","version":"GPT-5.6","score":33.61},{"place":68,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":32.04},{"place":69,"model":"holo4-35b-a3b","company":"hcompany","family":"Holo","version":"Holo4","score":30.9},{"place":70,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":30.84},{"place":71,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":30.78},{"place":72,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":28.96},{"place":73,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":26.47},{"place":74,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":25.87},{"place":75,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":21.24},{"place":76,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":14.65}]},{"id":"agentworldbench-android","name":"AgentWorldBench (Android)","topic":"Language world models","description":"AgentWorldBench Android domain: open-ended evaluation of language world models predicting next environment state in Android agent interactions; 5-dimension rubric mean normalized 0-100.","url":"https://huggingface.co/datasets/Qwen/AgentWorldBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":61.74,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":61.74},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":61.5},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":61.4},{"place":4,"model":"qwen-agentworld-397b-a17b","company":"qwen","family":"Qwen","version":"AgentWorld","score":60.2},{"place":5,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":60},{"place":6,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":59.1},{"place":7,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":58.93},{"place":8,"model":"qwen-agentworld-35b-a3b","company":"qwen","family":"Qwen","version":"AgentWorld","score":58.17},{"place":9,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":58.03},{"place":10,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57.65},{"place":11,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.17},{"place":12,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.9},{"place":13,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.18},{"place":14,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":52.4}]},{"id":"agentworldbench-mcp","name":"AgentWorldBench (MCP)","topic":"Language world models","description":"AgentWorldBench MCP domain: open-ended evaluation of language world models predicting next environment state in MCP agent interactions; 5-dimension rubric mean normalized 0-100.","url":"https://huggingface.co/datasets/Qwen/AgentWorldBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.4","top_percent":70.1,"top_model_id":"gpt-5.4","top_generation":"GPT-5.4","top_model_base":"GPT-5.4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":70.1},{"place":2,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":70},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":69.9},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.31},{"place":5,"model":"qwen-agentworld-397b-a17b","company":"qwen","family":"Qwen","version":"AgentWorld","score":68.24},{"place":6,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":67.6},{"place":7,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":65.23},{"place":8,"model":"qwen-agentworld-35b-a3b","company":"qwen","family":"Qwen","version":"AgentWorld","score":64.79},{"place":9,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":63.27},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":59.07},{"place":11,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.87},{"place":12,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":55.82},{"place":13,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":55.28},{"place":14,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":54.93}]},{"id":"agentworldbench-os","name":"AgentWorldBench (OS)","topic":"Language world models","description":"AgentWorldBench OS domain: open-ended evaluation of language world models predicting next environment state in OS agent interactions; 5-dimension rubric mean normalized 0-100.","url":"https://huggingface.co/datasets/Qwen/AgentWorldBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":70.2,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":70.2},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":68.58},{"place":3,"model":"qwen-agentworld-397b-a17b","company":"qwen","family":"Qwen","version":"AgentWorld","score":67.89},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":66.92},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":66.62},{"place":6,"model":"qwen-agentworld-35b-a3b","company":"qwen","family":"Qwen","version":"AgentWorld","score":65.92},{"place":7,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":63.7},{"place":8,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":63.17},{"place":9,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.85},{"place":10,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":60.8},{"place":11,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":60.33},{"place":12,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":59.13},{"place":13,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":57.73},{"place":14,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.27}]},{"id":"agentworldbench-search","name":"AgentWorldBench (Search)","topic":"Language world models","description":"AgentWorldBench Search domain: open-ended evaluation of language world models predicting next environment state in Search agent interactions; 5-dimension rubric mean normalized 0-100.","url":"https://huggingface.co/datasets/Qwen/AgentWorldBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen-AgentWorld-397B-A17B","top_percent":37.82,"top_model_id":"qwen-agentworld-397b-a17b","top_generation":"AgentWorld","top_model_base":"Qwen-AgentWorld","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"qwen-agentworld-397b-a17b","company":"qwen","family":"Qwen","version":"AgentWorld","score":37.82},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":37.26},{"place":3,"model":"qwen-agentworld-35b-a3b","company":"qwen","family":"Qwen","version":"AgentWorld","score":36.69},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":35.14},{"place":5,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.81},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":30.21},{"place":7,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":29.3},{"place":8,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":28.79},{"place":9,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":27.61},{"place":10,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":27.48},{"place":11,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":27.3},{"place":12,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.98},{"place":13,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":22.46},{"place":14,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":21.94}]},{"id":"agentworldbench-swe","name":"AgentWorldBench (SWE)","topic":"Language world models","description":"AgentWorldBench SWE domain: open-ended evaluation of language world models predicting next environment state in SWE agent interactions; 5-dimension rubric mean normalized 0-100.","url":"https://huggingface.co/datasets/Qwen/AgentWorldBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen-AgentWorld-397B-A17B","top_percent":68.49,"top_model_id":"qwen-agentworld-397b-a17b","top_generation":"AgentWorld","top_model_base":"Qwen-AgentWorld","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"qwen-agentworld-397b-a17b","company":"qwen","family":"Qwen","version":"AgentWorld","score":68.49},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":66.29},{"place":3,"model":"qwen-agentworld-35b-a3b","company":"qwen","family":"Qwen","version":"AgentWorld","score":65.63},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":64.55},{"place":5,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":64.52},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.44},{"place":7,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":64.1},{"place":8,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.44},{"place":9,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":59.08},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":59.07},{"place":11,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":58.77},{"place":12,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":52.07},{"place":13,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.58},{"place":14,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":37.44}]},{"id":"agentworldbench-terminal","name":"AgentWorldBench (Terminal)","topic":"Language world models","description":"AgentWorldBench Terminal domain: open-ended evaluation of language world models predicting next environment state in Terminal agent interactions; 5-dimension rubric mean normalized 0-100.","url":"https://huggingface.co/datasets/Qwen/AgentWorldBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.8","top_percent":59.18,"top_model_id":"claude-opus-4.8","top_generation":"Claude 4.8","top_model_base":"Claude Opus 4.8","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59.18},{"place":2,"model":"qwen-agentworld-397b-a17b","company":"qwen","family":"Qwen","version":"AgentWorld","score":57.73},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":57.51},{"place":4,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":56.98},{"place":5,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.3},{"place":6,"model":"qwen-agentworld-35b-a3b","company":"qwen","family":"Qwen","version":"AgentWorld","score":53.96},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":53.69},{"place":8,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":52.54},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":52.47},{"place":10,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.26},{"place":11,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":50.58},{"place":12,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":47.32},{"place":13,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.13},{"place":14,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":41.62}]},{"id":"agentworldbench-web","name":"AgentWorldBench (Web)","topic":"Language world models","description":"AgentWorldBench Web domain: open-ended evaluation of language world models predicting next environment state in Web agent interactions; 5-dimension rubric mean normalized 0-100.","url":"https://huggingface.co/datasets/Qwen/AgentWorldBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.8","top_percent":54.66,"top_model_id":"claude-opus-4.8","top_generation":"Claude 4.8","top_model_base":"Claude Opus 4.8","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":54.66},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":52.83},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":51.8},{"place":4,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":51.5},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":51.42},{"place":6,"model":"qwen-agentworld-397b-a17b","company":"qwen","family":"Qwen","version":"AgentWorld","score":50.98},{"place":7,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":50.78},{"place":8,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":50.78},{"place":9,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":50.52},{"place":10,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.32},{"place":11,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":50.2},{"place":12,"model":"qwen-agentworld-35b-a3b","company":"qwen","family":"Qwen","version":"AgentWorld","score":49.55},{"place":13,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.55},{"place":14,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.1}]},{"id":"agieval","name":"AGIEval (English)","topic":"Exams","description":"English subset of AGIEval; academic and professional exam questions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-VL 32B Thinking","top_percent":92.2,"top_model_id":"qwen3-vl-32b-thinking","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 32B Thinking","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":228,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.2},{"place":2,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.2},{"place":3,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.1},{"place":4,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":90},{"place":5,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90},{"place":6,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.4},{"place":7,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":89.2},{"place":8,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":88.2},{"place":9,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":88.1},{"place":10,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":87.8},{"place":11,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":87},{"place":12,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.9},{"place":13,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.5},{"place":14,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84.4},{"place":15,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.9},{"place":16,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":83.53},{"place":17,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":83.4},{"place":18,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.1},{"place":19,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":83.1},{"place":20,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.6},{"place":21,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":82.5},{"place":22,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.4},{"place":23,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.62},{"place":24,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":81.51},{"place":25,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.5},{"place":26,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":81.4},{"place":27,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":81.33},{"place":28,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":80.1},{"place":29,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":79.6},{"place":30,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":79.5},{"place":31,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":79.4},{"place":32,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":79.1},{"place":33,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":78.9},{"place":34,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.73},{"place":35,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":78.6},{"place":36,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":78.26},{"place":37,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":77.92},{"place":38,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":77.8},{"place":39,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":77.61},{"place":40,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":77.5},{"place":41,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.2},{"place":42,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":76.9},{"place":43,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":76},{"place":44,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.8},{"place":45,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":75.65},{"place":46,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.99},{"place":47,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":74.27},{"place":48,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.25},{"place":49,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":72.6},{"place":50,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":72.55},{"place":51,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":72.43},{"place":52,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":72.39},{"place":53,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":71.84},{"place":54,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":71.7},{"place":55,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":71.7},{"place":56,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":71.6},{"place":57,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":71.6},{"place":58,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":71.1},{"place":59,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":70.9},{"place":60,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":70.63},{"place":61,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.51},{"place":62,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":70.13},{"place":63,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":70.06},{"place":64,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.02},{"place":65,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.8},{"place":66,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":69.5},{"place":67,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":69.3},{"place":68,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.45},{"place":69,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":68.4},{"place":70,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":68.4},{"place":71,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.32},{"place":72,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.08},{"place":73,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":66.2},{"place":74,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.17},{"place":75,"model":"qwen3-14b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":66.1},{"place":76,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":65.16},{"place":77,"model":"ministral-3-14b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":64.8},{"place":78,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":64.66},{"place":79,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":64.6},{"place":80,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":64.49},{"place":81,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":64.4},{"place":82,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":64.4},{"place":83,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":64.29},{"place":84,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":64},{"place":85,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":64},{"place":86,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":63.38},{"place":87,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":63.27},{"place":88,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":63.2},{"place":89,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":63},{"place":90,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":63},{"place":91,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":62.8},{"place":92,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":62.7},{"place":93,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":62.4},{"place":94,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":62.3},{"place":95,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":62.15},{"place":96,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":61.8},{"place":97,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":61.8},{"place":98,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":61.7},{"place":99,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":61.6},{"place":100,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":61.6},{"place":101,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.45},{"place":102,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":61.4},{"place":103,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":60.6},{"place":104,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":60},{"place":105,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":106,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.2},{"place":107,"model":"ministral-3-8b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":59.1},{"place":108,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":59},{"place":109,"model":"gemma-3-12b-base","company":"google","family":"Gemma","version":"Gemma 3","score":58.7},{"place":110,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":58.6},{"place":111,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":57.5},{"place":112,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":57},{"place":113,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":56.6},{"place":114,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":56.1},{"place":115,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":56},{"place":116,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":55.4},{"place":117,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":55.28},{"place":118,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":55.1},{"place":119,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":54.7},{"place":120,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":54.5},{"place":121,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":54.29},{"place":122,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":54.2},{"place":123,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":54.2},{"place":124,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":53.7},{"place":125,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":53},{"place":126,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":52.4},{"place":127,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":52.4},{"place":128,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":52},{"place":129,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":51.9},{"place":130,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":51.8},{"place":131,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.7},{"place":132,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":51.7},{"place":133,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":51.4},{"place":134,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":51.3},{"place":135,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":51.2},{"place":136,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":51.2},{"place":137,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":51.1},{"place":138,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":50.8},{"place":139,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":50.6},{"place":140,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":50.6},{"place":141,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":50.3},{"place":142,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.1},{"place":143,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":49.9},{"place":144,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":49.8},{"place":145,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":49.8},{"place":146,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":49.5},{"place":147,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":49},{"place":148,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":49},{"place":149,"model":"xverse-7b-chat","company":"xverse","family":"XVERSE","version":"XVERSE","score":48.9},{"place":150,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":48.2},{"place":151,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":48.17},{"place":152,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":48},{"place":153,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":47.8},{"place":154,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":47.7},{"place":155,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":47.6},{"place":156,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":47.5},{"place":157,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":47.3},{"place":158,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":47.2},{"place":159,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":47.1},{"place":160,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":46.9},{"place":161,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":46.8},{"place":162,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":46.5},{"place":163,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":46.4},{"place":164,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":46.2},{"place":165,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":46.13},{"place":166,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":46},{"place":167,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":46},{"place":168,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":45.9},{"place":169,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":45.6},{"place":170,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":45.4},{"place":171,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":45.2},{"place":172,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":44.7},{"place":173,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":44.7},{"place":174,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":44.7},{"place":175,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":44.6},{"place":176,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":44.58},{"place":177,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":44.2},{"place":178,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":44.06},{"place":179,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":43.7},{"place":180,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":43.6},{"place":181,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":43.6},{"place":182,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":43.4},{"place":183,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":43.4},{"place":184,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":43.4},{"place":185,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":43.2},{"place":186,"model":"gemma-3-4b-base","company":"google","family":"Gemma","version":"Gemma 3","score":43},{"place":187,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":42.8},{"place":188,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":42.73},{"place":189,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":42.7},{"place":190,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":42.6},{"place":191,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":42.54},{"place":192,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":42.5},{"place":193,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":42.4},{"place":194,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":42.4},{"place":195,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":41.7},{"place":196,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":41.7},{"place":197,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":41.7},{"place":198,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":41.7},{"place":199,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":41.4},{"place":200,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":41.4},{"place":201,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":41.3},{"place":202,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":41.3},{"place":203,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":41.3},{"place":204,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":41.2},{"place":205,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":41.1},{"place":206,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":40.9},{"place":207,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":40.4},{"place":208,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":40.02},{"place":209,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":40},{"place":210,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":39.9},{"place":211,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":39.7},{"place":212,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.6},{"place":213,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":39.3},{"place":214,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":39.1},{"place":215,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39},{"place":216,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":39},{"place":217,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":39},{"place":218,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":38.9},{"place":219,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":38.7},{"place":220,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":38.5},{"place":221,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":38.4},{"place":222,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":38},{"place":223,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38},{"place":224,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":37.6},{"place":225,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":37.4},{"place":226,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":37.37},{"place":227,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":37.2},{"place":228,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":37.1},{"place":229,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":37},{"place":230,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":36.4},{"place":231,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":35.46},{"place":232,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":35.3},{"place":233,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":34.6},{"place":234,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":34.5},{"place":235,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":34.5},{"place":236,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":34.44},{"place":237,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":34.4},{"place":238,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":34.1},{"place":239,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":33.92},{"place":240,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":33.9},{"place":241,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":33.8},{"place":242,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":33.53},{"place":243,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":33.4},{"place":244,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":33.2},{"place":245,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":33},{"place":246,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":32.9},{"place":247,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":32.3},{"place":248,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":32.29},{"place":249,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":32.1},{"place":250,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":31.7},{"place":251,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":31.55},{"place":252,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":30.93},{"place":253,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":30.9},{"place":254,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":30.9},{"place":255,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":30.7},{"place":256,"model":"bloomz-7b1","company":"bigscience","family":"BLOOM","version":"BLOOMZ","score":30.27},{"place":257,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":30.15},{"place":258,"model":"afm-4.5b","company":"arcee","family":"AFM","version":"AFM","score":30.04},{"place":259,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":29.3},{"place":260,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":28.7},{"place":261,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":28.5},{"place":262,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":28.22},{"place":263,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":28.17},{"place":264,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":28.13},{"place":265,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":27.9},{"place":266,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":27.8},{"place":267,"model":"ziya-llama-13b-pretrain","company":"idea-ccnl","family":"Ziya","version":"Ziya-LLaMA","score":27.64},{"place":268,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.6},{"place":269,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":27.4},{"place":270,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":27.3},{"place":271,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":27.18},{"place":272,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":27},{"place":273,"model":"vicuna-7b-v1.5","company":"lmsys","family":"Vicuna","version":"Vicuna","score":26.7},{"place":274,"model":"bloom-7b1","company":"bigscience","family":"BLOOM","version":"BLOOM","score":26.55},{"place":275,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":26.53},{"place":276,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":26.4},{"place":277,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":26.4},{"place":278,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":26.2},{"place":279,"model":"aquila-7b","company":"baai","family":"Aquila","version":"Aquila","score":25.58},{"place":280,"model":"tigerbot-7b-base","company":"tigerbot","family":"TigerBot","version":"TigerBot","score":25.19},{"place":281,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":24.83},{"place":282,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":24.6},{"place":283,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":24.2},{"place":284,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":24.2},{"place":285,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":24.1},{"place":286,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":24.1},{"place":287,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":23.8},{"place":288,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":23.5},{"place":289,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":23.49},{"place":290,"model":"open-llama-7b-v2","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA v2","score":23.49},{"place":291,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":22.8},{"place":292,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":22.03},{"place":293,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":21.8},{"place":294,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":21.3},{"place":295,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":21.2},{"place":296,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":20.9},{"place":297,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":20.8},{"place":298,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":19.9},{"place":299,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":19.7},{"place":300,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":19.3},{"place":301,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":17.6},{"place":302,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":17.4},{"place":303,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":14}]},{"id":"agieval-lsat-ar","name":"AGIEval LSAT-AR","topic":"Law exam reasoning","description":"LSAT Analytical Reasoning subset from AGIEval benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen2.5 32B Base","top_percent":30.4,"top_model_id":"qwen2.5-32b-base","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 32B Base","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":30.4},{"place":2,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":28.7},{"place":3,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":24.8},{"place":4,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":23.4},{"place":5,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":22.6},{"place":6,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":22.2}]},{"id":"ai2d","name":"AI2D","topic":"Diagram understanding (VQA)","description":"Visual question answering over science and diagram images.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":98.7,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":258,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":98.7},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":97.7},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":97.1},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":97.1},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":97.09},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":96.96},{"place":7,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":96.89},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":96.4},{"place":9,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":96.4},{"place":10,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":96.3},{"place":11,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":95.9},{"place":12,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":95.8},{"place":13,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":95.8},{"place":14,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":95.63},{"place":15,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":95.6},{"place":16,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":95.6},{"place":17,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":95.3},{"place":18,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":94.7},{"place":19,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":94.7},{"place":20,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":94.4},{"place":21,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":94.4},{"place":22,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":94.3},{"place":23,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":94.2},{"place":24,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":94.2},{"place":25,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":94.2},{"place":26,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":94.1},{"place":27,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.9},{"place":28,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":93.8},{"place":29,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":93.8},{"place":30,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":93.8},{"place":31,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":93.72},{"place":32,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":93.7},{"place":33,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":93.7},{"place":34,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":93.7},{"place":35,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.5},{"place":36,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.4},{"place":37,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.3},{"place":38,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":93.2},{"place":39,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":92.91},{"place":40,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.9},{"place":41,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":92.7},{"place":42,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.7},{"place":43,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.6},{"place":44,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":92.3},{"place":45,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":92.2},{"place":46,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.87},{"place":47,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":91.7},{"place":48,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91.5},{"place":49,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":91.48},{"place":50,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":91.2},{"place":51,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":91.1},{"place":52,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.03},{"place":53,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.9},{"place":54,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":90.9},{"place":55,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":90.8},{"place":56,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.8},{"place":57,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":90.7},{"place":58,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":90.5},{"place":59,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.2},{"place":60,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":90.05},{"place":61,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":89.7},{"place":62,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":89.6},{"place":63,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.6},{"place":64,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.5},{"place":65,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.5},{"place":66,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":89.5},{"place":67,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":89.5},{"place":68,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":89.4},{"place":69,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":89.4},{"place":70,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":89.35},{"place":71,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":89.28},{"place":72,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.2},{"place":73,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":89.2},{"place":74,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":89.2},{"place":75,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.2},{"place":76,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":89.1},{"place":77,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":89.1},{"place":78,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.05},{"place":79,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89},{"place":80,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":89},{"place":81,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":89},{"place":82,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":89},{"place":83,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":88.93},{"place":84,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.9},{"place":85,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":88.9},{"place":86,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":88.89},{"place":87,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":88.8},{"place":88,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.7},{"place":89,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.7},{"place":90,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":88.7},{"place":91,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":88.6},{"place":92,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":88.5},{"place":93,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":88.4},{"place":94,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.4},{"place":95,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":88.37},{"place":96,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.3},{"place":97,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.3},{"place":98,"model":"grok-1.5v","company":"xai","family":"Grok","version":"Grok 1.5","score":88.3},{"place":99,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":88.2},{"place":100,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":88.2},{"place":101,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":88.1},{"place":102,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":88.1},{"place":103,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":88.1},{"place":104,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":88.1},{"place":105,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":87.9},{"place":106,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":87.9},{"place":107,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":87.9},{"place":108,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":87.75},{"place":109,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.7},{"place":110,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.7},{"place":111,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":87.6},{"place":112,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":87.6},{"place":113,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":87.6},{"place":114,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":87.5},{"place":115,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":87.3},{"place":116,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":87.3},{"place":117,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.2},{"place":118,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":87.1},{"place":119,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87},{"place":120,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":87},{"place":121,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.9},{"place":122,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":86.7},{"place":123,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":86.7},{"place":124,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":86.7},{"place":125,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.7},{"place":126,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":86.6},{"place":127,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":86.5},{"place":128,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":86.4},{"place":129,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":86.4},{"place":130,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":86.4},{"place":131,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86.3},{"place":132,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":86.3},{"place":133,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":86.2},{"place":134,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":86.1},{"place":135,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":86.1},{"place":136,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":86.04},{"place":137,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":86},{"place":138,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.7},{"place":139,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.7},{"place":140,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":85.6},{"place":141,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":85.6},{"place":142,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":85.5},{"place":143,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":85.2},{"place":144,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":85.2},{"place":145,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":85.2},{"place":146,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":85.16},{"place":147,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":85.1},{"place":148,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85},{"place":149,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85},{"place":150,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":84.96},{"place":151,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.9},{"place":152,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.9},{"place":153,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.8},{"place":154,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":84.8},{"place":155,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":84.8},{"place":156,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":84.7},{"place":157,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":84.7},{"place":158,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":84.6},{"place":159,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":84.6},{"place":160,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":84.6},{"place":161,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":84.6},{"place":162,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":84.5},{"place":163,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":84.5},{"place":164,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":84.5},{"place":165,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":84.5},{"place":166,"model":"ovis1.6-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":84.4},{"place":167,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":84.2},{"place":168,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":84.19},{"place":169,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.1},{"place":170,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":84},{"place":171,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":83.9},{"place":172,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.9},{"place":173,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":83.9},{"place":174,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":83.8},{"place":175,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":83.8},{"place":176,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":83.7},{"place":177,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":83.6},{"place":178,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":83.6},{"place":179,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":83.5},{"place":180,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":83.4},{"place":181,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.32},{"place":182,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.3},{"place":183,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":83.2},{"place":184,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":83},{"place":185,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83},{"place":186,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":83},{"place":187,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":83},{"place":188,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":82.87},{"place":189,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":82.6},{"place":190,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":82.6},{"place":191,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":82.6},{"place":192,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":82.6},{"place":193,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":82.5},{"place":194,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":82.4},{"place":195,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":82.34},{"place":196,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":82.2},{"place":197,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":82.16},{"place":198,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":82.1},{"place":199,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.09},{"place":200,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":82},{"place":201,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":82},{"place":202,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":81.9},{"place":203,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":81.9},{"place":204,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":81.86},{"place":205,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":81.6},{"place":206,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":81.5},{"place":207,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":81.4},{"place":208,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":81.4},{"place":209,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":81.4},{"place":210,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":81.4},{"place":211,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":81.2},{"place":212,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81.2},{"place":213,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":81.2},{"place":214,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":81.1},{"place":215,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":80.9},{"place":216,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":80.7},{"place":217,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":80.7},{"place":218,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":80.7},{"place":219,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":80.6},{"place":220,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":80.5},{"place":221,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.4},{"place":222,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":80.4},{"place":223,"model":"llava-next-110b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":80.4},{"place":224,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":80.3},{"place":225,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":80.2},{"place":226,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":80.2},{"place":227,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":80.2},{"place":228,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":80.1},{"place":229,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":80},{"place":230,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.9},{"place":231,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":79.9},{"place":232,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":79.7},{"place":233,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":79.7},{"place":234,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":79.53},{"place":235,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":79.5},{"place":236,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":79.5},{"place":237,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":79.5},{"place":238,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":79.4},{"place":239,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":79.3},{"place":240,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":79.3},{"place":241,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":79.2},{"place":242,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.15},{"place":243,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":79.1},{"place":244,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":79},{"place":245,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":79},{"place":246,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":78.9},{"place":247,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":78.9},{"place":248,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.8},{"place":249,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.7},{"place":250,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":78.7},{"place":251,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":78.6},{"place":252,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":78.6},{"place":253,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":78.6},{"place":254,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":78.4},{"place":255,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":78.2},{"place":256,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":78.1},{"place":257,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":78.1},{"place":258,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":77.8},{"place":259,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":77.8},{"place":260,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":77.8},{"place":261,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":77.5},{"place":262,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":77.4},{"place":263,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":77.2},{"place":264,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.9},{"place":265,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":76.8},{"place":266,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":76.7},{"place":267,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":76.3},{"place":268,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":76.2},{"place":269,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":75.9},{"place":270,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":75.9},{"place":271,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":75.7},{"place":272,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":75.5},{"place":273,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.2},{"place":274,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":75},{"place":275,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":74.9},{"place":276,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":74.9},{"place":277,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":74.7},{"place":278,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":74.7},{"place":279,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":74.6},{"place":280,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":74.4},{"place":281,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":74.2},{"place":282,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":74.1},{"place":283,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":74.1},{"place":284,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":73.9},{"place":285,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":73.9},{"place":286,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":73.4},{"place":287,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":73.3},{"place":288,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":73},{"place":289,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73},{"place":290,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":72.9},{"place":291,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":72.8},{"place":292,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":72.5},{"place":293,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.4},{"place":294,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":72.4},{"place":295,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":72.3},{"place":296,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":72.2},{"place":297,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":72.2},{"place":298,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":71.6},{"place":299,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.3},{"place":300,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.2},{"place":301,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":71.2},{"place":302,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":70.6},{"place":303,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":70.3},{"place":304,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":70.2},{"place":305,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":70},{"place":306,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":70},{"place":307,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":308,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":309,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":69.9},{"place":310,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":69.7},{"place":311,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":69.3},{"place":312,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.7},{"place":313,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":68.6},{"place":314,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":68.1},{"place":315,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":68},{"place":316,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":67.3},{"place":317,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":67},{"place":318,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":65.7},{"place":319,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":320,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":321,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":65.4},{"place":322,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":64.1},{"place":323,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":63.3},{"place":324,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":63},{"place":325,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":62.9},{"place":326,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":62.5},{"place":327,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":62.3},{"place":328,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":61.6},{"place":329,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":61.1},{"place":330,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":59.3},{"place":331,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":58},{"place":332,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":57.7},{"place":333,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":57.1},{"place":334,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":56.9},{"place":335,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":55.5},{"place":336,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":51},{"place":337,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":44.8},{"place":338,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":43.2},{"place":339,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":37.66},{"place":340,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":34.9},{"place":341,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":26.5}]},{"id":"aicodeking-non-agentic","name":"AICodeKing Non-Agentic","topic":"Code generation (non-agentic)","description":"Non-agentic code generation benchmark from AICodeKing.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":100,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":100},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":100},{"place":3,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":100},{"place":4,"model":"claude-opus-4.5-max","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74},{"place":5,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":65},{"place":6,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":64},{"place":7,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":43},{"place":8,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":43},{"place":9,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":43},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":42},{"place":11,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":42},{"place":12,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":41},{"place":13,"model":"sonoma-sky","company":"","family":"Sonoma","version":"Sonoma","score":41},{"place":14,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":40},{"place":15,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":40},{"place":16,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":40},{"place":17,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":40},{"place":18,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":38},{"place":19,"model":"gpt-5.1-codex-mini-high","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":36},{"place":20,"model":"sonic","company":"","family":"Sonic","version":"Sonic","score":36}]},{"id":"aider-code-editing","name":"Aider Code Editing","topic":"Code editing","description":"Measures interactive code editing quality within the Aider assistant workflow.","url":"https://aider.chat/docs/leaderboards/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":89.85,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":51,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.85},{"place":2,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":88.16},{"place":3,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":88},{"place":4,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":86.5},{"place":5,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85.34},{"place":6,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":84.4},{"place":7,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":84.2},{"place":8,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":83.65},{"place":9,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":79.7},{"place":10,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":74.4},{"place":11,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":73.7},{"place":12,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.7},{"place":13,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":72.9},{"place":14,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":72.9},{"place":15,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":72.2},{"place":16,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":71.6},{"place":17,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":70.7},{"place":18,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":69.9},{"place":19,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.2},{"place":20,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":68.4},{"place":21,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.4},{"place":22,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":66.2},{"place":23,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.2},{"place":24,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":65.4},{"place":25,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.4},{"place":26,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":63.9},{"place":27,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":63.9},{"place":28,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.3},{"place":29,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":57.1},{"place":30,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":55.64},{"place":31,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":55.6},{"place":32,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":55.6},{"place":33,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":54.5},{"place":34,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":54.1},{"place":35,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":52.6},{"place":36,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":51.1},{"place":37,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":51.1},{"place":38,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":49.62},{"place":39,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":49.2},{"place":40,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":45.11},{"place":41,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":44.4},{"place":42,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":44.4},{"place":43,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":43.61},{"place":44,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":39.85},{"place":45,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":39.1},{"place":46,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":38.3},{"place":47,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":37.6},{"place":48,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":34.6},{"place":49,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":31.6},{"place":50,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":18.8},{"place":51,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":17.3},{"place":52,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":15},{"place":53,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":14.3},{"place":54,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":1.5},{"place":55,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":1.5},{"place":56,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":1.5}]},{"id":"aider-polyglot","name":"Aider-Polyglot","topic":"Code assistant eval","description":"Aider polyglot coding leaderboard.","url":"https://aider.chat/docs/leaderboards/","leaderboard":"https://aider.chat/docs/leaderboards/","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro Preview","top_percent":92.9,"top_model_id":"gemini-3-pro-preview","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro Preview","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":133,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":92.9},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":88},{"place":3,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":88},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.1},{"place":5,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":86.7},{"place":6,"model":"o3-pro","company":"openai","family":"o3","version":"o3","score":84.9},{"place":7,"model":"o3-pro-high","company":"openai","family":"o3","version":"o3","score":84.9},{"place":8,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.1},{"place":9,"model":"o3","company":"openai","family":"o3","version":"o3","score":81.3},{"place":10,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":81.3},{"place":11,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":81.3},{"place":12,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":80.8},{"place":13,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":79.6},{"place":14,"model":"grok-4-high","company":"xai","family":"Grok","version":"Grok 4","score":79.6},{"place":15,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.1},{"place":16,"model":"o3-high-plus-gpt-4.1","company":"ensemble","family":"Composite","version":"Composite","score":78.2},{"place":17,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78},{"place":18,"model":"o3","company":"openai","family":"o3","version":"o3","score":76.9},{"place":19,"model":"gemini-2.5-pro-preview-05-06","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.9},{"place":20,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":76.3},{"place":21,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":76.1},{"place":22,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":74.5},{"place":23,"model":"deepseek-v3.2-exp-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":74.2},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.9},{"place":25,"model":"gemini-2.5-pro-preview-03-25","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.9},{"place":26,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":72},{"place":27,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":72},{"place":28,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":72},{"place":29,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":72},{"place":30,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":72},{"place":31,"model":"deepseek-v3-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":71.6},{"place":32,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":71.6},{"place":33,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":71.4},{"place":34,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":70.7},{"place":35,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":70.7},{"place":36,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":70.2},{"place":37,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":69.9},{"place":38,"model":"qwen3-coder-next","company":"qwen","family":"Qwen","version":"Qwen3","score":66.2},{"place":39,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":65.3},{"place":40,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":64.9},{"place":41,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":64.9},{"place":42,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":64.9},{"place":43,"model":"deepseek-tng-r1t2-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T2","score":64.4},{"place":44,"model":"deepseek-r1-plus-claude-3-5-sonnet-20241022","company":"ensemble","family":"Composite","version":"Composite","score":64},{"place":45,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":62.3},{"place":46,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.8},{"place":47,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":61.8},{"place":48,"model":"o1","company":"openai","family":"o1","version":"o1","score":61.7},{"place":49,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":61.7},{"place":50,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":61.7},{"place":51,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":61.3},{"place":52,"model":"claude-sonnet-4-20250514-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4","score":61.3},{"place":53,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":61},{"place":54,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":60.4},{"place":55,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":60.4},{"place":56,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":60},{"place":57,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":58,"model":"qwen3-235b-a22b-no-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":59,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":59.1},{"place":60,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.3},{"place":61,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":56.9},{"place":62,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":56.4},{"place":63,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":56.4},{"place":64,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.1},{"place":65,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":55.1},{"place":66,"model":"gemini-2.5-flash-preview-05-20-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.1},{"place":67,"model":"quasar-alpha","company":"quasar","family":"Quasar","version":"Quasar","score":54.7},{"place":68,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":53.8},{"place":69,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":53.8},{"place":70,"model":"grok-3-beta-think","company":"xai","family":"Grok","version":"Grok 3","score":53.3},{"place":71,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":53.3},{"place":72,"model":"optimus-alpha","company":"openbmb","family":"Optimus","version":"Optimus","score":52.9},{"place":73,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":52.4},{"place":74,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":52.1},{"place":75,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.6},{"place":76,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":50.7},{"place":77,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.2},{"place":78,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":49.8},{"place":79,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":49.6},{"place":80,"model":"grok-3-mini-beta-high","company":"xai","family":"Grok","version":"Grok 3","score":49.3},{"place":81,"model":"deepseek-tng-r1t-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T","score":48.4},{"place":82,"model":"deepseek-chat-v3-prev","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":48.4},{"place":83,"model":"gemini-2.5-flash-preview-04-17","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.1},{"place":84,"model":"magistral-medium","company":"magistral","family":"Magistral","version":"Magistral","score":47.1},{"place":85,"model":"chatgpt-4o-latest-20250329","company":"openai","family":"GPT","version":"GPT-4o","score":45.3},{"place":86,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":45.3},{"place":87,"model":"gpt-4.5-preview","company":"openai","family":"GPT","version":"GPT-4.5","score":44.9},{"place":88,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":44},{"place":89,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":44},{"place":90,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":43.6},{"place":91,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":42},{"place":92,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":41.8},{"place":93,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":40},{"place":94,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":40},{"place":95,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":40},{"place":96,"model":"gemini-exp-1206","company":"google","family":"Gemini","version":"Gemini 1.0","score":38.2},{"place":97,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":37.68},{"place":98,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.6},{"place":99,"model":"gemini-2.0-pro-exp-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":35.6},{"place":100,"model":"grok-3-mini-beta-low","company":"xai","family":"Grok","version":"Grok 3","score":34.7},{"place":101,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":34.2},{"place":102,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":34.2},{"place":103,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":32.9},{"place":104,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":32.4},{"place":105,"model":"openthinkeragent-32b","company":"openthinker","family":"OpenThinker","version":"OpenThinkerAgent","score":32.4},{"place":106,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":29.3},{"place":107,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":28.9},{"place":108,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":28},{"place":109,"model":"chatgpt-4o-latest-20250215","company":"openai","family":"GPT","version":"GPT-4o","score":27.1},{"place":110,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":26.37},{"place":111,"model":"qwq-32b-plus-qwen2.5-coder-32b-instruct","company":"ensemble","family":"Composite","version":"Composite","score":26.2},{"place":112,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":26.2},{"place":113,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":25.8},{"place":114,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":23.1},{"place":115,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":22.2},{"place":116,"model":"qwen-max-2025-01-25","company":"qwen","family":"Qwen","version":"Qwen Max","score":21.8},{"place":117,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":20.9},{"place":118,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":20},{"place":119,"model":"jan-code-4b","company":"menlo","family":"Jan","version":"Jan Code","score":19},{"place":120,"model":"gemini-2.0-flash-thinking-exp-01-21","company":"google","family":"Gemini","version":"Gemini 2.0","score":18.2},{"place":121,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":18.2},{"place":122,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":18.2},{"place":123,"model":"jan-v3","company":"menlo","family":"Jan","version":"Jan v3","score":18},{"place":124,"model":"deepseek-chat-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":17.8},{"place":125,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":16.4},{"place":126,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":16},{"place":127,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":15.6},{"place":128,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":15.6},{"place":129,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":15.6},{"place":130,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":14.7},{"place":131,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":12.9},{"place":132,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":12.9},{"place":133,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":12.1},{"place":134,"model":"command-a-03-2025-quality","company":"cohere","family":"Command","version":"Command","score":12},{"place":135,"model":"codestral-2501","company":"mistral","family":"Codestral","version":"Codestral","score":11.1},{"place":136,"model":"openhands-lm-32b-v0.1","company":"openhands","family":"OpenHands","version":"OpenHands","score":10.2},{"place":137,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":8.9},{"place":138,"model":"qwen2.5-coder-32b-instruct-hyperbolic","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8},{"place":139,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8},{"place":140,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.6},{"place":141,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":5.8},{"place":142,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":5.3},{"place":143,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":4.9},{"place":144,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":4.9},{"place":145,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":3.6},{"place":146,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":2.2}]},{"id":"aider-polyglot-diff","name":"Aider-Polyglot (Diff)","topic":"Code assistant eval","description":"Aider polyglot leaderboard using diff mode (pass@2).","url":"https://aider.chat/docs/leaderboards/","leaderboard":"https://aider.chat/docs/leaderboards/","github":"","paper":"","metric":"pass@2","stars":"","top_model":"Gemini 3 Pro Preview","top_percent":91.9,"top_model_id":"gemini-3-pro-preview","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro Preview","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":65,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":91.9},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.4},{"place":3,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":88},{"place":4,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":86.7},{"place":5,"model":"o3-pro-high","company":"openai","family":"o3","version":"o3","score":84.9},{"place":6,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":82.7},{"place":7,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":81.3},{"place":8,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":81.3},{"place":9,"model":"grok-4-high","company":"xai","family":"Grok","version":"Grok 4","score":79.6},{"place":10,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.8},{"place":11,"model":"o3","company":"openai","family":"o3","version":"o3","score":76.9},{"place":12,"model":"deepseek-v3.2-exp-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":74.2},{"place":13,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":72},{"place":14,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":72},{"place":15,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":71.4},{"place":16,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":70.7},{"place":17,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":70.2},{"place":18,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":68.9},{"place":19,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":64.9},{"place":20,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":63.1},{"place":21,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":61.7},{"place":22,"model":"claude-sonnet-4-20250514-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4","score":61.3},{"place":23,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":60.4},{"place":24,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":60.4},{"place":25,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":60},{"place":26,"model":"qwen3-235b-a22b-no-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":27,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":59.1},{"place":28,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":57.8},{"place":29,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":56.9},{"place":30,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":56.4},{"place":31,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":55.1},{"place":32,"model":"gemini-2.5-flash-preview-05-20-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.1},{"place":33,"model":"quasar-alpha","company":"quasar","family":"Quasar","version":"Quasar","score":54.7},{"place":34,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":53.8},{"place":35,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":53.3},{"place":36,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":53.3},{"place":37,"model":"optimus-alpha","company":"openbmb","family":"Optimus","version":"Optimus","score":52.9},{"place":38,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":52.4},{"place":39,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.6},{"place":40,"model":"deepseek-chat-v3-prev","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":48.4},{"place":41,"model":"gemini-2.5-flash-preview-04-17","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.1},{"place":42,"model":"chatgpt-4o-latest-20250329","company":"openai","family":"GPT","version":"GPT-4o","score":45.3},{"place":43,"model":"gpt-4.5-preview","company":"openai","family":"GPT","version":"GPT-4.5","score":44.9},{"place":44,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":44},{"place":45,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":41.8},{"place":46,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":40},{"place":47,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":32.4},{"place":48,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":28.4},{"place":49,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":28},{"place":50,"model":"chatgpt-4o-latest-20250215","company":"openai","family":"GPT","version":"GPT-4o","score":27.1},{"place":51,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":25.3},{"place":52,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":23.1},{"place":53,"model":"qwen-max-2025-01-25","company":"qwen","family":"Qwen","version":"Qwen Max","score":21.8},{"place":54,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":20.9},{"place":55,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":18.2},{"place":56,"model":"gemini-2.0-flash-thinking-exp-01-21","company":"google","family":"Gemini","version":"Gemini 2.0","score":18.2},{"place":57,"model":"deepseek-chat-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":17.8},{"place":58,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":16.4},{"place":59,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":12},{"place":60,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":8.9},{"place":61,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.4},{"place":62,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8},{"place":63,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8},{"place":64,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":6.2},{"place":65,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1.8},{"place":66,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":1.3}]},{"id":"aime-2024","name":"AIME 2024","topic":"Math (competition)","description":"American Invitational Mathematics Examination 2024 problems.","url":"https://artofproblemsolving.com/wiki/index.php/2024_AIME_I_Problems","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-OSS 120B","top_percent":96.6,"top_model_id":"gpt-oss-120b","top_generation":"GPT-OSS","top_model_base":"GPT-OSS 120B","top_model_family":"GPT","top_company":"openai","top_open_source":1,"lower_is_better":false,"bench_models":266,"total_models":3854,"placements":[{"place":1,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":96.6},{"place":2,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":96},{"place":3,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":95.8},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":94.78},{"place":5,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":94.3},{"place":6,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":93.4},{"place":7,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":93.3},{"place":8,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.4},{"place":9,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":92.26},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92},{"place":11,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":91.87},{"place":12,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":91.82},{"place":13,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":91.7},{"place":14,"model":"o3","company":"openai","family":"o3","version":"o3","score":91.6},{"place":15,"model":"deepseek-v3-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":91.4},{"place":16,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":91.4},{"place":17,"model":"golongrl-30b-a3b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":91.3},{"place":18,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":91},{"place":19,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":90.8},{"place":20,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":90.5},{"place":21,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":90.4},{"place":22,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":89.8},{"place":23,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":89.8},{"place":24,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":89.7},{"place":25,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":89.58},{"place":26,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":89.5},{"place":27,"model":"openreasoning-nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":89.2},{"place":28,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.2},{"place":29,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":89},{"place":30,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":88.8},{"place":31,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":88.7},{"place":32,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":88.3},{"place":33,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.1},{"place":34,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":88.1},{"place":35,"model":"openreasoning-nemotron-14b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":87.8},{"place":36,"model":"gka-primed-hqwen3-32b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":87.67},{"place":37,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":87.09},{"place":38,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":86.7},{"place":39,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":86.67},{"place":40,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":86.5},{"place":41,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":86.33},{"place":42,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.3},{"place":43,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":86.26},{"place":44,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":86.2},{"place":45,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":86.14},{"place":46,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":86},{"place":47,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":86},{"place":48,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86},{"place":49,"model":"ministral-3-8b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":86},{"place":50,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":85.8},{"place":51,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.7},{"place":52,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":84.7},{"place":53,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":84.6},{"place":54,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":84.6},{"place":55,"model":"ring-mini-sparse-2.0-exp","company":"antgroup","family":"Ring","version":"Ring 2.0","score":84.58},{"place":56,"model":"golongrl-4b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":84.2},{"place":57,"model":"grok-3-beta-think","company":"xai","family":"Grok","version":"Grok 3","score":83.9},{"place":58,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":83.75},{"place":59,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83.7},{"place":60,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":83.33},{"place":61,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":83.33},{"place":62,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":83.3},{"place":63,"model":"o1","company":"openai","family":"o1","version":"o1","score":83.3},{"place":64,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":83.3},{"place":65,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.3},{"place":66,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":83.3},{"place":67,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":83.3},{"place":68,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":83.2},{"place":69,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.7},{"place":70,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.6},{"place":71,"model":"deepseek-tng-r1t2-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T2","score":82.3},{"place":72,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.3},{"place":73,"model":"gka-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":82},{"place":74,"model":"gdn-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":82},{"place":75,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":81.9},{"place":76,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":81.46},{"place":77,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.4},{"place":78,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":81.4},{"place":79,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":81.35},{"place":80,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":80.83},{"place":81,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":80.8},{"place":82,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.8},{"place":83,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.8},{"place":84,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":80.62},{"place":85,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":80.6},{"place":86,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.4},{"place":87,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.4},{"place":88,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.4},{"place":89,"model":"vibethinker-1.5b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":80.3},{"place":90,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":80},{"place":91,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":80},{"place":92,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":80},{"place":93,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":80},{"place":94,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80},{"place":95,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":80},{"place":96,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":79.8},{"place":97,"model":"deepseek-r1-0120","company":"deepseek","family":"DeepSeek","version":"0120","score":79.8},{"place":98,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":79.6},{"place":99,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":79.6},{"place":100,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":79.5},{"place":101,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.4},{"place":102,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":79.38},{"place":103,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79.3},{"place":104,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.3},{"place":105,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":79},{"place":106,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":78.67},{"place":107,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":78.3},{"place":108,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.9},{"place":109,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":77.7},{"place":110,"model":"ministral-3-3b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":77.5},{"place":111,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":77.5},{"place":112,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":77.4},{"place":113,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":77.2},{"place":114,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":77},{"place":115,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":76.9},{"place":116,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":76.88},{"place":117,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":76.8},{"place":118,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":76.7},{"place":119,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":76.66},{"place":120,"model":"ring-lite","company":"antgroup","family":"Ring","version":"Ring Lite","score":76.6},{"place":121,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":76},{"place":122,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":76},{"place":123,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":76},{"place":124,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":76},{"place":125,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":75.9},{"place":126,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":75.8},{"place":127,"model":"glm-z1","company":"zai","family":"GLM","version":"GLM Z1","score":75.6},{"place":128,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":75.6},{"place":129,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.4},{"place":130,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.31},{"place":131,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.21},{"place":132,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":75},{"place":133,"model":"deepseek-tng-r1t-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T","score":74.7},{"place":134,"model":"phi-4-reasoning","company":"microsoft","family":"Phi","version":"Phi 4","score":74.6},{"place":135,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.6},{"place":136,"model":"o1","company":"openai","family":"o1","version":"o1","score":74.3},{"place":137,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":74.3},{"place":138,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.2},{"place":139,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":74},{"place":140,"model":"magistral-medium","company":"magistral","family":"Magistral","version":"Magistral","score":73.6},{"place":141,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":73.6},{"place":142,"model":"magistral-medium-1.0","company":"mistral","family":"Magistral","version":"Magistral 1.0","score":73.59},{"place":143,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":73.5},{"place":144,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.33},{"place":145,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":73.3},{"place":146,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.3},{"place":147,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":73.3},{"place":148,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":73.3},{"place":149,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.9},{"place":150,"model":"deepseek-r1-distill-32b","company":"deepseek","family":"DeepSeek-R1","version":"32B","score":72.6},{"place":151,"model":"acereason-nemotron-1.1","company":"nvidia","family":"AceReason","version":"1.1","score":72.6},{"place":152,"model":"questa-nemotron-1.5b","company":"amazon","family":"Nemotron","version":"QuestA Nemotron","score":72.5},{"place":153,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":72.3},{"place":154,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":72.19},{"place":155,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":72.1},{"place":156,"model":"magistral-medium-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":72.03},{"place":157,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":71.67},{"place":158,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":71.6},{"place":159,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":71.1},{"place":160,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.9},{"place":161,"model":"magistral-small-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":70.7},{"place":162,"model":"magistral-small-1.0","company":"mistral","family":"Magistral","version":"Magistral 1.0","score":70.68},{"place":163,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.63},{"place":164,"model":"magistral-small-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":70.52},{"place":165,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":70.52},{"place":166,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70.3},{"place":167,"model":"skywork-or1-7b","company":"skywork","family":"Skywork OR1","version":"Skywork OR1","score":70.2},{"place":168,"model":"deepseek-r1-distill-llama-70b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70},{"place":169,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":70},{"place":170,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.6},{"place":171,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.6},{"place":172,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.6},{"place":173,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":68.2},{"place":174,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":67.8},{"place":175,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":67.7},{"place":176,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":67.5},{"place":177,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":66.2},{"place":178,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":65.4},{"place":179,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":65.4},{"place":180,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":64.79},{"place":181,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":64.6},{"place":182,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":64.6},{"place":183,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":63.6},{"place":184,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.33},{"place":185,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":62},{"place":186,"model":"nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":61.77},{"place":187,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.3},{"place":188,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":60.31},{"place":189,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":59.4},{"place":190,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":59.4},{"place":191,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.44},{"place":192,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":56.7},{"place":193,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":55.5},{"place":194,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.1},{"place":195,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":54.9},{"place":196,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":54.8},{"place":197,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":53},{"place":198,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":52.5},{"place":199,"model":"deepseek-r1-lite-preview","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":52.5},{"place":200,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":52.2},{"place":201,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":50},{"place":202,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":49.7},{"place":203,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.33},{"place":204,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.3},{"place":205,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":48.2},{"place":206,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":48.1},{"place":207,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":47.81},{"place":208,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":47},{"place":209,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":46.7},{"place":210,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":46.5},{"place":211,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":44.6},{"place":212,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":44.3},{"place":213,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":44.2},{"place":214,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":43.4},{"place":215,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.1},{"place":216,"model":"mobilellm-r1.5-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":39.9},{"place":217,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":39.2},{"place":218,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":36.7},{"place":219,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":35.2},{"place":220,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":32.8},{"place":221,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":31.7},{"place":222,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":31},{"place":223,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":30.2},{"place":224,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":30},{"place":225,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":29.1},{"place":226,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":28.9},{"place":227,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.33},{"place":228,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":27.92},{"place":229,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.9},{"place":230,"model":"apertus-v1.5-70b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":27.9},{"place":231,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":27.5},{"place":232,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":26.8},{"place":233,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.2},{"place":234,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":23.75},{"place":235,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":23.5},{"place":236,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":23.3},{"place":237,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":23.3},{"place":238,"model":"apertus-v1.5-8b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":22.9},{"place":239,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":22.5},{"place":240,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":22.29},{"place":241,"model":"lfm2-350m-math","company":"liquidai","family":"LFM","version":"LFM2","score":21.3},{"place":242,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":20},{"place":243,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":20},{"place":244,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":18.9},{"place":245,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":17.92},{"place":246,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":17.29},{"place":247,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":16.7},{"place":248,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":16.7},{"place":249,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":16.04},{"place":250,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":16},{"place":251,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":16},{"place":252,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":15.7},{"place":253,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":15.5},{"place":254,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":14.37},{"place":255,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":13.3},{"place":256,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":13.3},{"place":257,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":13.3},{"place":258,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":13.3},{"place":259,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":13.2},{"place":260,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":13.1},{"place":261,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":12.92},{"place":262,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":12.7},{"place":263,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":12.5},{"place":264,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":12.29},{"place":265,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":11.88},{"place":266,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":11.67},{"place":267,"model":"qwen3-6b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.5},{"place":268,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.3},{"place":269,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":11.3},{"place":270,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":11.25},{"place":271,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":10.1},{"place":272,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":10},{"place":273,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":10},{"place":274,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":10},{"place":275,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":10},{"place":276,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":10},{"place":277,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":9.79},{"place":278,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":9.3},{"place":279,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":9.3},{"place":280,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":8.75},{"place":281,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":8.12},{"place":282,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":7.3},{"place":283,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.87},{"place":284,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":6.7},{"place":285,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":6.7},{"place":286,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":6.7},{"place":287,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":6.7},{"place":288,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":6.7},{"place":289,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":6.7},{"place":290,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":6.7},{"place":291,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":6.7},{"place":292,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":6.7},{"place":293,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":6.67},{"place":294,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":6.25},{"place":295,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":5.62},{"place":296,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":5.42},{"place":297,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":4.7},{"place":298,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":4.6},{"place":299,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":4.6},{"place":300,"model":"mobilellm-r1.5-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":4.1},{"place":301,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":3.96},{"place":302,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":3.75},{"place":303,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":3.3},{"place":304,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":3.3},{"place":305,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":3.3},{"place":306,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":3.3},{"place":307,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":3.3},{"place":308,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":3.28},{"place":309,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.71},{"place":310,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.5},{"place":311,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":2.43},{"place":312,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":2.4},{"place":313,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.29},{"place":314,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1.97},{"place":315,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":1.46},{"place":316,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":1.3},{"place":317,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":1.1},{"place":318,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1.1},{"place":319,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":0.9},{"place":320,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":0.89},{"place":321,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":0.89},{"place":322,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":0.83},{"place":323,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.62},{"place":324,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":0.6},{"place":325,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":0.5},{"place":326,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":0.41},{"place":327,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":0.31},{"place":328,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0.3},{"place":329,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":0.21},{"place":330,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0.2},{"place":331,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.1},{"place":332,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":0}]},{"id":"aime-2024-ko","name":"AIME 2024-Ko","topic":"Math (competition, Korean)","description":"Korean translation of AIME 2024 problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-30B-A3B-Thinking-2507","top_percent":80.3,"top_model_id":"qwen3-30b-a3b-thinking-2507","top_generation":"Qwen3","top_model_base":"Qwen3 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.3},{"place":2,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":75},{"place":3,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.3},{"place":4,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":25.3}]},{"id":"aime-2025","name":"AIME 2025","topic":"Math (competition)","description":"American Invitational Mathematics Examination 2025 problems.","url":"https://artofproblemsolving.com/wiki/index.php/AIME_Problems_and_Solutions","leaderboard":"https://www.kaggle.com/benchmarks/open-benchmarks/aime-2025","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.5","top_percent":100,"top_model_id":"claude-sonnet-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Sonnet 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":498,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":100},{"place":2,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":3,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":4,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":100},{"place":5,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":6,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":100},{"place":7,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":8,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":9,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":100},{"place":10,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":100},{"place":11,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":100},{"place":12,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":13,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":100},{"place":14,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":15,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":100},{"place":16,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":100},{"place":17,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":100},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":100},{"place":19,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":99.8},{"place":20,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":99.8},{"place":21,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":99.6},{"place":22,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":99.2},{"place":23,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":99.2},{"place":24,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":99.2},{"place":25,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":99.1},{"place":26,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":99},{"place":27,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":98.7},{"place":28,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":98.7},{"place":29,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":98.3},{"place":30,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":98},{"place":31,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":97.9},{"place":32,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":97.7},{"place":33,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":97.3},{"place":34,"model":"mai-thinking-1","company":"microsoft","family":"MAI","version":"MAI-Thinking-1","score":97},{"place":35,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":96.9},{"place":36,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":96.7},{"place":37,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":96.7},{"place":38,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":96.67},{"place":39,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":96.67},{"place":40,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":96.67},{"place":41,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":96.67},{"place":42,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":96.67},{"place":43,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":96.55},{"place":44,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":96.3},{"place":45,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":96.3},{"place":46,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":96.3},{"place":47,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":96.1},{"place":48,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":96.1},{"place":49,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":96},{"place":50,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":96},{"place":51,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":95.83},{"place":52,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":95.7},{"place":53,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":95.6},{"place":54,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":95.3},{"place":55,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":95.2},{"place":56,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":95},{"place":57,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":95},{"place":58,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":95},{"place":59,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":94.6},{"place":60,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":94.6},{"place":61,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":94.6},{"place":62,"model":"gpt-5-thinking-high","company":"openai","family":"GPT","version":"GPT-5","score":94.6},{"place":63,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":94.5},{"place":64,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":94.43},{"place":65,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":94.3},{"place":66,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":94.1},{"place":67,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":94.1},{"place":68,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":94},{"place":69,"model":"gpt-5.1-thinking","company":"openai","family":"GPT","version":"GPT-5.1","score":94},{"place":70,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":94},{"place":71,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":93.9},{"place":72,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":93.7},{"place":73,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.5},{"place":74,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.5},{"place":75,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":93.4},{"place":76,"model":"ring-1t","company":"antgroup","family":"Ring","version":"Ring","score":93.4},{"place":77,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.33},{"place":78,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":93.33},{"place":79,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":93.33},{"place":80,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":93.33},{"place":81,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":93.33},{"place":82,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":93.3},{"place":83,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":93.3},{"place":84,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":93.3},{"place":85,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":93.3},{"place":86,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.1},{"place":87,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.1},{"place":88,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":93.1},{"place":89,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":93.1},{"place":90,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":93},{"place":91,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93},{"place":92,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":93},{"place":93,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":92.91},{"place":94,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":92.9},{"place":95,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.8},{"place":96,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":92.8},{"place":97,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.8},{"place":98,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":92.7},{"place":99,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":92.6},{"place":100,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":92.6},{"place":101,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":92.5},{"place":102,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":92.5},{"place":103,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":92.4},{"place":104,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":92.3},{"place":105,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":92.3},{"place":106,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.2},{"place":107,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":92.1},{"place":108,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":92},{"place":109,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":92},{"place":110,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":91.9},{"place":111,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.9},{"place":112,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":91.7},{"place":113,"model":"gpt-oss-20b-a4b","company":"openai","family":"GPT","version":"GPT-OSS","score":91.7},{"place":114,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":91.7},{"place":115,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":91.7},{"place":116,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.7},{"place":117,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":91.7},{"place":118,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":91.6},{"place":119,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":91.4},{"place":120,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91.3},{"place":121,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":91.2},{"place":122,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":91.1},{"place":123,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":91.1},{"place":124,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":91},{"place":125,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91},{"place":126,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":91},{"place":127,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":91},{"place":128,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":91},{"place":129,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":90.8},{"place":130,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":90.8},{"place":131,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":90.76},{"place":132,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":90.6},{"place":133,"model":"longcat-flash-thinking","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":90.6},{"place":134,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":90.42},{"place":135,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.36},{"place":136,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":90.3},{"place":137,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":90.3},{"place":138,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.21},{"place":139,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.2},{"place":140,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90},{"place":141,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":90},{"place":142,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":90},{"place":143,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":90},{"place":144,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":89.7},{"place":145,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":89.7},{"place":146,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.7},{"place":147,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.7},{"place":148,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.6},{"place":149,"model":"cogito-671b-v2.1","company":"deepcogito","family":"Cogito","version":"Cogito 671B v2.1","score":89.47},{"place":150,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":89.4},{"place":151,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":89.3},{"place":152,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":89.2},{"place":153,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":89.17},{"place":154,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.1},{"place":155,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.1},{"place":156,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":89.06},{"place":157,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":89.06},{"place":158,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":89},{"place":159,"model":"o3","company":"openai","family":"o3","version":"o3","score":88.9},{"place":160,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":88.9},{"place":161,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.8},{"place":162,"model":"nemotron-labs-3-elastic-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88.54},{"place":163,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":88.4},{"place":164,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":88.3},{"place":165,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":88.3},{"place":166,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.1},{"place":167,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88},{"place":168,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":88},{"place":169,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88},{"place":170,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":88},{"place":171,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":88},{"place":172,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":88},{"place":173,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88},{"place":174,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87.92},{"place":175,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":87.9},{"place":176,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":87.8},{"place":177,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.7},{"place":178,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":87.66},{"place":179,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":87.66},{"place":180,"model":"deepseek-v3-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.5},{"place":181,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":87.5},{"place":182,"model":"o3","company":"openai","family":"o3","version":"o3","score":87.5},{"place":183,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":87.5},{"place":184,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":87.5},{"place":185,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.3},{"place":186,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":87.1},{"place":187,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87},{"place":188,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87},{"place":189,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":87},{"place":190,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":86.98},{"place":191,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86.9},{"place":192,"model":"golongrl-30b-a3b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":86.9},{"place":193,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.7},{"place":194,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":86.7},{"place":195,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":86.7},{"place":196,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":86.7},{"place":197,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":86.67},{"place":198,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":86.67},{"place":199,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":86.67},{"place":200,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.67},{"place":201,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":86.67},{"place":202,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":86.58},{"place":203,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":86.5},{"place":204,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":86.3},{"place":205,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":86},{"place":206,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":85.83},{"place":207,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":85.6},{"place":208,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":85.3},{"place":209,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":85.2},{"place":210,"model":"ring-flash-linear-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":85.1},{"place":211,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.1},{"place":212,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":85},{"place":213,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85},{"place":214,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":85},{"place":215,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.8},{"place":216,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":84.7},{"place":217,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.6},{"place":218,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":84.4},{"place":219,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":84.4},{"place":220,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":84.3},{"place":221,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":84.3},{"place":222,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":84.2},{"place":223,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":84.2},{"place":224,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":84.17},{"place":225,"model":"openreasoning-nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":84},{"place":226,"model":"claude-4.5-haiku-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84},{"place":227,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.96},{"place":228,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":83.8},{"place":229,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.75},{"place":230,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":83.67},{"place":231,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.59},{"place":232,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":83.48},{"place":233,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":83.3},{"place":234,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":83.3},{"place":235,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":83.3},{"place":236,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":83.3},{"place":237,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.1},{"place":238,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":83.1},{"place":239,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.1},{"place":240,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":83},{"place":241,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83},{"place":242,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":82.9},{"place":243,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":82.71},{"place":244,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.7},{"place":245,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":82.7},{"place":246,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.6},{"place":247,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":82.5},{"place":248,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":82.5},{"place":249,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.3},{"place":250,"model":"openreasoning-nemotron-14b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":82},{"place":251,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":82},{"place":252,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":82},{"place":253,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":81.9},{"place":254,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":81.9},{"place":255,"model":"gka-primed-hqwen3-32b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":81.67},{"place":256,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.5},{"place":257,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":81.5},{"place":258,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":81.4},{"place":259,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":81.3},{"place":260,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.3},{"place":261,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":81.3},{"place":262,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.3},{"place":263,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":81.2},{"place":264,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":81.04},{"place":265,"model":"golongrl-4b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":80.8},{"place":266,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":80.7},{"place":267,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.7},{"place":268,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":80.6},{"place":269,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":80.3},{"place":270,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":80.3},{"place":271,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":80.2},{"place":272,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":80.2},{"place":273,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.2},{"place":274,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":80.1},{"place":275,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":80},{"place":276,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":80},{"place":277,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":80},{"place":278,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":80},{"place":279,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":80},{"place":280,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":80},{"place":281,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.8},{"place":282,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":79.8},{"place":283,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.8},{"place":284,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":79.4},{"place":285,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":79.2},{"place":286,"model":"underdog-saluki-27b-1.0","company":"conwayresearch","family":"Underdog","version":"Underdog 1.0","score":79.2},{"place":287,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.8},{"place":288,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.8},{"place":289,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":78.8},{"place":290,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":78.7},{"place":291,"model":"ministral-3-8b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":78.7},{"place":292,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.5},{"place":293,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":78.33},{"place":294,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":78.33},{"place":295,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":78.33},{"place":296,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.33},{"place":297,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":78.3},{"place":298,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.3},{"place":299,"model":"gpt-oss-120b-2025-08-05","company":"openai","family":"GPT","version":"GPT-OSS","score":78.3},{"place":300,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":78.3},{"place":301,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":78.2},{"place":302,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":78.1},{"place":303,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":78},{"place":304,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":78},{"place":305,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":306,"model":"ring-mini-sparse-2.0-exp","company":"antgroup","family":"Ring","version":"Ring 2.0","score":77.92},{"place":307,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":77.72},{"place":308,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":77.7},{"place":309,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":77.5},{"place":310,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":77.34},{"place":311,"model":"grok-3-beta-think","company":"xai","family":"Grok","version":"Grok 3","score":77.3},{"place":312,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":76.9},{"place":313,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":76.8},{"place":314,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":76.7},{"place":315,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":76},{"place":316,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.83},{"place":317,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.8},{"place":318,"model":"gemini-2.5-flash-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.8},{"place":319,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":75.8},{"place":320,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":75.8},{"place":321,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":75.5},{"place":322,"model":"qwen3-32b-thinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":75.47},{"place":323,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":75.21},{"place":324,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":75.2},{"place":325,"model":"aquif-3.6-1b","company":"aquif","family":"Aquif","version":"Aquif 3.6","score":75},{"place":326,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":75},{"place":327,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":75},{"place":328,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":74.8},{"place":329,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":74.8},{"place":330,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":74.6},{"place":331,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":74.6},{"place":332,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":74.6},{"place":333,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.58},{"place":334,"model":"vibethinker-1.5b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":74.4},{"place":335,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":74.3},{"place":336,"model":"ring-mini-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":74.06},{"place":337,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":74},{"place":338,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":74},{"place":339,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":74},{"place":340,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.7},{"place":341,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":73.7},{"place":342,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.7},{"place":343,"model":"gka-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":73.67},{"place":344,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":73.4},{"place":345,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":73.4},{"place":346,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":73.33},{"place":347,"model":"gdn-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":73.33},{"place":348,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":73.33},{"place":349,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":73.33},{"place":350,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.3},{"place":351,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":73.3},{"place":352,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":73.3},{"place":353,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":73.23},{"place":354,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":73.1},{"place":355,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":73},{"place":356,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.9},{"place":357,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":72.9},{"place":358,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.9},{"place":359,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":72.7},{"place":360,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":72.5},{"place":361,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":72.5},{"place":362,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":72.1},{"place":363,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":72.1},{"place":364,"model":"ministral-3-3b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":72.1},{"place":365,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":72.08},{"place":366,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":72},{"place":367,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":72},{"place":368,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":72},{"place":369,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":71.88},{"place":370,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.67},{"place":371,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":71.35},{"place":372,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.25},{"place":373,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":71.2},{"place":374,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":71},{"place":375,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71},{"place":376,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.9},{"place":377,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.9},{"place":378,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.9},{"place":379,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.9},{"place":380,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":70.7},{"place":381,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.7},{"place":382,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":70.42},{"place":383,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":384,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":385,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":70.2},{"place":386,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.1},{"place":387,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70},{"place":388,"model":"deepseek-tng-r1t2-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T2","score":70},{"place":389,"model":"o1","company":"openai","family":"o1","version":"o1","score":70},{"place":390,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":70},{"place":391,"model":"deepseek-r1-0120","company":"deepseek","family":"DeepSeek","version":"0120","score":70},{"place":392,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70},{"place":393,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":69.7},{"place":394,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.7},{"place":395,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":69.5},{"place":396,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.3},{"place":397,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.3},{"place":398,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":69.2},{"place":399,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":69.17},{"place":400,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.17},{"place":401,"model":"ring-lite","company":"antgroup","family":"Ring","version":"Ring Lite","score":69.1},{"place":402,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.1},{"place":403,"model":"gemini-2.5-flash-lite-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":69},{"place":404,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":68.7},{"place":405,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.67},{"place":406,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":68.53},{"place":407,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":68.44},{"place":408,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":68.4},{"place":409,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":68.3},{"place":410,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.9},{"place":411,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":67.8},{"place":412,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":67.5},{"place":413,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.3},{"place":414,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.67},{"place":415,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.67},{"place":416,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":66.5},{"place":417,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":66.46},{"place":418,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":66.2},{"place":419,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":65.9},{"place":420,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":65.83},{"place":421,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.8},{"place":422,"model":"qwen3-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":65.6},{"place":423,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":65.4},{"place":424,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":65},{"place":425,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":65},{"place":426,"model":"magistral-medium-1.0","company":"mistral","family":"Magistral","version":"Magistral 1.0","score":64.95},{"place":427,"model":"magistral-medium","company":"magistral","family":"Magistral","version":"Magistral","score":64.9},{"place":428,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":64.9},{"place":429,"model":"acereason-nemotron-1.1","company":"nvidia","family":"AceReason","version":"1.1","score":64.8},{"place":430,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":64.7},{"place":431,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":64.6},{"place":432,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":64.27},{"place":433,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.2},{"place":434,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.2},{"place":435,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":64.06},{"place":436,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":63.96},{"place":437,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":63.74},{"place":438,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":63.6},{"place":439,"model":"qwen3-4b-saferl-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63.5},{"place":440,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":63.33},{"place":441,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":63.33},{"place":442,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.33},{"place":443,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":63.33},{"place":444,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":63.23},{"place":445,"model":"phi-4-reasoning","company":"microsoft","family":"Phi","version":"Phi 4","score":63.1},{"place":446,"model":"magistral-small-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":62.8},{"place":447,"model":"magistral-small-1.0","company":"mistral","family":"Magistral","version":"Magistral 1.0","score":62.76},{"place":448,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":62.7},{"place":449,"model":"questa-nemotron-1.5b","company":"amazon","family":"Nemotron","version":"QuestA Nemotron","score":62.29},{"place":450,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":62.08},{"place":451,"model":"magistral-small-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":62.03},{"place":452,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":62},{"place":453,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":61.9},{"place":454,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":61.88},{"place":455,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":61.7},{"place":456,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.5},{"place":457,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":61.3},{"place":458,"model":"magistral-medium-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":60.99},{"place":459,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":60.6},{"place":460,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":60},{"place":461,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":60},{"place":462,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":60},{"place":463,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":60},{"place":464,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":59.58},{"place":465,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":59.43},{"place":466,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":59},{"place":467,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":58.9},{"place":468,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":58.6},{"place":469,"model":"deepseek-tng-r1t-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T","score":58.3},{"place":470,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":57.9},{"place":471,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":57.6},{"place":472,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":57.3},{"place":473,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":57.2},{"place":474,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":57},{"place":475,"model":"command-a-reasoning-08-2025","company":"cohere","family":"Command","version":"Command","score":57},{"place":476,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":56.9},{"place":477,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":56.67},{"place":478,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":56.3},{"place":479,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56.3},{"place":480,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.07},{"place":481,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":55.9},{"place":482,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":55.89},{"place":483,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":55.4},{"place":484,"model":"glm-z1","company":"zai","family":"GLM","version":"GLM Z1","score":55.4},{"place":485,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":55.21},{"place":486,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":55.2},{"place":487,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":54.8},{"place":488,"model":"skywork-or1-7b","company":"skywork","family":"Skywork OR1","version":"Skywork OR1","score":54.6},{"place":489,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.28},{"place":490,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":53.33},{"place":491,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":53.3},{"place":492,"model":"jan-code-4b","company":"menlo","family":"Jan","version":"Jan Code","score":53},{"place":493,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.88},{"place":494,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":51.87},{"place":495,"model":"deepseek-r1-distill-32b","company":"deepseek","family":"DeepSeek-R1","version":"32B","score":51.8},{"place":496,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":51.7},{"place":497,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":51.67},{"place":498,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":51.4},{"place":499,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":51},{"place":500,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":50.16},{"place":501,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":50.1},{"place":502,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":49.8},{"place":503,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":49.8},{"place":504,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":49.5},{"place":505,"model":"nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":49.5},{"place":506,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":49.5},{"place":507,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.33},{"place":508,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":49.2},{"place":509,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.75},{"place":510,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":48.7},{"place":511,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.1},{"place":512,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":48},{"place":513,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":47.9},{"place":514,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":47.66},{"place":515,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.4},{"place":516,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":47},{"place":517,"model":"jan-v3","company":"menlo","family":"Jan","version":"Jan v3","score":47},{"place":518,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47},{"place":519,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":46.9},{"place":520,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":46.7},{"place":521,"model":"gpt-oss-20b-moe","company":"openai","family":"GPT","version":"GPT-OSS","score":46.7},{"place":522,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":46.7},{"place":523,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.6},{"place":524,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":46.6},{"place":525,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":46},{"place":526,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.9},{"place":527,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":45.6},{"place":528,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":45.2},{"place":529,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":43.33},{"place":530,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":43.3},{"place":531,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.3},{"place":532,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.92},{"place":533,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":42.53},{"place":534,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":41.9},{"place":535,"model":"k2-horizon-0.9b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":41.7},{"place":536,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.3},{"place":537,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":40.42},{"place":538,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":40.4},{"place":539,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":40.4},{"place":540,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":40.2},{"place":541,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":40},{"place":542,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":40},{"place":543,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":39},{"place":544,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":38.75},{"place":545,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.1},{"place":546,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37.1},{"place":547,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":37},{"place":548,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":37},{"place":549,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.8},{"place":550,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":36.7},{"place":551,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":36.7},{"place":552,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":36.7},{"place":553,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":36.67},{"place":554,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":36.67},{"place":555,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":36.67},{"place":556,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":36.5},{"place":557,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":36.27},{"place":558,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":36},{"place":559,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":35.83},{"place":560,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":35.8},{"place":561,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":35.1},{"place":562,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":34.4},{"place":563,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.33},{"place":564,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.27},{"place":565,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":34.2},{"place":566,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.2},{"place":567,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":33.9},{"place":568,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":33.33},{"place":569,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":33.33},{"place":570,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":33.3},{"place":571,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":33.3},{"place":572,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":33.1},{"place":573,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":32.5},{"place":574,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.08},{"place":575,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":31.88},{"place":576,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":31.73},{"place":577,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":31.7},{"place":578,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":31.7},{"place":579,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":31.67},{"place":580,"model":"mobilellm-r1.5-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":31.1},{"place":581,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.6},{"place":582,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":29.2},{"place":583,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":29.17},{"place":584,"model":"aquif-3.5-nano-1b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":28.7},{"place":585,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":27.3},{"place":586,"model":"lfm2-350m-math","company":"liquidai","family":"LFM","version":"LFM2","score":27.1},{"place":587,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":27},{"place":588,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":26.7},{"place":589,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.4},{"place":590,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.33},{"place":591,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26},{"place":592,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":25.83},{"place":593,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":25.8},{"place":594,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":25},{"place":595,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":24.7},{"place":596,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":24.7},{"place":597,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":24.17},{"place":598,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":24},{"place":599,"model":"apertus-v1.5-8b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":23.8},{"place":600,"model":"qwen3-8b-nothinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":23.4},{"place":601,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":23.4},{"place":602,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.3},{"place":603,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":23.3},{"place":604,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":23.3},{"place":605,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":23.1},{"place":606,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":22.9},{"place":607,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":22.71},{"place":608,"model":"lfm2-2.6b-exp","company":"liquidai","family":"LFM","version":"LFM2","score":22.67},{"place":609,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":22.08},{"place":610,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.7},{"place":611,"model":"apertus-v1.5-70b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":21.7},{"place":612,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.6},{"place":613,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.3},{"place":614,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":21.2},{"place":615,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":20.9},{"place":616,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":20.9},{"place":617,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":20.83},{"place":618,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":20.8},{"place":619,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":20.4},{"place":620,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":20.2},{"place":621,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":20},{"place":622,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":20},{"place":623,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":19.3},{"place":624,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":19.17},{"place":625,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":18.8},{"place":626,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":18.75},{"place":627,"model":"qwen3-4b-saferl","company":"qwen","family":"Qwen","version":"Qwen3","score":18.2},{"place":628,"model":"qwen3-6b","company":"qwen","family":"Qwen","version":"Qwen3","score":17.8},{"place":629,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":17.3},{"place":630,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":17},{"place":631,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":16.67},{"place":632,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":16.3},{"place":633,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":16.25},{"place":634,"model":"ernie-4.5-21b-a3b-pt","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":16.1},{"place":635,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":15.21},{"place":636,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":15.2},{"place":637,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":15.1},{"place":638,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":15},{"place":639,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":15},{"place":640,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":14.7},{"place":641,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":14},{"place":642,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":13.96},{"place":643,"model":"aquif-3.5-2.7b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":13.4},{"place":644,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":13.4},{"place":645,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":13.33},{"place":646,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":12.7},{"place":647,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":12.5},{"place":648,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":12.5},{"place":649,"model":"gpt-oss-20b-2025-08-05","company":"openai","family":"GPT","version":"GPT-OSS","score":11.7},{"place":650,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":11.67},{"place":651,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":11.46},{"place":652,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":11.46},{"place":653,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":11.04},{"place":654,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":10.83},{"place":655,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":10.83},{"place":656,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":10.8},{"place":657,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":10.8},{"place":658,"model":"mobilellm-r1.5-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":10.6},{"place":659,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":10.2},{"place":660,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":10},{"place":661,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":10},{"place":662,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":9.83},{"place":663,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.8},{"place":664,"model":"aquif-3-3.2b","company":"aquif","family":"Aquif","version":"Aquif 3","score":9.6},{"place":665,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":9.58},{"place":666,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.58},{"place":667,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.33},{"place":668,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":9.3},{"place":669,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":8.96},{"place":670,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":8.8},{"place":671,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":8.67},{"place":672,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":8.4},{"place":673,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":8.33},{"place":674,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":8.3},{"place":675,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":8.2},{"place":676,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":8},{"place":677,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":7.5},{"place":678,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":7.2},{"place":679,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":7},{"place":680,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":7},{"place":681,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":6.3},{"place":682,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":6.3},{"place":683,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":6.25},{"place":684,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":5.83},{"place":685,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":5.8},{"place":686,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":5.42},{"place":687,"model":"phi-4-mini-3.8b","company":"microsoft","family":"Phi","version":"Phi 4 mini","score":5.3},{"place":688,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":5},{"place":689,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":4.93},{"place":690,"model":"exaone-3.5-2.4b","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":4.5},{"place":691,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":4.38},{"place":692,"model":"apriel-5b-instruct","company":"servicenow","family":"Apriel","version":"Apriel","score":4.3},{"place":693,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":4.2},{"place":694,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":4.17},{"place":695,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":3.33},{"place":696,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":3.23},{"place":697,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.9},{"place":698,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":2.7},{"place":699,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":2.5},{"place":700,"model":"codestral-2501","company":"mistral","family":"Codestral","version":"Codestral","score":2.5},{"place":701,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":2.29},{"place":702,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1.7},{"place":703,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1.7},{"place":704,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":1.67},{"place":705,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1.67},{"place":706,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1.25},{"place":707,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":1.25},{"place":708,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1.25},{"place":709,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1.04},{"place":710,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":1},{"place":711,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1},{"place":712,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":1},{"place":713,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1},{"place":714,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":0.9},{"place":715,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":0.9},{"place":716,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.9},{"place":717,"model":"ministral-3b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":0.83},{"place":718,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":0.83},{"place":719,"model":"ministral-3b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":0.8},{"place":720,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":0.8},{"place":721,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":0.67},{"place":722,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":0.6},{"place":723,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":0.42},{"place":724,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":0.4},{"place":725,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":0.33},{"place":726,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":0.31},{"place":727,"model":"llama-3.1-3b","company":"meta","family":"Llama","version":"Llama 3.1","score":0.3},{"place":728,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.3},{"place":729,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":0.21},{"place":730,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":0.21},{"place":731,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.21},{"place":732,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":0.2},{"place":733,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":0.2},{"place":734,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":0.2},{"place":735,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":0.1},{"place":736,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":0.1},{"place":737,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":0.1},{"place":738,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0.1},{"place":739,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":740,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":0},{"place":741,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0},{"place":742,"model":"open-mixtral-8x22b-2404","company":"mistral","family":"Mixtral","version":"Mixtral","score":0},{"place":743,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":0},{"place":744,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":745,"model":"codestral-12b-instruct","company":"mistral","family":"Codestral","version":"Codestral","score":0},{"place":746,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":747,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":0}]},{"id":"aime-2026-i","name":"AIME 2026 I","topic":"Math (competition)","description":"American Invitational Mathematics Examination 2026 I problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":100,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":171,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":100},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":100},{"place":3,"model":"darwin-180b-rsi","company":"finalbench","family":"Darwin","version":"Darwin","score":100},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":99.9},{"place":5,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":99.2},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":99.2},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":99.17},{"place":8,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":98.8},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":98.7},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":98.33},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98.3},{"place":12,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":98.3},{"place":13,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":98.3},{"place":14,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":98.2},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":98},{"place":16,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":97.8},{"place":17,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":97.7},{"place":18,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":97.7},{"place":19,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":97.6},{"place":20,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":97.5},{"place":21,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":97.1},{"place":22,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":97.1},{"place":23,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":97},{"place":24,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":97},{"place":25,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":97},{"place":26,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":97},{"place":27,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":96.7},{"place":28,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":96.7},{"place":29,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":96.7},{"place":30,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":96.7},{"place":31,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":96.67},{"place":32,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":96.67},{"place":33,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":96.5},{"place":34,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":96.41},{"place":35,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":96.4},{"place":36,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":96.4},{"place":37,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":96.3},{"place":38,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":96},{"place":39,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":96},{"place":40,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95.83},{"place":41,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":95.83},{"place":42,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":95.83},{"place":43,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":95.8},{"place":44,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":95.8},{"place":45,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":95.8},{"place":46,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95.8},{"place":47,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":95.8},{"place":48,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95.8},{"place":49,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95.8},{"place":50,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":95.78},{"place":51,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":95.7},{"place":52,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":95.7},{"place":53,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":95.6},{"place":54,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":95.5},{"place":55,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":95.4},{"place":56,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":95.4},{"place":57,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":95.4},{"place":58,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":95.4},{"place":59,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":95.31},{"place":60,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":95.3},{"place":61,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":95.3},{"place":62,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":95.3},{"place":63,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95.2},{"place":64,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":95.2},{"place":65,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":95.1},{"place":66,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":95.1},{"place":67,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":95.1},{"place":68,"model":"ring-1t-2.5-heavy-thinking","company":"antgroup","family":"Ring","version":"Ring 2.5","score":95},{"place":69,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":95},{"place":70,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":95},{"place":71,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":94.7},{"place":72,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.6},{"place":73,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.58},{"place":74,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":94.5},{"place":75,"model":"mai-thinking-1","company":"microsoft","family":"MAI","version":"MAI-Thinking-1","score":94.5},{"place":76,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.5},{"place":77,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":94.4},{"place":78,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":94.3},{"place":79,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":94.2},{"place":80,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":94.2},{"place":81,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":94.2},{"place":82,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":94.2},{"place":83,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":94.1},{"place":84,"model":"ring-1t-2.5","company":"antgroup","family":"Ring","version":"Ring 2.5","score":93.75},{"place":85,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":93.6},{"place":86,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.33},{"place":87,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.3},{"place":88,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":93.3},{"place":89,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":93.3},{"place":90,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":93.3},{"place":91,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":93.3},{"place":92,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.3},{"place":93,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":93.3},{"place":94,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":93.3},{"place":95,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":93.3},{"place":96,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":93.3},{"place":97,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":93.2},{"place":98,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":93.2},{"place":99,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93},{"place":100,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":92.9},{"place":101,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.9},{"place":102,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":92.9},{"place":103,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":92.71},{"place":104,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.7},{"place":105,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.6},{"place":106,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":92.6},{"place":107,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.5},{"place":108,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":92.5},{"place":109,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":92.5},{"place":110,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.5},{"place":111,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":92.4},{"place":112,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":92.3},{"place":113,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":92.3},{"place":114,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":92.2},{"place":115,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.1},{"place":116,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.08},{"place":117,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.7},{"place":118,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.7},{"place":119,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.3},{"place":120,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":91.3},{"place":121,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":91.2},{"place":122,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.1},{"place":123,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91},{"place":124,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":91},{"place":125,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":90.9},{"place":126,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.8},{"place":127,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":90.8},{"place":128,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":90.8},{"place":129,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":90.7},{"place":130,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":90.62},{"place":131,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.6},{"place":132,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.4},{"place":133,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":90.2},{"place":134,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":90.2},{"place":135,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":90.2},{"place":136,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.1},{"place":137,"model":"xing4.0-29b-a4b","company":"teleai","family":"Xing","version":"Xing4.0","score":90},{"place":138,"model":"thomson-1.0-small","company":"thomsonreuters","family":"Thomson","version":"Thomson-1.0","score":90},{"place":139,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.9},{"place":140,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":89.8},{"place":141,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.8},{"place":142,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.4},{"place":143,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":89.2},{"place":144,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":89.2},{"place":145,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":89.1},{"place":146,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":89},{"place":147,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":88.8},{"place":148,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":88.75},{"place":149,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88.59},{"place":150,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":88.5},{"place":151,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":88.3},{"place":152,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.3},{"place":153,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":88.3},{"place":154,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.2},{"place":155,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.92},{"place":156,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87.9},{"place":157,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":87.86},{"place":158,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":87.7},{"place":159,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":87.7},{"place":160,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.5},{"place":161,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":87.4},{"place":162,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":87.4},{"place":163,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.3},{"place":164,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":87.3},{"place":165,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":87.1},{"place":166,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":87.08},{"place":167,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":86.7},{"place":168,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.7},{"place":169,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":86.5},{"place":170,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":86.5},{"place":171,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":86.4},{"place":172,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":86.3},{"place":173,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.4},{"place":174,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.1},{"place":175,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":85},{"place":176,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.5},{"place":177,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":84.1},{"place":178,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84},{"place":179,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":83.8},{"place":180,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":83.5},{"place":181,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.3},{"place":182,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":83.1},{"place":183,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83},{"place":184,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.7},{"place":185,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82.5},{"place":186,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":82.2},{"place":187,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.1},{"place":188,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":81.5},{"place":189,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.46},{"place":190,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.42},{"place":191,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":80.2},{"place":192,"model":"underdog-saluki-27b-1.0","company":"conwayresearch","family":"Underdog","version":"Underdog 1.0","score":80},{"place":193,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":79},{"place":194,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":78.9},{"place":195,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.5},{"place":196,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.5},{"place":197,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.88},{"place":198,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":76.46},{"place":199,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":76.46},{"place":200,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.04},{"place":201,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":76},{"place":202,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.83},{"place":203,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":75.16},{"place":204,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":75},{"place":205,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.17},{"place":206,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":73.85},{"place":207,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":73.6},{"place":208,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":72.92},{"place":209,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72},{"place":210,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":71.67},{"place":211,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.42},{"place":212,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":69.4},{"place":213,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":69.17},{"place":214,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":69.1},{"place":215,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.1},{"place":216,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":68.67},{"place":217,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":66.98},{"place":218,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.67},{"place":219,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.67},{"place":220,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":66.41},{"place":221,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":66.2},{"place":222,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":66.16},{"place":223,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":65.73},{"place":224,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":62.1},{"place":225,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":60.1},{"place":226,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":59.6},{"place":227,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.33},{"place":228,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":57.7},{"place":229,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":57.5},{"place":230,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":56.7},{"place":231,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":56.67},{"place":232,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.3},{"place":233,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":50},{"place":234,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":49.22},{"place":235,"model":"k2-horizon-0.9b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":48.5},{"place":236,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":45.2},{"place":237,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45},{"place":238,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.5},{"place":239,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":41},{"place":240,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.67},{"place":241,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":40.42},{"place":242,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":40.4},{"place":243,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":40.37},{"place":244,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.8},{"place":245,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.8},{"place":246,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":37.71},{"place":247,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37.5},{"place":248,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":35.68},{"place":249,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":35.05},{"place":250,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":31.67},{"place":251,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.8},{"place":252,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30},{"place":253,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29},{"place":254,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":20.8},{"place":255,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":12.29},{"place":256,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":3.33},{"place":257,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":0.6},{"place":258,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.21},{"place":259,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.2}]},{"id":"aime-2026-i-with-tools","name":"AIME 2026 I (with tools)","topic":"Math competition (with tools)","description":"AIME 2026 I problems solved with tool (code execution) access.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":99.9,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":99.9},{"place":2,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":99.6},{"place":3,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":92.6},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":81.2}]},{"id":"ainstein-swe-bench","name":"AInstein-SWE-Bench","topic":"Agentic coding","description":"AInstein agent coding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":42.8,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":42.8},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":36.7},{"place":3,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":35.4},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33.7},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":19.3}]},{"id":"alignbench","name":"AlignBench","topic":"Alignment and instruction following","description":"Benchmark for instruction-following quality and alignment behavior.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Hunyuan-Large-Instruct","top_percent":8.3,"top_model_id":"hunyuan-large-instruct","top_generation":"Hunyuan-Large","top_model_base":"Hunyuan-Large","top_model_family":"Hunyuan","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":98,"total_models":3854,"placements":[{"place":1,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":8.3},{"place":2,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":8.27},{"place":3,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":8.24},{"place":4,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":8.19},{"place":5,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.16},{"place":6,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":8.15},{"place":7,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":8.15},{"place":8,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":8.07},{"place":9,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":8.04},{"place":10,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":8.03},{"place":11,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":8.01},{"place":12,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":8},{"place":13,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":8},{"place":14,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":8},{"place":15,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.99},{"place":16,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.94},{"place":17,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.93},{"place":18,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":7.91},{"place":19,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":7.91},{"place":20,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.9},{"place":21,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":7.9},{"place":22,"model":"ernie-bot-4.0-202404","company":"baidu","family":"ERNIE","version":"ERNIE 4.0","score":7.89},{"place":23,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":7.88},{"place":24,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":7.88},{"place":25,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.87},{"place":26,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.86},{"place":27,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":7.84},{"place":28,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":7.81},{"place":29,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":7.74},{"place":30,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":7.74},{"place":31,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":7.69},{"place":32,"model":"glm-4-0116","company":"zai","family":"GLM","version":"GLM 4","score":7.66},{"place":33,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":7.65},{"place":34,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":7.59},{"place":35,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":7.54},{"place":36,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":7.53},{"place":37,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":7.53},{"place":38,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.51},{"place":39,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":7.47},{"place":40,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":7.46},{"place":41,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":7.42},{"place":42,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":7.38},{"place":43,"model":"ernie-bot-4.0-202312","company":"baidu","family":"ERNIE","version":"ERNIE 4.0","score":7.36},{"place":44,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":7.36},{"place":45,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.33},{"place":46,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.28},{"place":47,"model":"moonshot-v1-32k-202404","company":"moonshotai","family":"Moonshot","version":"Moonshot v1","score":7.22},{"place":48,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":7.22},{"place":49,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":7.21},{"place":50,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":7.2},{"place":51,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":7.2},{"place":52,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.2},{"place":53,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.19},{"place":54,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.19},{"place":55,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":7.17},{"place":56,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":7.13},{"place":57,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":7.1},{"place":58,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":7.1},{"place":59,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":7.1},{"place":60,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.1},{"place":61,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":7.05},{"place":62,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":7.02},{"place":63,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":7.01},{"place":64,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":6.96},{"place":65,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":6.9},{"place":66,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":6.85},{"place":67,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":6.83},{"place":68,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":6.8},{"place":69,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":6.74},{"place":70,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":6.61},{"place":71,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":6.6},{"place":72,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":6.5},{"place":73,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":6.44},{"place":74,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":6.43},{"place":75,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":6.26},{"place":76,"model":"chatglm-turbo","company":"zai","family":"ChatGLM","version":"ChatGLM","score":6.24},{"place":77,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":6.2},{"place":78,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":6.2},{"place":79,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":6.2},{"place":80,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":6.2},{"place":81,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":6.17},{"place":82,"model":"ernie-bot-3.5","company":"baidu","family":"ERNIE","version":"ERNIE 3.5","score":6.14},{"place":83,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":6.12},{"place":84,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":6.1},{"place":85,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":6.08},{"place":86,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":6.02},{"place":87,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":6},{"place":88,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":5.95},{"place":89,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":5.94},{"place":90,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":5.9},{"place":91,"model":"chatglm-pro","company":"zai","family":"ChatGLM","version":"ChatGLM","score":5.83},{"place":92,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":5.82},{"place":93,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":5.81},{"place":94,"model":"sparkdesk-v2","company":"iflytek","family":"Spark","version":"Spark V2","score":5.74},{"place":95,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":5.74},{"place":96,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":5.73},{"place":97,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":5.72},{"place":98,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":5.7},{"place":99,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":5.7},{"place":100,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":5.68},{"place":101,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":5.56},{"place":102,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":5.51},{"place":103,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":5.4},{"place":104,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":5.3},{"place":105,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":5.3},{"place":106,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":5.3},{"place":107,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":5.27},{"place":108,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":5.25},{"place":109,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":5.12},{"place":110,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":5.1},{"place":111,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":5.04},{"place":112,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":5},{"place":113,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":5},{"place":114,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":4.97},{"place":115,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":4.97},{"place":116,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":4.96},{"place":117,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":4.91},{"place":118,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":4.9},{"place":119,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":4.75},{"place":120,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":4.7},{"place":121,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":4.7},{"place":122,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":4.63},{"place":123,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":4.48},{"place":124,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":4.33},{"place":125,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":3.97},{"place":126,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":3.65},{"place":127,"model":"chinese-llama-2-7b-chat","company":"hfl","family":"Chinese-LLaMA","version":"Chinese-LLaMA-2","score":3.57},{"place":128,"model":"llama-2-13b-chinese-chat","company":"flagalpha","family":"Llama2-Chinese","version":"Llama2-Chinese","score":3.35},{"place":129,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":3.2},{"place":130,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":2.85}]},{"id":"all-angles-bench","name":"All-Angles Bench","topic":"Spatial perception","description":"All-Angles benchmark for spatial recognition and 3D perception.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.6-35B-A3B","top_percent":64,"top_model_id":"qwen3.6-35b-a3b","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 35B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64},{"place":2,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":63.4},{"place":3,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":57.21},{"place":4,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":56.9},{"place":5,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":55.1},{"place":6,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":53.24},{"place":7,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":52.7},{"place":8,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":52.4},{"place":9,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":51.62},{"place":10,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":49},{"place":11,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":48.9},{"place":12,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":48.2},{"place":13,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.7},{"place":14,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.88},{"place":15,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":45.29},{"place":16,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":43.8},{"place":17,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.3}]},{"id":"almieyar","name":"Almieyar","topic":"Arabic linguistics","description":"Arabic linguistic competence benchmark across phonology, morphology, syntax, semantics and pragmatics.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Fanar-2-27B-Instruct","top_percent":79.46,"top_model_id":"fanar-2-27b-instruct","top_generation":"Fanar 2.0","top_model_base":"Fanar","top_model_family":"Fanar","top_company":"qcri","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":79.46},{"place":2,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":70.48},{"place":3,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.18},{"place":4,"model":"acegpt-v2-32b-chat","company":"freedomintelligence","family":"AceGPT","version":"AceGPT-v2","score":55.24}]},{"id":"alpacaeval","name":"AlpacaEval","topic":"Instruction following","description":"Automatic eval using GPT-4 as a judge.","url":"https://github.com/tatsu-lab/alpaca_eval","leaderboard":"","github":"","paper":"","metric":"percent","stars":"1849","top_model":"Llama-3_1-70B-TFree-HAT-SFT","top_percent":99.4,"top_model_id":"llama-3_1-70b-tfree-hat-sft","top_generation":"Llama TFree HAT","top_model_base":"Llama 3.1 70B TFree HAT","top_model_family":"Llama TFree HAT","top_company":"alephalpha","top_open_source":1,"lower_is_better":false,"bench_models":51,"total_models":3854,"placements":[{"place":1,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":99.4},{"place":2,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":99.3},{"place":3,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":96.1},{"place":4,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":94.5},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.49},{"place":6,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.21},{"place":7,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":56.16},{"place":8,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.9},{"place":9,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":51.39},{"place":10,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.29},{"place":11,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":48.32},{"place":12,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":46.8},{"place":13,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":46.66},{"place":14,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.13},{"place":15,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":45.81},{"place":16,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":45.19},{"place":17,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":43.55},{"place":18,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":40.92},{"place":19,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.28},{"place":20,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":40.23},{"place":21,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39.64},{"place":22,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39.26},{"place":23,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":38.27},{"place":24,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.51},{"place":25,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":36.3},{"place":26,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":36.26},{"place":27,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":33.39},{"place":28,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":31.09},{"place":29,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":29.48},{"place":30,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.35},{"place":31,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":28.18},{"place":32,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":27.56},{"place":33,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":27.12},{"place":34,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":25.48},{"place":35,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":24.31},{"place":36,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.89},{"place":37,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":21.39},{"place":38,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":19.69},{"place":39,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":17.87},{"place":40,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":17.37},{"place":41,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":16.8},{"place":42,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":14.82},{"place":43,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":10.79},{"place":44,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":9.7},{"place":45,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.59},{"place":46,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.54},{"place":47,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":9.38},{"place":48,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":8.9},{"place":49,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":6.98},{"place":50,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":3.76},{"place":51,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":3.72},{"place":52,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":3.71},{"place":53,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":3.26},{"place":54,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":2.32},{"place":55,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":2.01}]},{"id":"alpacaeval-1.0","name":"AlpacaEval 1.0","topic":"Instruction following","description":"Original AlpacaEval: win rate against text-davinci-003 judged by GPT-4.","url":"https://github.com/tatsu-lab/alpaca_eval","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-4 Turbo (11-06)","top_percent":97.7,"top_model_id":"gpt-4-1106-preview","top_generation":"GPT-4","top_model_base":"GPT-4 Turbo","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":45,"total_models":3854,"placements":[{"place":1,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":97.7},{"place":2,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":97.7},{"place":3,"model":"mistral-medium","company":"mistral","family":"Mistral","version":"Mistral","score":96.8},{"place":4,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":95.3},{"place":5,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":94.8},{"place":6,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":94.8},{"place":7,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":94.1},{"place":8,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":94.08},{"place":9,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":93.8},{"place":10,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":93.4},{"place":11,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":92.8},{"place":12,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":92.7},{"place":13,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":92.66},{"place":14,"model":"claude","company":"anthropic","family":"Claude","version":"Claude 1","score":91.6},{"place":15,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":91.4},{"place":16,"model":"command","company":"cohere","family":"Command","version":"Command","score":90.6},{"place":17,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":89.4},{"place":18,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":89.37},{"place":19,"model":"vicuna-33b-v1.3","company":"lmsys","family":"Vicuna","version":"Vicuna","score":89},{"place":20,"model":"claude-2.1","company":"anthropic","family":"Claude","version":"Claude 2","score":87.1},{"place":21,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":86.3},{"place":22,"model":"phi-2-dpo","company":"microsoft","family":"Phi","version":"Phi","score":82.3},{"place":23,"model":"vicuna-13b-v1.3","company":"lmsys","family":"Vicuna","version":"Vicuna","score":82.1},{"place":24,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":81.1},{"place":25,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":79.7},{"place":26,"model":"vicuna-7b-v1.3","company":"lmsys","family":"Vicuna","version":"Vicuna","score":76.8},{"place":27,"model":"wizardlm-13b","company":"wizardlm","family":"WizardLM","version":"WizardLM-13B","score":75.3},{"place":28,"model":"guanaco-65b","company":"timdettmers","family":"Guanaco","version":"Guanaco","score":71.8},{"place":29,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":71.4},{"place":30,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":70.4},{"place":31,"model":"phi-2-sft","company":"microsoft","family":"Phi","version":"Phi","score":68.5},{"place":32,"model":"llama-33b-oasst-rlhf","company":"openassistant","family":"LLaMA","version":"LLaMA OASST","score":66.5},{"place":33,"model":"guanaco-33b","company":"timdettmers","family":"Guanaco","version":"Guanaco-33B","score":66},{"place":34,"model":"nous-hermes-13b","company":"nousresearch","family":"Nous Hermes","version":"Nous Hermes","score":65.5},{"place":35,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":64.4},{"place":36,"model":"llama-33b-oasst-sft","company":"openassistant","family":"LLaMA","version":"LLaMA OASST","score":55},{"place":37,"model":"guanaco-13b","company":"timdettmers","family":"Guanaco","version":"Guanaco","score":52.6},{"place":38,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":50},{"place":39,"model":"guanaco-7b","company":"timdettmers","family":"Guanaco","version":"Guanaco","score":46.6},{"place":40,"model":"falcon-40b-instruct","company":"tii","family":"Falcon","version":"Falcon","score":45.7},{"place":41,"model":"falcon-7b-instruct","company":"tii","family":"Falcon","version":"Falcon","score":45.7},{"place":42,"model":"alpaca-farm-ppo-sim-gpt4-7b","company":"stanford","family":"Alpaca Farm","version":"Alpaca Farm","score":44.1},{"place":43,"model":"pythia-12b-sft","company":"eleutherai","family":"Pythia","version":"Pythia","score":41.9},{"place":44,"model":"alpaca-farm-ppo-human-7b","company":"stanford","family":"Alpaca Farm","version":"Alpaca Farm","score":41.2},{"place":45,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":26.5},{"place":46,"model":"pythia-12b-oasst-sft","company":"openassistant","family":"Pythia","version":"Pythia","score":26},{"place":47,"model":"davinci-001","company":"openai","family":"Davinci","version":"Davinci","score":15.2}]},{"id":"alpacaeval-2.0","name":"AlpacaEval 2.0","topic":"Instruction following","description":"Updated AlpacaEval with improved prompts and judging.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek R1","top_percent":87.6,"top_model_id":"deepseek-r1","top_generation":"DeepSeek R1","top_model_base":"DeepSeek R1","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":121,"total_models":3854,"placements":[{"place":1,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":87.6},{"place":2,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.3},{"place":3,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.9},{"place":4,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.9},{"place":5,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":78.6},{"place":6,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.2},{"place":7,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.6},{"place":8,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":75.6},{"place":9,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.2},{"place":10,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.5},{"place":11,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.5},{"place":12,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.8},{"place":13,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":70.7},{"place":14,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":70.1},{"place":15,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":70},{"place":16,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":69.7},{"place":17,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.1},{"place":18,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":69.1},{"place":19,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.9},{"place":20,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":67.2},{"place":21,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":66.1},{"place":22,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":65.5},{"place":23,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":65},{"place":24,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":64.9},{"place":25,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":62.68},{"place":26,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":62.6},{"place":27,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":61.19},{"place":28,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":60.5},{"place":29,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":59.8},{"place":30,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":58},{"place":31,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":57.6},{"place":32,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":57.3},{"place":33,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":56.3},{"place":34,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":56.16},{"place":35,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":53.5},{"place":36,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":52.1},{"place":37,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":52},{"place":38,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":51.8},{"place":39,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":51.4},{"place":40,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":51.1},{"place":41,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":50.6},{"place":42,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":50.5},{"place":43,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":50.08},{"place":44,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":49.8},{"place":45,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":49.8},{"place":46,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.8},{"place":47,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":49.8},{"place":48,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":49.6},{"place":49,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.1},{"place":50,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":49},{"place":51,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":49},{"place":52,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.7},{"place":53,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":47.2},{"place":54,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":46.6},{"place":55,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":44.5},{"place":56,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.9},{"place":57,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":43.9},{"place":58,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":43.7},{"place":59,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":43.45},{"place":60,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.3},{"place":61,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":42.48},{"place":62,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":42.2},{"place":63,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":40.9},{"place":64,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":40.5},{"place":65,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":39.8},{"place":66,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":39.3},{"place":67,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":38.9},{"place":68,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":38.57},{"place":69,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":38.5},{"place":70,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":38},{"place":71,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":36.92},{"place":72,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":36.9},{"place":73,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":36.6},{"place":74,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":36.6},{"place":75,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":35.16},{"place":76,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":34.51},{"place":77,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":34.5},{"place":78,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":34.4},{"place":79,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":34.3},{"place":80,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":33.5},{"place":81,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":33.4},{"place":82,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":31.4},{"place":83,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":30.9},{"place":84,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":30.47},{"place":85,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":30.4},{"place":86,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":30.34},{"place":87,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":30.23},{"place":88,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":30.2},{"place":89,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":30},{"place":90,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":29.49},{"place":91,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":29},{"place":92,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":28.6},{"place":93,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":28.4},{"place":94,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":27.49},{"place":95,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":27.17},{"place":96,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":26.3},{"place":97,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":26.2},{"place":98,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":26},{"place":99,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":25.6},{"place":100,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":25.2},{"place":101,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":24.2},{"place":102,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":24},{"place":103,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":23.9},{"place":104,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":23.7},{"place":105,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":23},{"place":106,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":22.9},{"place":107,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":22.9},{"place":108,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":21.85},{"place":109,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":21.8},{"place":110,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":21.8},{"place":111,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":19.9},{"place":112,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":18.3},{"place":113,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":17.74},{"place":114,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":17.1},{"place":115,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":16.85},{"place":116,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":16.65},{"place":117,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":16.6},{"place":118,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":15.7},{"place":119,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":15.35},{"place":120,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":14.7},{"place":121,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":14.7},{"place":122,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":12.5},{"place":123,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":12.4},{"place":124,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":11.3},{"place":125,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":10.4},{"place":126,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":9.77},{"place":127,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":9.6},{"place":128,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":8.6},{"place":129,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":8.1},{"place":130,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":8},{"place":131,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":7.7},{"place":132,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":7.7},{"place":133,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":7.5},{"place":134,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":6.9},{"place":135,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":5.4},{"place":136,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":5},{"place":137,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":3.64},{"place":138,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":1.21}]},{"id":"am-2k-mad","name":"AM-2K (Box) Matting (MAD)","topic":"Image matting","description":"AM-2K (Box): box-prompted animal matting; mean absolute difference x10^3 (lower is better).","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"mad","stars":"","top_model":"WeVisOne-VL-4B","top_percent":5,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":5},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":5.7}]},{"id":"amazon-esci","name":"Amazon ESCI","topic":"Product search relevance","description":"Shopping query/product relevance (Exact, Substitute, Complement, Irrelevant); macro-F1 (Jev Decision Index suite, posed as typed decisions).","url":"https://github.com/amazon-science/esci-data","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"pplx-decider-v1.2","top_percent":62.4,"top_model_id":"pplx-decider-v1.2","top_generation":"v1.2","top_model_base":"pplx-decider","top_model_family":"pplx-decider","top_company":"perplexity","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":62.4},{"place":2,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":61.7},{"place":3,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":60.8},{"place":4,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":59},{"place":5,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":58.5},{"place":6,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":58.3},{"place":7,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":57.8},{"place":8,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":57.8},{"place":9,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":57.5},{"place":10,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":57.4},{"place":11,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":57.2},{"place":12,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":56.7},{"place":13,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":55.2},{"place":14,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":54.6},{"place":15,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":53.7},{"place":16,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":53.4},{"place":17,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":52},{"place":18,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":51.2},{"place":19,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":49.2},{"place":20,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":47.1},{"place":21,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":46.2},{"place":22,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":46.1},{"place":23,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":45.5},{"place":24,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":45.3},{"place":25,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":44.6},{"place":26,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":44.2},{"place":27,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":41.3},{"place":28,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":35},{"place":29,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":34.6},{"place":30,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":33.8},{"place":31,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":29.5},{"place":32,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":28.2},{"place":33,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":27.3},{"place":34,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":26},{"place":35,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":24.4},{"place":36,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":24.4},{"place":37,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":23.3},{"place":38,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":21.8}]},{"id":"amc-23","name":"AMC-23","topic":"Math (competition)","description":"American Mathematics Competition 2023 evaluation.","url":"https://www.maa.org/math-competitions/amc-1012","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"QwQ-32B","top_percent":98.5,"top_model_id":"qwq-32b","top_generation":"QwQ","top_model_base":"QwQ-32B","top_model_family":"QwQ","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":64,"total_models":3854,"placements":[{"place":1,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":98.5},{"place":2,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":95},{"place":3,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":95},{"place":4,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":93.5},{"place":5,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":92.5},{"place":6,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":91.64},{"place":7,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":89.16},{"place":8,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.17},{"place":9,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.81},{"place":10,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.78},{"place":11,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":70},{"place":12,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":69.38},{"place":13,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":69.06},{"place":14,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.75},{"place":15,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.34},{"place":16,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.34},{"place":17,"model":"lfm2-350m-math","company":"liquidai","family":"LFM","version":"LFM2","score":67.2},{"place":18,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.88},{"place":19,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.88},{"place":20,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":62.5},{"place":21,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":62.5},{"place":22,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":60},{"place":23,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":60},{"place":24,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":56.72},{"place":25,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":56.56},{"place":26,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":55.63},{"place":27,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":55},{"place":28,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55},{"place":29,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":53.91},{"place":30,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":52.5},{"place":31,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":52.5},{"place":32,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":52},{"place":33,"model":"qwen3-6b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.9},{"place":34,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50},{"place":35,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":48.12},{"place":36,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.09},{"place":37,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":45.78},{"place":38,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45},{"place":39,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":45},{"place":40,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":43.59},{"place":41,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.5},{"place":42,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":42.4},{"place":43,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":40.4},{"place":44,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":40.2},{"place":45,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":40},{"place":46,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39.84},{"place":47,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":39.38},{"place":48,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":36},{"place":49,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":35.2},{"place":50,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":34.4},{"place":51,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":33.13},{"place":52,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":31.2},{"place":53,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":30},{"place":54,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":29.69},{"place":55,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":28},{"place":56,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.97},{"place":57,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":25},{"place":58,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.06},{"place":59,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":22.81},{"place":60,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":22.66},{"place":61,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":19.22},{"place":62,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":12.5},{"place":63,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":7.19},{"place":64,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":6.87}]},{"id":"amobench","name":"AMO-Bench","topic":"Math (competition)","description":"Advanced math olympiad-style benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":72.5,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.5},{"place":2,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66},{"place":3,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":66},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":64},{"place":5,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":62.4},{"place":6,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":62.2},{"place":7,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":61.6},{"place":8,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":60.4},{"place":9,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":60},{"place":10,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":58},{"place":11,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":56},{"place":12,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":51.9},{"place":13,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":50},{"place":14,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50},{"place":15,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.8},{"place":16,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":40},{"place":17,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":38.7},{"place":18,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":36.3},{"place":19,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32},{"place":20,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":26},{"place":21,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":23.3},{"place":22,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":22.2},{"place":23,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.3},{"place":24,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":16},{"place":25,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":15},{"place":26,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":14.1},{"place":27,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":7}]},{"id":"amobench-zh","name":"AMO-Bench CH","topic":"Math (competition)","description":"Chinese subset of AMO-Bench.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":74.9,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.9},{"place":2,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.7},{"place":3,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":67.5},{"place":4,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":58.3},{"place":5,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":57.3},{"place":6,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":56.8},{"place":7,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":52},{"place":8,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":51.8},{"place":9,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":35.1},{"place":10,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":28.8}]},{"id":"android-daily","name":"Android Daily","topic":"GUI agents","description":"Benchmark of long-horizon daily phone-use tasks across multiple Android apps.","url":"https://arxiv.org/abs/2605.27761","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2605.27761","metric":"percent","stars":"","top_model":"Gemini 3 Flash","top_percent":63.21,"top_model_id":"gemini-3-flash","top_generation":"Gemini 3","top_model_base":"Gemini 3 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":63.21},{"place":2,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":61.87},{"place":3,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":53.36},{"place":4,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":51.68}]},{"id":"androidbench","name":"AndroidBench","topic":"Software engineering (Android)","description":"Agentic Android app development benchmark; Qwen reports avg@3 on the 95-task public subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":84.5,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84.5},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.1},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":74},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.8},{"place":5,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":56.5}]},{"id":"androidworld","name":"AndroidWorld","topic":"Mobile agents","description":"Benchmark for agents operating Android apps via UI automation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":88.8,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":70,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.8},{"place":2,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":87.1},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":85.3},{"place":4,"model":"holo4-27b","company":"hcompany","family":"Holo","version":"Holo4","score":85.1},{"place":5,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.5},{"place":6,"model":"ui-venus-2-27b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":84},{"place":7,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.9},{"place":8,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":81},{"place":9,"model":"ui-venus-2-9b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":80.2},{"place":10,"model":"holo3.1-35b-a3b","company":"hcompany","family":"Holo","version":"Holo3.1","score":79.3},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.6},{"place":12,"model":"ui-venus-1.5-30b-a3b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":77.6},{"place":13,"model":"holo4-35b-a3b","company":"hcompany","family":"Holo","version":"Holo4","score":77.6},{"place":14,"model":"mai-gym-9b","company":"tongyi","family":"MAI-Gym","version":"MAI-Gym","score":75.9},{"place":15,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":75.7},{"place":16,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75},{"place":17,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":74.1},{"place":18,"model":"ui-venus-1.5-8b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":73.7},{"place":19,"model":"ui-tars-2","company":"bytedance","family":"UI-TARS","version":"UI-TARS-2","score":73.3},{"place":20,"model":"mai-ui-32b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":73.3},{"place":21,"model":"gui-owl-1.5-8b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl-1.5","score":71.6},{"place":22,"model":"holo2-30b-a3b","company":"hcompany","family":"Holo","version":"Holo2","score":71.6},{"place":23,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.1},{"place":24,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":70.7},{"place":25,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.7},{"place":26,"model":"mai-ui-8b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":70.7},{"place":27,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":70.3},{"place":28,"model":"gui-owl-1.5-32b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl-1.5","score":69.8},{"place":29,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.7},{"place":30,"model":"step-gui-8b","company":"stepfun","family":"Step-GUI","version":"Step-GUI","score":67.7},{"place":31,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.2},{"place":32,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.8},{"place":33,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.4},{"place":34,"model":"gui-owl-7b","company":"alibaba","family":"GUI","version":"GUI","score":66.4},{"place":35,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":65.9},{"place":36,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.2},{"place":37,"model":"ui-tars-1.5","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":64.2},{"place":38,"model":"step-gui-4b","company":"stepfun","family":"Step-GUI","version":"Step-GUI","score":63.9},{"place":39,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.7},{"place":40,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":62.1},{"place":41,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":62},{"place":42,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":60.4},{"place":43,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.6},{"place":44,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.8},{"place":45,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.3},{"place":46,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":57},{"place":47,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":57},{"place":48,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56},{"place":49,"model":"ui-venus-1.5-2b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":55.6},{"place":50,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55},{"place":51,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.3},{"place":52,"model":"llada-ui","company":"antgroup","family":"LLaDA","version":"LLaDA-UI","score":53.5},{"place":53,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":49.1},{"place":54,"model":"mai-ui-2b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":49.1},{"place":55,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.9},{"place":56,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.6},{"place":57,"model":"ui-tars-72b-sft","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":46.6},{"place":58,"model":"ui-tars-72b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":46.6},{"place":59,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.3},{"place":60,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":43.1},{"place":61,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":42.7},{"place":62,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":41.7},{"place":63,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.4},{"place":64,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":35},{"place":65,"model":"ui-tars-7b","company":"bytedance","family":"UI","version":"UI","score":33},{"place":66,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":30.6},{"place":67,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":30.5},{"place":68,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":30},{"place":69,"model":"ferret-ui-lite-3b","company":"apple","family":"Ferret-UI","version":"Ferret-UI Lite","score":28},{"place":70,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":25.5},{"place":71,"model":"scalecua-3b","company":"opengvlab","family":"ScaleCUA","version":"ScaleCUA","score":23.7},{"place":72,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":4.4}]},{"id":"anli","name":"ANLI","topic":"Natural language inference","description":"Adversarial NLI (entailment / neutral / contradiction); macro-F1 (Jev Decision Index suite, posed as typed decisions).","url":"https://huggingface.co/datasets/facebook/anli","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"https://arxiv.org/abs/1910.14599","metric":"f1","stars":"","top_model":"AutoTrust JEV-27B","top_percent":77.2,"top_model_id":"autotrust-jev-27b","top_generation":"JEV-27B","top_model_base":"JEV-27B","top_model_family":"JEV","top_company":"autotrust","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":77.2},{"place":2,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":76},{"place":3,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":75.5},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":74.8},{"place":5,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":74.3},{"place":6,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":73.7},{"place":7,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":73.3},{"place":8,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":70.3},{"place":9,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":70.3},{"place":10,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":70},{"place":11,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":69.8},{"place":12,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":69.6},{"place":13,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":69.3},{"place":14,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":68.2},{"place":15,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":67.9},{"place":16,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":67.6},{"place":17,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":66.4},{"place":18,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":65.5},{"place":19,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":64.6},{"place":20,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":62.4},{"place":21,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59.8},{"place":22,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":59.1},{"place":23,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":58.4},{"place":24,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":56.4},{"place":25,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":56.3},{"place":26,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56},{"place":27,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":49.3},{"place":28,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":48.7},{"place":29,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":46.9},{"place":30,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":44.4},{"place":31,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":40.8},{"place":32,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":39.9},{"place":33,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":37.6},{"place":34,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":36.5},{"place":35,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":36},{"place":36,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":34.1},{"place":37,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":30.9},{"place":38,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":30.5}]},{"id":"apex-agents","name":"APEX-Agents","topic":"Long horizon professional tasks","description":"APEX benchmark evaluating agents on long-horizon professional tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":59.2,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":76,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":59.2},{"place":2,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":57.5},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":56.7},{"place":4,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":47.1},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":43.5},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":43.3},{"place":7,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":42.92},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":42.5},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":42.3},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":41.8},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":41.7},{"place":12,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":41},{"place":13,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":40},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":39.9},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":39.4},{"place":16,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":39.3},{"place":17,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":38.9},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":38.5},{"place":19,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":38.5},{"place":20,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":38.4},{"place":21,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":38.1},{"place":22,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":37.7},{"place":23,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":37.2},{"place":24,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":37.1},{"place":25,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":35.6},{"place":26,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":35.5},{"place":27,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":35.4},{"place":28,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35},{"place":29,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":34.79},{"place":30,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":34.4},{"place":31,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":34.4},{"place":32,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":34},{"place":33,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":33.9},{"place":34,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":33.8},{"place":35,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":33.7},{"place":36,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":33.5},{"place":37,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":33.4},{"place":38,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":33.3},{"place":39,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":33},{"place":40,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":32.4},{"place":41,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":32},{"place":42,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":31.7},{"place":43,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":30.8},{"place":44,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":29.9},{"place":45,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":29.9},{"place":46,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":29.8},{"place":47,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":29.7},{"place":48,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":29.2},{"place":49,"model":"ling-3.0-flash-fin","company":"antgroup","family":"Ling","version":"Ling 3.0","score":29.17},{"place":50,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":28.6},{"place":51,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":27.9},{"place":52,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":27.9},{"place":53,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":27.7},{"place":54,"model":"apodex-1.1-mini","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":27.7},{"place":55,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":27.6},{"place":56,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":26.9},{"place":57,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":26.2},{"place":58,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":25.6},{"place":59,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":25.4},{"place":60,"model":"fx-work","company":"endless-frontier","family":"Fx","version":"Fx","score":25.2},{"place":61,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":24.8},{"place":62,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":24.4},{"place":63,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":24.3},{"place":64,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":24.3},{"place":65,"model":"apodex-1.1-mini","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":24.2},{"place":66,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":24},{"place":67,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":23.8},{"place":68,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":23},{"place":69,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":22.4},{"place":70,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":22.2},{"place":71,"model":"gpt-5.1-codex","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":20.6},{"place":72,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":20.5},{"place":73,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":20.4},{"place":74,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":20},{"place":75,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":19.2},{"place":76,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":19},{"place":77,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":18.7},{"place":78,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":18.4},{"place":79,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":18.4},{"place":80,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":18.3},{"place":81,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":18.3},{"place":82,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":17.5},{"place":83,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":16.6},{"place":84,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":16.6},{"place":85,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":16.5},{"place":86,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":15.6},{"place":87,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":15.2},{"place":88,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":15.2},{"place":89,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":14.6},{"place":90,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":14.4},{"place":91,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":13.4},{"place":92,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":13.4},{"place":93,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":13.2},{"place":94,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":13.2},{"place":95,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":12.4},{"place":96,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":11.7},{"place":97,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":11.5},{"place":98,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":9},{"place":99,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":6.2},{"place":100,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":6.1},{"place":101,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":5.6},{"place":102,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":4.7},{"place":103,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":4},{"place":104,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":3.1},{"place":105,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":3},{"place":106,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":2.4},{"place":107,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":1.6}]},{"id":"apex-agents-v1.1","name":"APEX-Agents 1.1","topic":"Long horizon professional tasks","description":"Mercor APEX-Agents 1.1 revision: 240 long-horizon cross-application professional-services tasks (investment banking, consulting, corporate law) with updated task specs and judge; Pass@1. Not comparable to APEX-Agents v1.0.","url":"https://huggingface.co/datasets/mercor/apex-agents-v1.1","leaderboard":"https://mercor.com/apex/","github":"","paper":"https://arxiv.org/abs/2601.14242","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":82.4,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":54,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":82.4},{"place":2,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":75.5},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":73.5},{"place":4,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":72.1},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":68.6},{"place":6,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":67.8},{"place":7,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":65.8},{"place":8,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":65.3},{"place":9,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":64.7},{"place":10,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":64.6},{"place":11,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":64.3},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.6},{"place":13,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":63.3},{"place":14,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":60},{"place":15,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":58.6},{"place":16,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":58.2},{"place":17,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":57.4},{"place":18,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":56.6},{"place":19,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":56.2},{"place":20,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":56.1},{"place":21,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.3},{"place":22,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":55.1},{"place":23,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":54.6},{"place":24,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.5},{"place":25,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":54.4},{"place":26,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":54.3},{"place":27,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":54.3},{"place":28,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":52.8},{"place":29,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":52.4},{"place":30,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":51.5},{"place":31,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":49.2},{"place":32,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":48.9},{"place":33,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":47.8},{"place":34,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":47.5},{"place":35,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":47.3},{"place":36,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":46.9},{"place":37,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":46.3},{"place":38,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":45.4},{"place":39,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":45.2},{"place":40,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":44.3},{"place":41,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":43},{"place":42,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":43},{"place":43,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":40.9},{"place":44,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":39.5},{"place":45,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":37.7},{"place":46,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":37.6},{"place":47,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":35.1},{"place":48,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":33.8},{"place":49,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":33.4},{"place":50,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":31.8},{"place":51,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":29.3},{"place":52,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":27.5},{"place":53,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.9},{"place":54,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":22.7},{"place":55,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":21.3},{"place":56,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":4.4}]},{"id":"apex-swe","name":"APEX-SWE","topic":"Software engineering","description":"Mercor/Cognition benchmark of integration (shipping end-to-end systems on cloud/business/infra services) and observability (debugging production-style failures from telemetry) tasks; Pass@1.","url":"https://www.mercor.com/blog/introducing-apex-swe/","leaderboard":"https://www.mercor.com/blog/introducing-apex-swe/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":58.8,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":58.8},{"place":2,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":56.4},{"place":3,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":53.6}]},{"id":"api-bank","name":"API-Bank","topic":"Tool use","description":"API-Bank tool-use benchmark.","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/api-bank","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 3.1 405B","top_percent":92,"top_model_id":"llama-3.1-405b","top_generation":"Llama 3.1","top_model_base":"Llama 3.1 405B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":92},{"place":2,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":90},{"place":3,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":85.1},{"place":4,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":82.6},{"place":5,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":48.3}]},{"id":"api-bank-decision","name":"API-Bank (decision)","topic":"Tool use","description":"API-Bank cases answered as option choices; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/api-bank","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef-Flash","top_percent":93.1,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":93.1},{"place":2,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":92.7},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":91.9},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":88.2},{"place":5,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":87.4},{"place":6,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":86.6},{"place":7,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":86.4},{"place":8,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":86.4},{"place":9,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":85.8},{"place":10,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":85.4},{"place":11,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":85},{"place":12,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":84.8},{"place":13,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":84.2},{"place":14,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":83.9},{"place":15,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":83.7},{"place":16,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":82.9},{"place":17,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":80.5},{"place":18,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":79.1},{"place":19,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":78.1},{"place":20,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":77.6},{"place":21,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":76},{"place":22,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":71.3},{"place":23,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":67.9},{"place":24,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":62.4},{"place":25,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56.9},{"place":26,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":56.3},{"place":27,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56.3},{"place":28,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":49.6},{"place":29,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":40.2},{"place":30,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":40},{"place":31,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":39.6},{"place":32,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":38.8},{"place":33,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":28.5},{"place":34,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":21.1},{"place":35,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":11.5},{"place":36,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":7.7}]},{"id":"arabicmmlu","name":"ArabicMMLU","topic":"Arabic knowledge","description":"Native Arabic multi-task knowledge benchmark (school exams across MENA countries), 40 tasks.","url":"https://huggingface.co/datasets/MBZUAI/ArabicMMLU","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Fanar-2-27B-Instruct","top_percent":74.67,"top_model_id":"fanar-2-27b-instruct","top_generation":"Fanar 2.0","top_model_base":"Fanar","top_model_family":"Fanar","top_company":"qcri","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":74.67},{"place":2,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.08},{"place":3,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.44},{"place":4,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":72.21},{"place":5,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.44},{"place":6,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":70.08},{"place":7,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":69.73},{"place":8,"model":"acegpt-v2-32b-chat","company":"freedomintelligence","family":"AceGPT","version":"AceGPT-v2","score":69.55},{"place":9,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":69.24},{"place":10,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":68.85},{"place":11,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":67.35},{"place":12,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.81},{"place":13,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":60.26},{"place":14,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.78},{"place":15,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":54.87},{"place":16,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":54.28},{"place":17,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":53.92}]},{"id":"arc-agi-1","name":"ARC-AGI-1","topic":"General reasoning","description":"ARC-AGI Phase 1 aggregate accuracy.","url":"https://arcprize.org/","leaderboard":"https://arcprize.org/leaderboard","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":98.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":332,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":98.5},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":98.5},{"place":3,"model":"claude-fable-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":98.5},{"place":4,"model":"claude-fable-5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5","score":98.5},{"place":5,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":98.5},{"place":6,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":98.5},{"place":7,"model":"claude-opus-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":98.5},{"place":8,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":98.5},{"place":9,"model":"gpt-6.1-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":98.5},{"place":10,"model":"gpt-6.1-sol-high","company":"openai","family":"GPT","version":"GPT-6.1","score":98.5},{"place":11,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":98.5},{"place":12,"model":"gemini-4-argon-medium","company":"google","family":"Gemini","version":"Gemini 4","score":98.5},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":98},{"place":14,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":97.5},{"place":15,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":97.5},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":97.5},{"place":17,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":97.5},{"place":18,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":97.5},{"place":19,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":97.5},{"place":20,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":97.5},{"place":21,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":97.5},{"place":22,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":97.5},{"place":23,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":97.5},{"place":24,"model":"claude-opus-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":97.5},{"place":25,"model":"claude-opus-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":97.5},{"place":26,"model":"gemini-3.8-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.8","score":97.5},{"place":27,"model":"gpt-5.6-sol-high","company":"openai","family":"GPT","version":"GPT-5.6","score":97},{"place":28,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":96.5},{"place":29,"model":"gpt-5.5-pro-high","company":"openai","family":"GPT","version":"GPT-5.5","score":96.5},{"place":30,"model":"gpt-5.6-sol-max","company":"openai","family":"GPT","version":"GPT-5.6","score":96.5},{"place":31,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":96.5},{"place":32,"model":"claude-fable-5.1-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.1","score":96.5},{"place":33,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":96.5},{"place":34,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":96.5},{"place":35,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":96.5},{"place":36,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":96},{"place":37,"model":"claude-fable-5.1-high","company":"anthropic","family":"Claude","version":"Claude 5.1","score":96},{"place":38,"model":"claude-fable-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":95.5},{"place":39,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":95.5},{"place":40,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":95.5},{"place":41,"model":"gpt-6.1-sol-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":95.5},{"place":42,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95},{"place":43,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":95},{"place":44,"model":"gpt-5.5-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":95},{"place":45,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":94.5},{"place":46,"model":"johan-land-gpt-5.2-refine","company":"johan_land","family":"GPT","version":"GPT-5.2","score":94.5},{"place":47,"model":"gpt-5.4-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":94.5},{"place":48,"model":"gpt-5.5-high","company":"openai","family":"GPT","version":"GPT-5.5","score":94.5},{"place":49,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":94.5},{"place":50,"model":"claude-fable-5.1-medium","company":"anthropic","family":"Claude","version":"Claude 5.1","score":94.5},{"place":51,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":94.5},{"place":52,"model":"claude-opus-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":94},{"place":53,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":94},{"place":54,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":93.7},{"place":55,"model":"gpt-5.4-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":93.67},{"place":56,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":93.5},{"place":57,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":93.5},{"place":58,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":93.5},{"place":59,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":93},{"place":60,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":93},{"place":61,"model":"gpt-5.4-high","company":"openai","family":"GPT","version":"GPT-5.4","score":92.67},{"place":62,"model":"gpt-6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":92.67},{"place":63,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":92.5},{"place":64,"model":"claude-opus-4.8-max","company":"anthropic","family":"Claude","version":"Claude 4.8","score":92.5},{"place":65,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":92.5},{"place":66,"model":"gpt-5.6-sol-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":92.5},{"place":67,"model":"claude-fable-5-medium","company":"anthropic","family":"Claude","version":"Claude 5","score":92.5},{"place":68,"model":"gpt-5.5-medium","company":"openai","family":"GPT","version":"GPT-5.5","score":92.17},{"place":69,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":92},{"place":70,"model":"claude-opus-4.6-medium","company":"anthropic","family":"Claude","version":"Claude 4.6","score":92},{"place":71,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":92},{"place":72,"model":"claude-opus-4.7-max","company":"anthropic","family":"Claude","version":"Claude 4.7","score":92},{"place":73,"model":"gpt-5.6-terra-high","company":"openai","family":"GPT","version":"GPT-5.6","score":92},{"place":74,"model":"claude-opus-4.8-medium","company":"anthropic","family":"Claude","version":"Claude 4.8","score":91.5},{"place":75,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":91.17},{"place":76,"model":"gemini-3.7-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.7","score":91.17},{"place":77,"model":"claude-opus-4.7-low","company":"anthropic","family":"Claude","version":"Claude 4.7","score":91},{"place":78,"model":"claude-opus-4.7-medium","company":"anthropic","family":"Claude","version":"Claude 4.7","score":91},{"place":79,"model":"gpt-6-sol-high","company":"openai","family":"GPT","version":"GPT-6","score":91},{"place":80,"model":"glm-5.3-flash-max","company":"zai","family":"GLM","version":"GLM 5.3","score":91},{"place":81,"model":"gpt-5.6-luna-0730-max","company":"openai","family":"GPT","version":"GPT-5.6","score":90.67},{"place":82,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":90.5},{"place":83,"model":"gpt-5.2-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":90.5},{"place":84,"model":"claude-fable-5-low","company":"anthropic","family":"Claude","version":"Claude 5","score":90.5},{"place":85,"model":"deepseek-v4-pro-0813-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.5},{"place":86,"model":"gemini-3.8-flash-low","company":"google","family":"Gemini","version":"Gemini 3.8","score":90.5},{"place":87,"model":"deepseek-v4.1-flash-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":90.5},{"place":88,"model":"grok-4.7-high","company":"xai","family":"Grok","version":"Grok 4.7","score":90.17},{"place":89,"model":"deepseek-v4-pro-0813-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90},{"place":90,"model":"claude-fable-5.1-low","company":"anthropic","family":"Claude","version":"Claude 5.1","score":90},{"place":91,"model":"grok-4.7-medium","company":"xai","family":"Grok","version":"Grok 4.7","score":90},{"place":92,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":89.9},{"place":93,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":89.5},{"place":94,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":89.5},{"place":95,"model":"deepseek-v4-flash-0731-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89},{"place":96,"model":"claude-haiku-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":89},{"place":97,"model":"claude-opus-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":88.5},{"place":98,"model":"deepseek-v4.1-flash-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":88.5},{"place":99,"model":"claude-opus-4.8-low","company":"anthropic","family":"Claude","version":"Claude 4.8","score":88},{"place":100,"model":"gpt-5.6-luna-max","company":"openai","family":"GPT","version":"GPT-5.6","score":88},{"place":101,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":87.7},{"place":102,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":87.67},{"place":103,"model":"gemini-3-deep-think-preview","company":"google","family":"Gemini","version":"Gemini 3","score":87.5},{"place":104,"model":"grok-4.6-medium","company":"xai","family":"Grok","version":"Grok 4.6","score":87.5},{"place":105,"model":"qwen3.8-27b-xhigh","company":"qwen","family":"Qwen","version":"Qwen3.8","score":87.5},{"place":106,"model":"claude-haiku-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":87.5},{"place":107,"model":"grok-4.5-medium","company":"xai","family":"Grok","version":"Grok 4.5","score":87.17},{"place":108,"model":"deepseek-v4-pro-0813-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.17},{"place":109,"model":"deepseek-v4-flash-0731-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87},{"place":110,"model":"grok-4.6-xhigh","company":"xai","family":"Grok","version":"Grok 4.6","score":87},{"place":111,"model":"grok-4.6-high","company":"xai","family":"Grok","version":"Grok 4.6","score":87},{"place":112,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":86.9},{"place":113,"model":"kimi-k3-high","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":86.67},{"place":114,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":86.67},{"place":115,"model":"claude-sonnet-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86.5},{"place":116,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":86.2},{"place":117,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.2},{"place":118,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":86.17},{"place":119,"model":"gpt-5.4-medium","company":"openai","family":"GPT","version":"GPT-5.4","score":86.17},{"place":120,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":86.17},{"place":121,"model":"claude-opus-4.6-low","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86},{"place":122,"model":"claude-sonnet-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86},{"place":123,"model":"gpt-6-astra-none","company":"openai","family":"GPT","version":"GPT-6","score":86},{"place":124,"model":"gpt-5.2-pro-high","company":"openai","family":"GPT","version":"GPT-5.2","score":85.67},{"place":125,"model":"grok-4.5-high","company":"xai","family":"Grok","version":"Grok 4.5","score":85.67},{"place":126,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":85.4},{"place":127,"model":"gemini-3.7-flash-low","company":"google","family":"Gemini","version":"Gemini 3.7","score":85.17},{"place":128,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85},{"place":129,"model":"gpt-5.6-luna-0730-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":85},{"place":130,"model":"gemini-3-flash-high","company":"google","family":"Gemini","version":"Gemini 3","score":84.67},{"place":131,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84},{"place":132,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":84},{"place":133,"model":"inkling-small-xhigh","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":84},{"place":134,"model":"deepseek-v4-flash-0731-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84},{"place":135,"model":"gpt-6-sol-medium","company":"openai","family":"GPT","version":"GPT-6","score":83.67},{"place":136,"model":"gemini-3.6-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.6","score":83.17},{"place":137,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":81.5},{"place":138,"model":"gpt-5.2-pro-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":81.17},{"place":139,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80},{"place":140,"model":"claude-opus-4.5-thinking-64k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80},{"place":141,"model":"berman-grok-4-refine","company":"j_berman","family":"Grok","version":"Grok 4","score":79.6},{"place":142,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":79.5},{"place":143,"model":"grok-4.5-low","company":"xai","family":"Grok","version":"Grok 4.5","score":79.17},{"place":144,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":78.67},{"place":145,"model":"inkling-small-high","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":78},{"place":146,"model":"gpt-5.6-luna-0730-high","company":"openai","family":"GPT","version":"GPT-5.6","score":78},{"place":147,"model":"gpt-5.6-terra-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":77},{"place":148,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":77},{"place":149,"model":"gpt-5.6-luna-high","company":"openai","family":"GPT","version":"GPT-5.6","score":76.5},{"place":150,"model":"gemini-3.6-flash-low","company":"google","family":"Gemini","version":"Gemini 3.6","score":76.5},{"place":151,"model":"gemini-4-argon-low","company":"google","family":"Gemini","version":"Gemini 4","score":76.5},{"place":152,"model":"gpt-5.5-low","company":"openai","family":"GPT","version":"GPT-5.5","score":76.17},{"place":153,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":75.83},{"place":154,"model":"o3","company":"openai","family":"o3","version":"o3","score":75.7},{"place":155,"model":"o3-preview-low","company":"openai","family":"o3","version":"o3","score":75.7},{"place":156,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":75.7},{"place":157,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":75},{"place":158,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":75},{"place":159,"model":"grok-4.6-low","company":"xai","family":"Grok","version":"Grok 4.6","score":74.83},{"place":160,"model":"gpt-5.6-sol-low","company":"openai","family":"GPT","version":"GPT-5.6","score":74.5},{"place":161,"model":"gpt-6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":73},{"place":162,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":72.83},{"place":163,"model":"gpt-5.1-thinking","company":"openai","family":"GPT","version":"GPT-5.1","score":72.8},{"place":164,"model":"gpt-5.2-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":72.67},{"place":165,"model":"gpt-6-sol-low","company":"openai","family":"GPT","version":"GPT-6","score":72.17},{"place":166,"model":"claude-opus-4.5-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72},{"place":167,"model":"glm-5.3-flash-high","company":"zai","family":"GLM","version":"GLM 5.3","score":71.83},{"place":168,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.9},{"place":169,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":70.33},{"place":170,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":70.2},{"place":171,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":70.17},{"place":172,"model":"qwen3.8-27b-low","company":"qwen","family":"Qwen","version":"Qwen3.8","score":69.17},{"place":173,"model":"qwen3.8-27b-medium","company":"qwen","family":"Qwen","version":"Qwen3.8","score":68.67},{"place":174,"model":"gpt-5.4-low","company":"openai","family":"GPT","version":"GPT-5.4","score":68.17},{"place":175,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":67.9},{"place":176,"model":"inkling-small-medium","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":67},{"place":177,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":66.7},{"place":178,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":66.7},{"place":179,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":66.67},{"place":180,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":181,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":182,"model":"gpt-5-thinking-high","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":183,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":65.67},{"place":184,"model":"kimi-k3-low","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":65.67},{"place":185,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":65.33},{"place":186,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":65.33},{"place":187,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.7},{"place":188,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.7},{"place":189,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.67},{"place":190,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":63.67},{"place":191,"model":"gpt-5.4-mini-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":63.67},{"place":192,"model":"grok-4.7-low","company":"xai","family":"Grok","version":"Grok 4.7","score":63.33},{"place":193,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":61},{"place":194,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":60.83},{"place":195,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":60.8},{"place":196,"model":"gpt-5.6-terra-low","company":"openai","family":"GPT","version":"GPT-5.6","score":60.17},{"place":197,"model":"o3-pro-high","company":"openai","family":"o3","version":"o3","score":59.33},{"place":198,"model":"o3-pro","company":"openai","family":"o3","version":"o3","score":59.3},{"place":199,"model":"o3-pro-high","company":"openai","family":"o3","version":"o3","score":59.3},{"place":200,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":58.7},{"place":201,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":58.7},{"place":202,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":58.67},{"place":203,"model":"claude-opus-4.5-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.67},{"place":204,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":58},{"place":205,"model":"gpt-5.1-medium","company":"openai","family":"GPT","version":"GPT-5.1","score":57.67},{"place":206,"model":"gemini-3-flash-medium","company":"google","family":"Gemini","version":"Gemini 3","score":57.67},{"place":207,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":57.33},{"place":208,"model":"o3-pro-medium","company":"openai","family":"o3","version":"o3","score":57},{"place":209,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":57},{"place":210,"model":"gpt-5.6-luna-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":56.5},{"place":211,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":56.2},{"place":212,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":56.17},{"place":213,"model":"architects","company":"arcprize","family":"ARChitects","version":"ARChitects","score":56},{"place":214,"model":"ring-1t","company":"antgroup","family":"Ring","version":"Ring","score":55.94},{"place":215,"model":"gpt-5.2-low","company":"openai","family":"GPT","version":"GPT-5.2","score":55.67},{"place":216,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":54.5},{"place":217,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":54.33},{"place":218,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":54.3},{"place":219,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":54.3},{"place":220,"model":"gpt-5.6-luna-0730-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":54},{"place":221,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":53.83},{"place":222,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":53.8},{"place":223,"model":"gemini-3.5-flash-lite-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":53.5},{"place":224,"model":"inkling-small-low","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":52.5},{"place":225,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":51.88},{"place":226,"model":"gpt-5.4-nano-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":51.5},{"place":227,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":50.8},{"place":228,"model":"claude-haiku-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":50.33},{"place":229,"model":"gemini-3.5-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3.5","score":48.83},{"place":230,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":48.5},{"place":231,"model":"inkling-small-minimal","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":48.5},{"place":232,"model":"claude-4.5-sonnet-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":48.33},{"place":233,"model":"claude-4.5-sonnet-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":48.3},{"place":234,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.12},{"place":235,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.7},{"place":236,"model":"claude-4.5-haiku-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.67},{"place":237,"model":"glm-5.3-flash-low","company":"zai","family":"GLM","version":"GLM 5.3","score":47},{"place":238,"model":"claude-4.5-sonnet-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":46.5},{"place":239,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":45.44},{"place":240,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":44.67},{"place":241,"model":"o3-pro-low","company":"openai","family":"o3","version":"o3","score":44.33},{"place":242,"model":"o3-pro-low","company":"openai","family":"o3","version":"o3","score":44.3},{"place":243,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":44.25},{"place":244,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":44},{"place":245,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":43.81},{"place":246,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":43.3},{"place":247,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":41.83},{"place":248,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":41.8},{"place":249,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":41.5},{"place":250,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":41},{"place":251,"model":"gemini-2.5-pro-thinking-16k","company":"google","family":"Gemini","version":"Gemini 2.5","score":41},{"place":252,"model":"gpt-5.4-mini-medium","company":"openai","family":"GPT","version":"GPT-5.4","score":40.83},{"place":253,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":40.62},{"place":254,"model":"claude-sonnet-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":40},{"place":255,"model":"trm","company":"samsung","family":"TRM","version":"TRM","score":40},{"place":256,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":40},{"place":257,"model":"claude-sonnet-4-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":40},{"place":258,"model":"gpt-5.6-luna-0730-low","company":"openai","family":"GPT","version":"GPT-5.6","score":39.5},{"place":259,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":38.17},{"place":260,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":37.67},{"place":261,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":37.33},{"place":262,"model":"claude-4.5-haiku-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":37.33},{"place":263,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":37.3},{"place":264,"model":"gemini-2.5-pro-thinking-32k","company":"google","family":"Gemini","version":"Gemini 2.5","score":37},{"place":265,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":37},{"place":266,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":35.7},{"place":267,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":35.67},{"place":268,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":34.5},{"place":269,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":34.5},{"place":270,"model":"gemini-3.6-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3.6","score":34.5},{"place":271,"model":"gpt-5.6-luna-low","company":"openai","family":"GPT","version":"GPT-5.6","score":34.17},{"place":272,"model":"qwen3.8-27b-none","company":"qwen","family":"Qwen","version":"Qwen3.8","score":34},{"place":273,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.33},{"place":274,"model":"gemini-2.5-flash-preview-thinking-16k","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.33},{"place":275,"model":"gemini-2.5-flash-preview-thinking-16k","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.3},{"place":276,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.3},{"place":277,"model":"gpt-5.1-low","company":"openai","family":"GPT","version":"GPT-5.1","score":33.17},{"place":278,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":33.06},{"place":279,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":33},{"place":280,"model":"gpt-5.4-nano-medium","company":"openai","family":"GPT","version":"GPT-5.4","score":33},{"place":281,"model":"gemini-2.5-flash-preview-thinking-24k","company":"google","family":"Gemini","version":"Gemini 2.5","score":32.33},{"place":282,"model":"gemini-3.5-flash-lite-medium","company":"google","family":"Gemini","version":"Gemini 3.5","score":32.33},{"place":283,"model":"gemini-2.5-flash-preview-thinking-24k","company":"google","family":"Gemini","version":"Gemini 2.5","score":32.3},{"place":284,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":32},{"place":285,"model":"gemini-2.5-pro-preview-thinking-1k","company":"google","family":"Gemini","version":"Gemini 2.5","score":31.3},{"place":286,"model":"claude-4.5-sonnet-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":31},{"place":287,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":30.88},{"place":288,"model":"claude-opus-4-20250514-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":30.7},{"place":289,"model":"claude-opus-4-20250514-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":30.67},{"place":290,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":30.44},{"place":291,"model":"gemini-2.5-pro-thinking-8k","company":"google","family":"Gemini","version":"Gemini 2.5","score":29.5},{"place":292,"model":"gpt-6-sol-none","company":"openai","family":"GPT","version":"GPT-6","score":29.33},{"place":293,"model":"claude-sonnet-4-20250514-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":29},{"place":294,"model":"gemini-3-flash-low","company":"google","family":"Gemini","version":"Gemini 3","score":29},{"place":295,"model":"claude-sonnet-4-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":29},{"place":296,"model":"claude-3.7-sonnet-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":28.6},{"place":297,"model":"ring-flash-linear-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":28.31},{"place":298,"model":"claude-sonnet-4-20250514-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4","score":28},{"place":299,"model":"claude-sonnet-4-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4","score":28},{"place":300,"model":"codex-mini-latest","company":"openai","family":"Codex","version":"Codex","score":27.33},{"place":301,"model":"codex-mini-latest","company":"openai","family":"Codex","version":"Codex","score":27.3},{"place":302,"model":"claude-opus-4-20250514-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4","score":27},{"place":303,"model":"gpt-5-mini-low","company":"openai","family":"GPT","version":"GPT-5","score":26.33},{"place":304,"model":"gpt-5-mini-low","company":"openai","family":"GPT","version":"GPT-5","score":26.3},{"place":305,"model":"gemini-2.5-flash-preview-thinking-8k","company":"google","family":"Gemini","version":"Gemini 2.5","score":25.83},{"place":306,"model":"gemini-2.5-flash-preview-thinking-8k","company":"google","family":"Gemini","version":"Gemini 2.5","score":25.8},{"place":307,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":25.5},{"place":308,"model":"claude-4.5-haiku-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":25.5},{"place":309,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":23.83},{"place":310,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":23.8},{"place":311,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":22.5},{"place":312,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":22.5},{"place":313,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":22.33},{"place":314,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":22.3},{"place":315,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":22.19},{"place":316,"model":"gemini-3-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3","score":21.5},{"place":317,"model":"o4-mini-low","company":"openai","family":"o4","version":"o4","score":21.33},{"place":318,"model":"o4-mini-low","company":"openai","family":"o4","version":"o4","score":21.3},{"place":319,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":21.21},{"place":320,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":21.2},{"place":321,"model":"claude-3.7-sonnet-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":21.2},{"place":322,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":20.71},{"place":323,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":20.7},{"place":324,"model":"ring-mini-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":20.12},{"place":325,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":18.94},{"place":326,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":18.62},{"place":327,"model":"gpt-5.4-nano-low","company":"openai","family":"GPT","version":"GPT-5.4","score":18.33},{"place":328,"model":"icecuber","company":"arcprize","family":"ARChitects","version":"ARChitects","score":17},{"place":329,"model":"gemini-3.5-flash-lite-low","company":"google","family":"Gemini","version":"Gemini 3.5","score":17},{"place":330,"model":"claude-4.5-haiku-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":16.83},{"place":331,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":16.7},{"place":332,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":16.67},{"place":333,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":16.5},{"place":334,"model":"grok-3-mini-beta-low","company":"xai","family":"Grok","version":"Grok 3","score":16.5},{"place":335,"model":"gemini-2.5-flash-preview-thinking-1k","company":"google","family":"Gemini","version":"Gemini 2.5","score":16},{"place":336,"model":"gemini-2.5-pro-thinking-1k","company":"google","family":"Gemini","version":"Gemini 2.5","score":16},{"place":337,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":15.8},{"place":338,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":14.69},{"place":339,"model":"o3-mini-low","company":"openai","family":"o3","version":"o3","score":14.5},{"place":340,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":14.33},{"place":341,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":14.06},{"place":342,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":14},{"place":343,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":13.6},{"place":344,"model":"gpt-5.4-mini-low","company":"openai","family":"GPT","version":"GPT-5.4","score":13},{"place":345,"model":"deepseek-v4-pro-0813-none","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":13},{"place":346,"model":"gpt-5.2-none","company":"openai","family":"GPT","version":"GPT-5.2","score":12.33},{"place":347,"model":"deepseek-v4-flash-0731-none","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":11.83},{"place":348,"model":"claude-3.7-sonnet-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":11.6},{"place":349,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":11},{"place":350,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":10.3},{"place":351,"model":"gpt-6-luna-none","company":"openai","family":"GPT","version":"GPT-6","score":8.83},{"place":352,"model":"qwen3-32b-thinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":8.75},{"place":353,"model":"deepseek-v4.1-flash-none","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":7.83},{"place":354,"model":"gemini-3.5-flash-lite-minimal","company":"google","family":"Gemini","version":"Gemini 3.5","score":7.5},{"place":355,"model":"magistral-medium-thinking","company":"mistral","family":"Magistral","version":"Magistral","score":6.12},{"place":356,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":6},{"place":357,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":5.91},{"place":358,"model":"magistral-medium","company":"magistral","family":"Magistral","version":"Magistral","score":5.91},{"place":359,"model":"gpt-5.1-none","company":"openai","family":"GPT","version":"GPT-5.1","score":5.83},{"place":360,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":5.5},{"place":361,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":5.5},{"place":362,"model":"inkling-small-none","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":5.5},{"place":363,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":5.33},{"place":364,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":5.3},{"place":365,"model":"magistral-small-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":5},{"place":366,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":4.5},{"place":367,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":4.5},{"place":368,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":4.38},{"place":369,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":4.38},{"place":370,"model":"gpt-5-nano-low","company":"openai","family":"GPT","version":"GPT-5","score":4.04},{"place":371,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":3.5},{"place":372,"model":"gpt-5.6-luna-0730-none","company":"openai","family":"GPT","version":"GPT-5.6","score":3.33},{"place":373,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":1.5},{"place":374,"model":"llama-4-scout","company":"meta","family":"Llama","version":"Llama 1","score":0.5},{"place":375,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":0}]},{"id":"arc-agi-2","name":"ARC-AGI-2","topic":"General reasoning","description":"ARC-AGI Phase 2 aggregate accuracy.","url":"https://arcprize.org/","leaderboard":"https://arcprize.org/leaderboard","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":95,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":345,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":95},{"place":2,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":95},{"place":3,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":94.17},{"place":4,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":93.33},{"place":5,"model":"claude-opus-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.33},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":92.5},{"place":7,"model":"gpt-5.6-sol-max","company":"openai","family":"GPT","version":"GPT-5.6","score":92.5},{"place":8,"model":"claude-opus-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":92.5},{"place":9,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":92.08},{"place":10,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":92.08},{"place":11,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":91.67},{"place":12,"model":"gpt-6.1-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":91.67},{"place":13,"model":"gpt-6.1-sol-high","company":"openai","family":"GPT","version":"GPT-6.1","score":91.67},{"place":14,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":91.25},{"place":15,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.42},{"place":16,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":90.42},{"place":17,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.4},{"place":18,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":90},{"place":19,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":90},{"place":20,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":90},{"place":21,"model":"claude-fable-5.1-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.1","score":90},{"place":22,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":89.58},{"place":23,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89.2},{"place":24,"model":"claude-fable-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":89.17},{"place":25,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":89.17},{"place":26,"model":"claude-fable-5.1-high","company":"anthropic","family":"Claude","version":"Claude 5.1","score":88.75},{"place":27,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":88.33},{"place":28,"model":"claude-fable-5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5","score":88.33},{"place":29,"model":"claude-fable-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":87.5},{"place":30,"model":"claude-opus-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":87.5},{"place":31,"model":"gemini-4-argon-medium","company":"google","family":"Gemini","version":"Gemini 4","score":87.08},{"place":32,"model":"gpt-6.1-sol-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":86.67},{"place":33,"model":"claude-fable-5.1-medium","company":"anthropic","family":"Claude","version":"Claude 5.1","score":86.25},{"place":34,"model":"gpt-5.6-sol-high","company":"openai","family":"GPT","version":"GPT-5.6","score":85.42},{"place":35,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":85.42},{"place":36,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":85},{"place":37,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":85},{"place":38,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":84.6},{"place":39,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":84.58},{"place":40,"model":"gpt-5.5-pro-high","company":"openai","family":"GPT","version":"GPT-5.5","score":84.58},{"place":41,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":84.58},{"place":42,"model":"gpt-5.5-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":84.16},{"place":43,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":83.9},{"place":44,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":83.89},{"place":45,"model":"gpt-5.4-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":83.33},{"place":46,"model":"gpt-5.5-high","company":"openai","family":"GPT","version":"GPT-5.5","score":83.33},{"place":47,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":83.3},{"place":48,"model":"gemini-3.8-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.8","score":82.92},{"place":49,"model":"claude-fable-5-medium","company":"anthropic","family":"Claude","version":"Claude 5","score":82.5},{"place":50,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":81.4},{"place":51,"model":"claude-fable-5.1-low","company":"anthropic","family":"Claude","version":"Claude 5.1","score":78.33},{"place":52,"model":"gpt-6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":78.06},{"place":53,"model":"gemini-3.8-flash-low","company":"google","family":"Gemini","version":"Gemini 3.8","score":77.5},{"place":54,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":77.1},{"place":55,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":77.08},{"place":56,"model":"claude-fable-5-low","company":"anthropic","family":"Claude","version":"Claude 5","score":76.81},{"place":57,"model":"dots3-note-preview-max","company":"rednote","family":"dots","version":"dots3","score":76.81},{"place":58,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":76.67},{"place":59,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.5},{"place":60,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":76.1},{"place":61,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":75.83},{"place":62,"model":"claude-opus-4.7-max","company":"anthropic","family":"Claude","version":"Claude 4.7","score":75.83},{"place":63,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":75.8},{"place":64,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":74.17},{"place":65,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":74},{"place":66,"model":"gpt-5.4-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":73.95},{"place":67,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":73.3},{"place":68,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":72.92},{"place":69,"model":"johan-land-gpt-5.2-refine","company":"johan_land","family":"GPT","version":"GPT-5.2","score":72.9},{"place":70,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":72.1},{"place":71,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":72.1},{"place":72,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":72.08},{"place":73,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":72.08},{"place":74,"model":"claude-opus-4.8-medium","company":"anthropic","family":"Claude","version":"Claude 4.8","score":71.67},{"place":75,"model":"gpt-5.5-medium","company":"openai","family":"GPT","version":"GPT-5.5","score":70.42},{"place":76,"model":"claude-opus-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":70.14},{"place":77,"model":"claude-opus-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":69.17},{"place":78,"model":"gpt-6-sol-high","company":"openai","family":"GPT","version":"GPT-6","score":68.89},{"place":79,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":68.8},{"place":80,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":68.8},{"place":81,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":68.75},{"place":82,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":68.33},{"place":83,"model":"gpt-5.4-high","company":"openai","family":"GPT","version":"GPT-5.4","score":67.5},{"place":84,"model":"claude-opus-4.7-medium","company":"anthropic","family":"Claude","version":"Claude 4.7","score":67.5},{"place":85,"model":"deepseek-v4.1-flash-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":67.5},{"place":86,"model":"gpt-5.6-sol-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":67.08},{"place":87,"model":"gpt-5.6-terra-high","company":"openai","family":"GPT","version":"GPT-5.6","score":67.08},{"place":88,"model":"grok-4.6-xhigh","company":"xai","family":"Grok","version":"Grok 4.6","score":67.08},{"place":89,"model":"claude-opus-4.6-medium","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66.25},{"place":90,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":66.18},{"place":91,"model":"glm-5.3-flash-max","company":"zai","family":"GLM","version":"GLM 5.3","score":65.83},{"place":92,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":65.14},{"place":93,"model":"grok-4.6-high","company":"xai","family":"Grok","version":"Grok 4.6","score":65.14},{"place":94,"model":"claude-opus-4.6-low","company":"anthropic","family":"Claude","version":"Claude 4.6","score":64.58},{"place":95,"model":"gemini-3.7-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.7","score":63.75},{"place":96,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":63.3},{"place":97,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":62.5},{"place":98,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.43},{"place":99,"model":"claude-opus-4.8-low","company":"anthropic","family":"Claude","version":"Claude 4.8","score":62.22},{"place":100,"model":"claude-opus-4.7-low","company":"anthropic","family":"Claude","version":"Claude 4.7","score":62.08},{"place":101,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.4},{"place":102,"model":"deepseek-v4-flash-0731-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.39},{"place":103,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":61.39},{"place":104,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":61.3},{"place":105,"model":"grok-4.6-medium","company":"xai","family":"Grok","version":"Grok 4.6","score":61.25},{"place":106,"model":"deepseek-v4-pro-0813-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.25},{"place":107,"model":"claude-haiku-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":61.25},{"place":108,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":60.6},{"place":109,"model":"deepseek-v4.1-flash-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":60.56},{"place":110,"model":"claude-sonnet-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":60.42},{"place":111,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":60.42},{"place":112,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":60.42},{"place":113,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":60.4},{"place":114,"model":"deepseek-v4-pro-0813-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.72},{"place":115,"model":"gpt-5.6-luna-0730-max","company":"openai","family":"GPT","version":"GPT-5.6","score":59.58},{"place":116,"model":"gpt-6-astra-none","company":"openai","family":"GPT","version":"GPT-6","score":59.58},{"place":117,"model":"gpt-5.6-luna-max","company":"openai","family":"GPT","version":"GPT-5.6","score":59.54},{"place":118,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":59.31},{"place":119,"model":"grok-4.7-medium","company":"xai","family":"Grok","version":"Grok 4.7","score":58.75},{"place":120,"model":"claude-sonnet-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":58.33},{"place":121,"model":"grok-4.7-high","company":"xai","family":"Grok","version":"Grok 4.7","score":58.33},{"place":122,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":58.3},{"place":123,"model":"gpt-6-sol-medium","company":"openai","family":"GPT","version":"GPT-6","score":57.78},{"place":124,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":57.5},{"place":125,"model":"deepseek-v4-pro-0813-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.25},{"place":126,"model":"deepseek-v4-flash-0731-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.97},{"place":127,"model":"gpt-5.4-medium","company":"openai","family":"GPT","version":"GPT-5.4","score":55.42},{"place":128,"model":"kimi-k3-high","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":55},{"place":129,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.2},{"place":130,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.2},{"place":131,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":54.2},{"place":132,"model":"gpt-5.2-pro-high","company":"openai","family":"GPT","version":"GPT-5.2","score":54.16},{"place":133,"model":"poetiq-gemini-3-pro-refine","company":"poetiq","family":"Gemini","version":"Gemini 3","score":54},{"place":134,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":53.3},{"place":135,"model":"gemini-3.7-flash-low","company":"google","family":"Gemini","version":"Gemini 3.7","score":52.92},{"place":136,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":52.91},{"place":137,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":52.9},{"place":138,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":52.9},{"place":139,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":52.9},{"place":140,"model":"grok-4.5-high","company":"xai","family":"Grok","version":"Grok 4.5","score":52.64},{"place":141,"model":"grok-4.5-medium","company":"xai","family":"Grok","version":"Grok 4.5","score":52.64},{"place":142,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":50.94},{"place":143,"model":"gemini-3.6-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.6","score":50.42},{"place":144,"model":"glm-5.3-flash-high","company":"zai","family":"GLM","version":"GLM 5.3","score":50.14},{"place":145,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":47.64},{"place":146,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":47.6},{"place":147,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":47.25},{"place":148,"model":"deepseek-v4-flash-0731-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":45.97},{"place":149,"model":"gemini-3-deep-think-preview","company":"google","family":"Gemini","version":"Gemini 3","score":45.14},{"place":150,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.1},{"place":151,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.1},{"place":152,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":45.1},{"place":153,"model":"gpt-5.6-luna-0730-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":43.47},{"place":154,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":43.33},{"place":155,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":43.3},{"place":156,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":43.19},{"place":157,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":42.5},{"place":158,"model":"gpt-5.6-sol-low","company":"openai","family":"GPT","version":"GPT-5.6","score":42.5},{"place":159,"model":"qwen3.8-27b-xhigh","company":"qwen","family":"Qwen","version":"Qwen3.8","score":42.36},{"place":160,"model":"gemini-4-argon-low","company":"google","family":"Gemini","version":"Gemini 4","score":42.08},{"place":161,"model":"gpt-6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":41.94},{"place":162,"model":"inkling-small-xhigh","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":40.14},{"place":163,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":40.1},{"place":164,"model":"gpt-5.2-pro-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":38.47},{"place":165,"model":"claude-opus-4.5-thinking-64k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":37.64},{"place":166,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":37.6},{"place":167,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":37.6},{"place":168,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":37.5},{"place":169,"model":"gpt-5.6-terra-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":37.5},{"place":170,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37},{"place":171,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":36.53},{"place":172,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":36.5},{"place":173,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":35.8},{"place":174,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":34.3},{"place":175,"model":"gemini-3-flash-high","company":"google","family":"Gemini","version":"Gemini 3","score":33.61},{"place":176,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":33.6},{"place":177,"model":"gpt-5.5-low","company":"openai","family":"GPT","version":"GPT-5.5","score":33.33},{"place":178,"model":"gpt-5.6-luna-0730-high","company":"openai","family":"GPT","version":"GPT-5.6","score":33.33},{"place":179,"model":"grok-4.5-low","company":"xai","family":"Grok","version":"Grok 4.5","score":33.06},{"place":180,"model":"inkling-small-high","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":33.06},{"place":181,"model":"gpt-6-sol-low","company":"openai","family":"GPT","version":"GPT-6","score":31.53},{"place":182,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":31.39},{"place":183,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":31.19},{"place":184,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":31.11},{"place":185,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":31.1},{"place":186,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":30.69},{"place":187,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":30.6},{"place":188,"model":"gemini-3.6-flash-low","company":"google","family":"Gemini","version":"Gemini 3.6","score":30.42},{"place":189,"model":"berman-grok-4-refine","company":"j_berman","family":"Grok","version":"Grok 4","score":29.44},{"place":190,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":29.38},{"place":191,"model":"gpt-5.6-luna-high","company":"openai","family":"GPT","version":"GPT-5.6","score":29.31},{"place":192,"model":"gpt-5.4-low","company":"openai","family":"GPT","version":"GPT-5.4","score":29.17},{"place":193,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":29.1},{"place":194,"model":"glm-5.3-flash-low","company":"zai","family":"GLM","version":"GLM 5.3","score":27.92},{"place":195,"model":"nvarc","company":"nvidia","family":"NVARC","version":"NVARC","score":27.64},{"place":196,"model":"grok-4.6-low","company":"xai","family":"Grok","version":"Grok 4.6","score":27.64},{"place":197,"model":"gpt-5.2-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":26.67},{"place":198,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":26},{"place":199,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":24.19},{"place":200,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":22.8},{"place":201,"model":"claude-opus-4.5-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":22.78},{"place":202,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":22.78},{"place":203,"model":"qwen3.8-27b-low","company":"qwen","family":"Qwen","version":"Qwen3.8","score":22.78},{"place":204,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":21.74},{"place":205,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":20.06},{"place":206,"model":"ring-1t-2.5","company":"antgroup","family":"Ring","version":"Ring 2.5","score":19.31},{"place":207,"model":"gpt-5.4-mini-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":18.9},{"place":208,"model":"gpt-5.6-terra-low","company":"openai","family":"GPT","version":"GPT-5.6","score":18.75},{"place":209,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":18.33},{"place":210,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":18.3},{"place":211,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":18.06},{"place":212,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":17.64},{"place":213,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":17.6},{"place":214,"model":"gpt-5.1-thinking","company":"openai","family":"GPT","version":"GPT-5.1","score":17.6},{"place":215,"model":"grok-4.7-low","company":"xai","family":"Grok","version":"Grok 4.7","score":16.67},{"place":216,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":16.25},{"place":217,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":16},{"place":218,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":16},{"place":219,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":15.97},{"place":220,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":14.8},{"place":221,"model":"claude-opus-4.5-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.89},{"place":222,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.61},{"place":223,"model":"inkling-small-medium","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":13.61},{"place":224,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.6},{"place":225,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.6},{"place":226,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.6},{"place":227,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.6},{"place":228,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":13.19},{"place":229,"model":"qwen3.8-27b-medium","company":"qwen","family":"Qwen","version":"Qwen3.8","score":13.19},{"place":230,"model":"gemini-3-flash-medium","company":"google","family":"Gemini","version":"Gemini 3","score":12.78},{"place":231,"model":"kimi-k3-low","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":12.36},{"place":232,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":12.31},{"place":233,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":11.81},{"place":234,"model":"gemini-3.5-flash-lite-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":10.28},{"place":235,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":9.9},{"place":236,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":9.86},{"place":237,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":9.8},{"place":238,"model":"gpt-5.2-low","company":"openai","family":"GPT","version":"GPT-5.2","score":9.72},{"place":239,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":9.44},{"place":240,"model":"gemini-3.5-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3.5","score":8.89},{"place":241,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":8.61},{"place":242,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":8.6},{"place":243,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":7.78},{"place":244,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":7.5},{"place":245,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":7.49},{"place":246,"model":"gpt-5.6-luna-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":7.36},{"place":247,"model":"gpt-5.6-luna-0730-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":7.36},{"place":248,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":7.22},{"place":249,"model":"claude-4.5-sonnet-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":6.94},{"place":250,"model":"claude-4.5-sonnet-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":6.94},{"place":251,"model":"claude-4.5-sonnet-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":6.9},{"place":252,"model":"claude-4.5-sonnet-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":6.9},{"place":253,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":6.7},{"place":254,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":6.53},{"place":255,"model":"gpt-5.1-medium","company":"openai","family":"GPT","version":"GPT-5.1","score":6.53},{"place":256,"model":"o3","company":"openai","family":"o3","version":"o3","score":6.5},{"place":257,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":6.5},{"place":258,"model":"trm","company":"samsung","family":"TRM","version":"TRM","score":6.25},{"place":259,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":6.11},{"place":260,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":6.1},{"place":261,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":6.1},{"place":262,"model":"claude-sonnet-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":5.93},{"place":263,"model":"claude-sonnet-4-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":5.93},{"place":264,"model":"claude-sonnet-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":5.9},{"place":265,"model":"claude-4.5-sonnet-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":5.83},{"place":266,"model":"claude-4.5-sonnet-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":5.8},{"place":267,"model":"gpt-5.4-nano-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":5.69},{"place":268,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":5.28},{"place":269,"model":"gemini-3.5-flash-lite-medium","company":"google","family":"Gemini","version":"Gemini 3.5","score":5.28},{"place":270,"model":"gpt-5.6-luna-low","company":"openai","family":"GPT","version":"GPT-5.6","score":5.14},{"place":271,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":5},{"place":272,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":5},{"place":273,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.9},{"place":274,"model":"o3-pro","company":"openai","family":"o3","version":"o3","score":4.9},{"place":275,"model":"o3-pro-high","company":"openai","family":"o3","version":"o3","score":4.9},{"place":276,"model":"gemini-2.5-pro-thinking-32k","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.9},{"place":277,"model":"o3-pro-high","company":"openai","family":"o3","version":"o3","score":4.86},{"place":278,"model":"gemini-2.5-pro-thinking-32k","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.86},{"place":279,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":4.86},{"place":280,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":4.86},{"place":281,"model":"inkling-small-low","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":4.86},{"place":282,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":4.58},{"place":283,"model":"claude-opus-4-20250514-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":4.52},{"place":284,"model":"claude-opus-4-20250514-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":4.5},{"place":285,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":4.44},{"place":286,"model":"gpt-5.4-mini-medium","company":"openai","family":"GPT","version":"GPT-5.4","score":4.44},{"place":287,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":4.4},{"place":288,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":4.4},{"place":289,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":4.2},{"place":290,"model":"gemini-2.5-pro-thinking-16k","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.03},{"place":291,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":4.03},{"place":292,"model":"claude-4.5-haiku-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.03},{"place":293,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":4.03},{"place":294,"model":"inkling-small-minimal","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":4.03},{"place":295,"model":"gemini-2.5-pro-thinking-16k","company":"google","family":"Gemini","version":"Gemini 2.5","score":4},{"place":296,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":4},{"place":297,"model":"o3-preview-low","company":"openai","family":"o3","version":"o3","score":4},{"place":298,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":4},{"place":299,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4},{"place":300,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.8},{"place":301,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3.8},{"place":302,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3.75},{"place":303,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":3.61},{"place":304,"model":"gpt-5.6-luna-0730-low","company":"openai","family":"GPT","version":"GPT-5.6","score":3.61},{"place":305,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":3.5},{"place":306,"model":"gemini-2.5-pro-preview-thinking-1k","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.4},{"place":307,"model":"gemini-3-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3","score":3.33},{"place":308,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":3},{"place":309,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":3},{"place":310,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":3},{"place":311,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":2.99},{"place":312,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":2.98},{"place":313,"model":"gemini-2.5-pro-thinking-8k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.92},{"place":314,"model":"gemini-2.5-pro-thinking-8k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.9},{"place":315,"model":"claude-4.5-haiku-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.78},{"place":316,"model":"claude-haiku-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":2.78},{"place":317,"model":"gemini-3.6-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3.6","score":2.64},{"place":318,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":2.61},{"place":319,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":2.6},{"place":320,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":2.6},{"place":321,"model":"gemini-2.5-flash-preview-thinking-24k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.54},{"place":322,"model":"gemini-2.5-flash-preview-thinking-24k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.5},{"place":323,"model":"architects","company":"arcprize","family":"ARChitects","version":"ARChitects","score":2.5},{"place":324,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.5},{"place":325,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":2.4},{"place":326,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":2.36},{"place":327,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":2.3},{"place":328,"model":"gemini-2.5-flash-preview-thinking-1k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.2},{"place":329,"model":"gemini-2.5-flash-preview-thinking-1k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.16},{"place":330,"model":"gemini-2.5-flash-preview-thinking-8k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.12},{"place":331,"model":"claude-sonnet-4-20250514-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":2.12},{"place":332,"model":"claude-sonnet-4-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":2.12},{"place":333,"model":"gemini-2.5-flash-preview-thinking-8k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.1},{"place":334,"model":"claude-sonnet-4-20250514-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4","score":2.1},{"place":335,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":2.1},{"place":336,"model":"o3-pro-low","company":"openai","family":"o3","version":"o3","score":2.1},{"place":337,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":2.08},{"place":338,"model":"deepseek-v4-flash-0731-none","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":2.08},{"place":339,"model":"o3-pro-low","company":"openai","family":"o3","version":"o3","score":2.05},{"place":340,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":2},{"place":341,"model":"gemini-2.5-flash-preview-thinking-16k","company":"google","family":"Gemini","version":"Gemini 2.5","score":2},{"place":342,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":1.99},{"place":343,"model":"gemini-2.5-flash-preview-thinking-16k","company":"google","family":"Gemini","version":"Gemini 2.5","score":1.98},{"place":344,"model":"o3-pro-medium","company":"openai","family":"o3","version":"o3","score":1.94},{"place":345,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":1.94},{"place":346,"model":"gpt-5.1-low","company":"openai","family":"GPT","version":"GPT-5.1","score":1.94},{"place":347,"model":"gpt-5.4-nano-medium","company":"openai","family":"GPT","version":"GPT-5.4","score":1.94},{"place":348,"model":"o3-pro-medium","company":"openai","family":"o3","version":"o3","score":1.9},{"place":349,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":1.9},{"place":350,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":1.7},{"place":351,"model":"o4-mini-low","company":"openai","family":"o4","version":"o4","score":1.7},{"place":352,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":1.7},{"place":353,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":1.69},{"place":354,"model":"o4-mini-low","company":"openai","family":"o4","version":"o4","score":1.67},{"place":355,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":1.67},{"place":356,"model":"claude-4.5-haiku-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1.67},{"place":357,"model":"gpt-6-sol-none","company":"openai","family":"GPT","version":"GPT-6","score":1.67},{"place":358,"model":"icecuber","company":"arcprize","family":"ARChitects","version":"ARChitects","score":1.6},{"place":359,"model":"gpt-5.4-nano-low","company":"openai","family":"GPT","version":"GPT-5.4","score":1.53},{"place":360,"model":"gemini-3.5-flash-lite-low","company":"google","family":"Gemini","version":"Gemini 3.5","score":1.53},{"place":361,"model":"qwen3.8-27b-none","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1.53},{"place":362,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1.3},{"place":363,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1.3},{"place":364,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":1.3},{"place":365,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1.3},{"place":366,"model":"codex-mini-latest","company":"openai","family":"Codex","version":"Codex","score":1.3},{"place":367,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1.3},{"place":368,"model":"codex-mini-latest","company":"openai","family":"Codex","version":"Codex","score":1.27},{"place":369,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1.27},{"place":370,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1.27},{"place":371,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1.25},{"place":372,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1.25},{"place":373,"model":"claude-4.5-haiku-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1.25},{"place":374,"model":"gemini-3-flash-low","company":"google","family":"Gemini","version":"Gemini 3","score":1.25},{"place":375,"model":"deepseek-v4.1-flash-none","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1.25},{"place":376,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1.12},{"place":377,"model":"gpt-5.4-mini-low","company":"openai","family":"GPT","version":"GPT-5.4","score":1.11},{"place":378,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1.1},{"place":379,"model":"claude-3.7-sonnet-thinking-8k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":0.9},{"place":380,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":0.9},{"place":381,"model":"claude-sonnet-4-20250514-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4","score":0.9},{"place":382,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":0.88},{"place":383,"model":"claude-sonnet-4-20250514-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4","score":0.85},{"place":384,"model":"claude-sonnet-4-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4","score":0.85},{"place":385,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":0.83},{"place":386,"model":"gpt-5-mini-low","company":"openai","family":"GPT","version":"GPT-5","score":0.83},{"place":387,"model":"gpt-5.2-none","company":"openai","family":"GPT","version":"GPT-5.2","score":0.83},{"place":388,"model":"gpt-5.6-luna-0730-none","company":"openai","family":"GPT","version":"GPT-5.6","score":0.83},{"place":389,"model":"gemini-3.5-flash-lite-minimal","company":"google","family":"Gemini","version":"Gemini 3.5","score":0.83},{"place":390,"model":"deepseek-v4-pro-0813-none","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":0.83},{"place":391,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":0.8},{"place":392,"model":"gpt-5-mini-low","company":"openai","family":"GPT","version":"GPT-5","score":0.8},{"place":393,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":0.8},{"place":394,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":0.8},{"place":395,"model":"claude-3.7-sonnet-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":0.7},{"place":396,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":0.42},{"place":397,"model":"grok-3-mini-beta-low","company":"xai","family":"Grok","version":"Grok 3","score":0.42},{"place":398,"model":"gpt-5.1-none","company":"openai","family":"GPT","version":"GPT-5.1","score":0.42},{"place":399,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":0.4},{"place":400,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":0.4},{"place":401,"model":"claude-3.7-sonnet-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":0.4},{"place":402,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":0},{"place":403,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0},{"place":404,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":0},{"place":405,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":406,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":0},{"place":407,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":0},{"place":408,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":0},{"place":409,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":0},{"place":410,"model":"llama-4-scout","company":"meta","family":"Llama","version":"Llama 1","score":0},{"place":411,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":412,"model":"o3-mini-low","company":"openai","family":"o3","version":"o3","score":0},{"place":413,"model":"claude-opus-4-20250514-thinking-1k","company":"anthropic","family":"Claude","version":"Claude 4","score":0},{"place":414,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":0},{"place":415,"model":"magistral-small-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":0},{"place":416,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":0},{"place":417,"model":"magistral-medium-thinking","company":"mistral","family":"Magistral","version":"Magistral","score":0},{"place":418,"model":"gemini-2.5-pro-thinking-1k","company":"google","family":"Gemini","version":"Gemini 2.5","score":0},{"place":419,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":420,"model":"gpt-5-nano-low","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":421,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":422,"model":"inkling-small-none","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":0},{"place":423,"model":"gpt-6-luna-none","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":424,"model":"magistral-medium","company":"magistral","family":"Magistral","version":"Magistral","score":0}]},{"id":"arc-agi-3","name":"ARC-AGI-3","topic":"General reasoning","description":"ARC-AGI-3 interactive reasoning benchmark; Relative Human Action Efficiency (RHAE) score.","url":"https://arcprize.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":99.9,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.9},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":30.2},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":7.8},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":7.78},{"place":5,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":6.9},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1.5},{"place":7,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":0.8},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":0.43},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":0.42},{"place":10,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":0.4},{"place":11,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":0.18}]},{"id":"arc-average","name":"ARC Average","topic":"Science QA (average)","description":"Average accuracy across ARC-Easy and ARC-Challenge.","url":"https://github.com/allenai/ai2-arc","leaderboard":"","github":"https://github.com/allenai/ai2-arc","paper":"","metric":"percent","stars":"","top_model":"SmolLM2 1.7B Pretrained","top_percent":60.5,"top_model_id":"smollm2-1.7b-pretrained","top_generation":"SmolLM2","top_model_base":"SmolLM2 1.7B","top_model_family":"SmolLM","top_company":"huggingface","top_open_source":1,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":60.5},{"place":2,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":59.9},{"place":3,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.5},{"place":4,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":51.7},{"place":5,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":49.2},{"place":6,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.2},{"place":7,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":43.9},{"place":8,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":43.9},{"place":9,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":43.7},{"place":10,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":41.6},{"place":11,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":37.3}]},{"id":"arc-challenge","name":"ARC-Challenge","topic":"Science QA","description":"Hard subset of AI2 Reasoning Challenge; grade-school science.","url":"https://github.com/allenai/ai2-arc","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef-Flash","top_percent":98.3,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":378,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":98.3},{"place":2,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":97.8},{"place":3,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":97.8},{"place":4,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":97.7},{"place":5,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":97.7},{"place":6,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":97.6},{"place":7,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":97.5},{"place":8,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":97.4},{"place":9,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":97.35},{"place":10,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":97.3},{"place":11,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":97.27},{"place":12,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":97.2},{"place":13,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":97.1},{"place":14,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97},{"place":15,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":96.9},{"place":16,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":96.9},{"place":17,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":96.9},{"place":18,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":96.8},{"place":19,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":96.7},{"place":20,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":96.66},{"place":21,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":96.6},{"place":22,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":96.59},{"place":23,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":96.5},{"place":24,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":96.4},{"place":25,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":96.4},{"place":26,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":96.32},{"place":27,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":96.3},{"place":28,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":96.27},{"place":29,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":96.27},{"place":30,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":96.2},{"place":31,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":96.2},{"place":32,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":96.1},{"place":33,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":96.08},{"place":34,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":95.99},{"place":35,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":95.99},{"place":36,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.96},{"place":37,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":95.93},{"place":38,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":95.9},{"place":39,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":95.82},{"place":40,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":95.81},{"place":41,"model":"yuan2.0-m32","company":"yuanlab","family":"Yuan","version":"Yuan2.0-M32","score":95.8},{"place":42,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":95.7},{"place":43,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":95.7},{"place":44,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":95.6},{"place":45,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":95.6},{"place":46,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":95.59},{"place":47,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":95.59},{"place":48,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":95.5},{"place":49,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":95.5},{"place":50,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.39},{"place":51,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":95.3},{"place":52,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":95.3},{"place":53,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":95.22},{"place":54,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":95.2},{"place":55,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.16},{"place":56,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":95.08},{"place":57,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":95},{"place":58,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":94.8},{"place":59,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":94.8},{"place":60,"model":"nova-pro","company":"amazon","family":"Nova","version":"Nova","score":94.8},{"place":61,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":94.8},{"place":62,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":94.8},{"place":63,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":94.71},{"place":64,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":94.65},{"place":65,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":94.6},{"place":66,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":94.58},{"place":67,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94.58},{"place":68,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":94.5},{"place":69,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":94.5},{"place":70,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":94.5},{"place":71,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":94.45},{"place":72,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":94.4},{"place":73,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":94.4},{"place":74,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":94.4},{"place":75,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":94.3},{"place":76,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":94.3},{"place":77,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":94.1},{"place":78,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":93.9},{"place":79,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":93.9},{"place":80,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.9},{"place":81,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":93.7},{"place":82,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":93.54},{"place":83,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":93.5},{"place":84,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":93.43},{"place":85,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.3},{"place":86,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":93.3},{"place":87,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":93.3},{"place":88,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":93.2},{"place":89,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":93.1},{"place":90,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.1},{"place":91,"model":"jamba-1.5-large","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":93},{"place":92,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":92.92},{"place":93,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":92.9},{"place":94,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":92.88},{"place":95,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":92.83},{"place":96,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":92.8},{"place":97,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":92.8},{"place":98,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":92.66},{"place":99,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":92.66},{"place":100,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":92.6},{"place":101,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":92.55},{"place":102,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":92.5},{"place":103,"model":"nova-lite","company":"amazon","family":"Nova","version":"Nova","score":92.4},{"place":104,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":92.4},{"place":105,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":92.33},{"place":106,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":92.3},{"place":107,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":92.2},{"place":108,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.2},{"place":109,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":92.2},{"place":110,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":92.2},{"place":111,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":92.1},{"place":112,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":92.06},{"place":113,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.98},{"place":114,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":91.9},{"place":115,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.89},{"place":116,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.72},{"place":117,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":91.7},{"place":118,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":91.7},{"place":119,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":91.6},{"place":120,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":91.47},{"place":121,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":91.4},{"place":122,"model":"mistral-small-3-24b-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":91.3},{"place":123,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":91.3},{"place":124,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":91.2},{"place":125,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":91.19},{"place":126,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":91},{"place":127,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":90.7},{"place":128,"model":"phi-3-small-8k-instruct","company":"microsoft","family":"Phi","version":"Phi-3","score":90.7},{"place":129,"model":"nova-micro","company":"amazon","family":"Nova","version":"Nova","score":90.2},{"place":130,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":90.13},{"place":131,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":90.09},{"place":132,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":90},{"place":133,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":90},{"place":134,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":89.76},{"place":135,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":89.22},{"place":136,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":89.2},{"place":137,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":89},{"place":138,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":88.9},{"place":139,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":88.8},{"place":140,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":88.6},{"place":141,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.6},{"place":142,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":88},{"place":143,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":87.8},{"place":144,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":87.46},{"place":145,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":86.4},{"place":146,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":86.1},{"place":147,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":86.1},{"place":148,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":86},{"place":149,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":85.9},{"place":150,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":85.8},{"place":151,"model":"jamba-1.5-mini","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":85.7},{"place":152,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":85.6},{"place":153,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":85.4},{"place":154,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":85.1},{"place":155,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":85},{"place":156,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":84.9},{"place":157,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":84.8},{"place":158,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":84.67},{"place":159,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":84.6},{"place":160,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.4},{"place":161,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":84.4},{"place":162,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":84.3},{"place":163,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":84},{"place":164,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":83.8},{"place":165,"model":"phi-4-mini","company":"microsoft","family":"Phi","version":"Phi 4","score":83.7},{"place":166,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":83.4},{"place":167,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":83.4},{"place":168,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":82.66},{"place":169,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":82.4},{"place":170,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.4},{"place":171,"model":"hrm-text-1b","company":"sapient","family":"HRM","version":"HRM-Text","score":81.9},{"place":172,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":81.8},{"place":173,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":81.7},{"place":174,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.6},{"place":175,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":81.36},{"place":176,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":81.09},{"place":177,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81},{"place":178,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":80.7},{"place":179,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":80},{"place":180,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":80},{"place":181,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":80},{"place":182,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":79.8},{"place":183,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":79.7},{"place":184,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":79.7},{"place":185,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":79.66},{"place":186,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":79.4},{"place":187,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":78.98},{"place":188,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":78.6},{"place":189,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":78.6},{"place":190,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":78.59},{"place":191,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":78.3},{"place":192,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":78.2},{"place":193,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":78.2},{"place":194,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":78.1},{"place":195,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":77.7},{"place":196,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":77.6},{"place":197,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":77.4},{"place":198,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":77.2},{"place":199,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":76.79},{"place":200,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.3},{"place":201,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":75.3},{"place":202,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":74.8},{"place":203,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":74.06},{"place":204,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":74},{"place":205,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":73.7},{"place":206,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":73.56},{"place":207,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":73.4},{"place":208,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":73.38},{"place":209,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":72.44},{"place":210,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.4},{"place":211,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":71.9},{"place":212,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":71.53},{"place":213,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":71.4},{"place":214,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":71.25},{"place":215,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":71.2},{"place":216,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":71.1},{"place":217,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":71.08},{"place":218,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":71},{"place":219,"model":"command-r-plus-08-2024","company":"cohere","family":"Command","version":"Command","score":71},{"place":220,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":70.73},{"place":221,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":70.7},{"place":222,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":70.6},{"place":223,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.5},{"place":224,"model":"hy-1.8b","company":"tencent","family":"HY","version":"HY","score":70.5},{"place":225,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":70.5},{"place":226,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.4},{"place":227,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":70.39},{"place":228,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":70.39},{"place":229,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":70.2},{"place":230,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":70},{"place":231,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":69.6},{"place":232,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":69.6},{"place":233,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":69.5},{"place":234,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":69.5},{"place":235,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":69.2},{"place":236,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":69.2},{"place":237,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":69.2},{"place":238,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":69.1},{"place":239,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":68.9},{"place":240,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":68.9},{"place":241,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":68.9},{"place":242,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":68.86},{"place":243,"model":"hy-1.8b-int4gptq","company":"tencent","family":"HY","version":"HY","score":68.83},{"place":244,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":68.8},{"place":245,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":68.5},{"place":246,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":68.4},{"place":247,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":68.34},{"place":248,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":68.2},{"place":249,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":68.17},{"place":250,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":68.14},{"place":251,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":68},{"place":252,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":67.5},{"place":253,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":67.32},{"place":254,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.3},{"place":255,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.3},{"place":256,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":67.12},{"place":257,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":66.81},{"place":258,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":66.55},{"place":259,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":66.5},{"place":260,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":66.4},{"place":261,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":66.3},{"place":262,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.1},{"place":263,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.04},{"place":264,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":66},{"place":265,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":66},{"place":266,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":65.9},{"place":267,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":65.8},{"place":268,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":65.7},{"place":269,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":65.6},{"place":270,"model":"llama-tfree-hat-pretrained-7b-dpo","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":65.5},{"place":271,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":65.44},{"place":272,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":65.4},{"place":273,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":65.4},{"place":274,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":65.4},{"place":275,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":64.99},{"place":276,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":64.9},{"place":277,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":64.9},{"place":278,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":64.76},{"place":279,"model":"openchat-3.5-0106-gemma","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":64.68},{"place":280,"model":"bielik-11b-v3.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":64.59},{"place":281,"model":"hy-1.8b-2bit","company":"tencent","family":"HY","version":"HY","score":64.45},{"place":282,"model":"jamba-v0.1","company":"ai21","family":"Jamba","version":"Jamba","score":64.4},{"place":283,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":64.3},{"place":284,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":64.1},{"place":285,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":64.1},{"place":286,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":63.99},{"place":287,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.7},{"place":288,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":63.65},{"place":289,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.65},{"place":290,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.65},{"place":291,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":63.6},{"place":292,"model":"rnd1-base-0910","company":"radicalnumerics","family":"RND1","version":"RND1","score":63.2},{"place":293,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":63.14},{"place":294,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":63.05},{"place":295,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":62.9},{"place":296,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":62.7},{"place":297,"model":"bielik-11b-v2.6-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.6","score":62.54},{"place":298,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":62.37},{"place":299,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":62},{"place":300,"model":"bielik-11b-v2.5-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.5","score":61.95},{"place":301,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":61.9},{"place":302,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":61.6},{"place":303,"model":"bielik-11b-v3.0","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":61.43},{"place":304,"model":"apertus-v1.1-4b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":61.15},{"place":305,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":61.1},{"place":306,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":61.1},{"place":307,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":61.09},{"place":308,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":61.01},{"place":309,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":61},{"place":310,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":60.92},{"place":311,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":60.92},{"place":312,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.9},{"place":313,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":60.9},{"place":314,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":60.9},{"place":315,"model":"mistral-7b-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":60.84},{"place":316,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":60.75},{"place":317,"model":"meta-llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":60.75},{"place":318,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":60.6},{"place":319,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":60.6},{"place":320,"model":"bielik-11b-v2","company":"SpeakLeash","family":"Bielik","version":"Bielik v2","score":60.58},{"place":321,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":60.3},{"place":322,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":60.24},{"place":323,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":60.24},{"place":324,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":60.23},{"place":325,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":60.15},{"place":326,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":60},{"place":327,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":59.98},{"place":328,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":59.98},{"place":329,"model":"bielik-11b-v2.2-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.2","score":59.9},{"place":330,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":59.8},{"place":331,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":59.7},{"place":332,"model":"bielik-11b-v2.1-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.1","score":59.56},{"place":333,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":59.5},{"place":334,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":59.4},{"place":335,"model":"bielik-11b-v2.3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.3","score":59.3},{"place":336,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":59.3},{"place":337,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":59},{"place":338,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":58.7},{"place":339,"model":"bielik-11b-v2.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.0","score":58.62},{"place":340,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":58.28},{"place":341,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":58.2},{"place":342,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":58.19},{"place":343,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":58},{"place":344,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":57.9},{"place":345,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":57.8},{"place":346,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":57.8},{"place":347,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":57.68},{"place":348,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":57.63},{"place":349,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":57.6},{"place":350,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":57.3},{"place":351,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":57.2},{"place":352,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":57},{"place":353,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":57},{"place":354,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":56.82},{"place":355,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":56.57},{"place":356,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":56.5},{"place":357,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.5},{"place":358,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":56.49},{"place":359,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":56.2},{"place":360,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":56.14},{"place":361,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":56.1},{"place":362,"model":"bielik-4.5b-v3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":56.06},{"place":363,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":56},{"place":364,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.9},{"place":365,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":55.89},{"place":366,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.72},{"place":367,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.7},{"place":368,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":55.7},{"place":369,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":55.6},{"place":370,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":55.59},{"place":371,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":55.5},{"place":372,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.46},{"place":373,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":55.38},{"place":374,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":54.9},{"place":375,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54.78},{"place":376,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":54.7},{"place":377,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.7},{"place":378,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":54.52},{"place":379,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":54.52},{"place":380,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":54.44},{"place":381,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.44},{"place":382,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":54.35},{"place":383,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":54.2},{"place":384,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":53.4},{"place":385,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":53.2},{"place":386,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.2},{"place":387,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":53.2},{"place":388,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":53.2},{"place":389,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":53.2},{"place":390,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":53},{"place":391,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":52.9},{"place":392,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":52.7},{"place":393,"model":"apertus-v1.1-1.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":52.66},{"place":394,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":52.62},{"place":395,"model":"palm-62b","company":"google","family":"PaLM","version":"PaLM","score":52.5},{"place":396,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":52.5},{"place":397,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":52.47},{"place":398,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":52.39},{"place":399,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":51.96},{"place":400,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":51.86},{"place":401,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":51.5},{"place":402,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":51.4},{"place":403,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":51.4},{"place":404,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":51.2},{"place":405,"model":"bielik-4.5b-v3","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":51.19},{"place":406,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":50.8},{"place":407,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":50.51},{"place":408,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":50.3},{"place":409,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":50.2},{"place":410,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":50.2},{"place":411,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":50},{"place":412,"model":"hy-0.5b","company":"tencent","family":"HY","version":"HY","score":49.89},{"place":413,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":49.83},{"place":414,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":49.8},{"place":415,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":49.57},{"place":416,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":49.4},{"place":417,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":49.1},{"place":418,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":49},{"place":419,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.98},{"place":420,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":48.8},{"place":421,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":48.6},{"place":422,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":48.6},{"place":423,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":48.5},{"place":424,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":48.4},{"place":425,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":48.35},{"place":426,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":48.21},{"place":427,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":48.1},{"place":428,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":48.1},{"place":429,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":47.6},{"place":430,"model":"bielik-7b-instruct-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":47.53},{"place":431,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":47.5},{"place":432,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":47.2},{"place":433,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":47.2},{"place":434,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.59},{"place":435,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":46.2},{"place":436,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":46.08},{"place":437,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":45.9},{"place":438,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":45.56},{"place":439,"model":"bielik-7b-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":45.22},{"place":440,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":45.2},{"place":441,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":45.1},{"place":442,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":45},{"place":443,"model":"apertus-v1.1-0.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":44.96},{"place":444,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":44.88},{"place":445,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":44.88},{"place":446,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":44.54},{"place":447,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":43.9},{"place":448,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":43.86},{"place":449,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.77},{"place":450,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":43.7},{"place":451,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":43.69},{"place":452,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":43.2},{"place":453,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":43.09},{"place":454,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":42.75},{"place":455,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":42.6},{"place":456,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":42.4},{"place":457,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":42.2},{"place":458,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":42.15},{"place":459,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":42.1},{"place":460,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":42.06},{"place":461,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":42.06},{"place":462,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":41.98},{"place":463,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.8},{"place":464,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":41.7},{"place":465,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":41.38},{"place":466,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":41},{"place":467,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":40.7},{"place":468,"model":"trlm-135m","company":"loka","family":"TRLM","version":"TRLM","score":40.61},{"place":469,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":40.53},{"place":470,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39.25},{"place":471,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":39.25},{"place":472,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":38.8},{"place":473,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":38.7},{"place":474,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":38.4},{"place":475,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":38.28},{"place":476,"model":"huginn-3.5b","company":"tomg-umd","family":"Huginn","version":"Huginn","score":38.2},{"place":477,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":38},{"place":478,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":37.9},{"place":479,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.9},{"place":480,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":37.8},{"place":481,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.71},{"place":482,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":37.4},{"place":483,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":37.29},{"place":484,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":36.8},{"place":485,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":36.4},{"place":486,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":35.93},{"place":487,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":35.8},{"place":488,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":35.7},{"place":489,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.6},{"place":490,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":34.81},{"place":491,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":34.64},{"place":492,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":34.5},{"place":493,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":34.4},{"place":494,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":34.2},{"place":495,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":34.13},{"place":496,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":33.28},{"place":497,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":33.2},{"place":498,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":33.1},{"place":499,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":32.5},{"place":500,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":32.5},{"place":501,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":31.5},{"place":502,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":31.06},{"place":503,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":31},{"place":504,"model":"pythia-2.8b","company":"eleutherai","family":"Pythia","version":"Pythia","score":30.1},{"place":505,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":29},{"place":506,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":28.6},{"place":507,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":28.2},{"place":508,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":28.15},{"place":509,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":27.9},{"place":510,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":27.7},{"place":511,"model":"pythia-1.4b","company":"eleutherai","family":"Pythia","version":"Pythia","score":27.2},{"place":512,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":25.4},{"place":513,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":25.08},{"place":514,"model":"pythia-1b","company":"eleutherai","family":"Pythia","version":"Pythia","score":24.5},{"place":515,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":24.41},{"place":516,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":24.07},{"place":517,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":22.71},{"place":518,"model":"pythia-410m","company":"eleutherai","family":"Pythia","version":"Pythia","score":20.2},{"place":519,"model":"pythia-160m","company":"eleutherai","family":"Pythia","version":"Pythia","score":20.1},{"place":520,"model":"pythia-70m","company":"eleutherai","family":"Pythia","version":"Pythia","score":16.2},{"place":521,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.741},{"place":522,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.739}]},{"id":"arc-challenge-de","name":"ARC-Challenge (DE)","topic":"Science QA (German)","description":"German translation of the ARC Challenge benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"norm_log_acc","stars":"","top_model":"Llama-3_1-70B-TFree-HAT-SFT","top_percent":0.669,"top_model_id":"llama-3_1-70b-tfree-hat-sft","top_generation":"Llama TFree HAT","top_model_base":"Llama 3.1 70B TFree HAT","top_model_family":"Llama TFree HAT","top_company":"alephalpha","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.669},{"place":2,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.653}]},{"id":"arc-easy","name":"ARC-Easy","topic":"Science QA","description":"Easier subset of AI2 Reasoning Challenge.","url":"https://github.com/allenai/ai2-arc","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef-Omni","top_percent":99.8,"top_model_id":"clef-omni","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":172,"total_models":3854,"placements":[{"place":1,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":99.8},{"place":2,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":99.5},{"place":3,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":99.4},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":99.3},{"place":5,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":99.3},{"place":6,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":99.3},{"place":7,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":99.1},{"place":8,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":99.1},{"place":9,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":99},{"place":10,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":99},{"place":11,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":99},{"place":12,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":98.9},{"place":13,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":98.9},{"place":14,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":98.9},{"place":15,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":98.8},{"place":16,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":98.6},{"place":17,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":98.4},{"place":18,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":98.4},{"place":19,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":98.3},{"place":20,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":98.2},{"place":21,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":98.2},{"place":22,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":98.2},{"place":23,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":98.1},{"place":24,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":98.1},{"place":25,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":98.1},{"place":26,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":98},{"place":27,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":97.9},{"place":28,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":97.7},{"place":29,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":97.6},{"place":30,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":97.6},{"place":31,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":97.6},{"place":32,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":97.5},{"place":33,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97.5},{"place":34,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":97.4},{"place":35,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":97.3},{"place":36,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":97.1},{"place":37,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":97.1},{"place":38,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":96.9},{"place":39,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":96.8},{"place":40,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":96.6},{"place":41,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":96.6},{"place":42,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":96.4},{"place":43,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":96.1},{"place":44,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":95.4},{"place":45,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":95.3},{"place":46,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":95.3},{"place":47,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":95.06},{"place":48,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":94.8},{"place":49,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.7},{"place":50,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":93.6},{"place":51,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":93.6},{"place":52,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":93.47},{"place":53,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":93},{"place":54,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":92.6},{"place":55,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":91.4},{"place":56,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":91.2},{"place":57,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":91.2},{"place":58,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":90.9},{"place":59,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":90.6},{"place":60,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":90.5},{"place":61,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":90.4},{"place":62,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":90.3},{"place":63,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":90.1},{"place":64,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":90},{"place":65,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":89.35},{"place":66,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":89},{"place":67,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":89},{"place":68,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":88.9},{"place":69,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":88.9},{"place":70,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":88.7},{"place":71,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":88.36},{"place":72,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":88.3},{"place":73,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":88.2},{"place":74,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":88},{"place":75,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":87.8},{"place":76,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":87.6},{"place":77,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":86.28},{"place":78,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":86.11},{"place":79,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":86.1},{"place":80,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":86.1},{"place":81,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":85.9},{"place":82,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":85.9},{"place":83,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":85.44},{"place":84,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":85.3},{"place":85,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":85.02},{"place":86,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":84.89},{"place":87,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":84.4},{"place":88,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":84.1},{"place":89,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":84},{"place":90,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":83.92},{"place":91,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":83.7},{"place":92,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":83.6},{"place":93,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":83.42},{"place":94,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":83.1},{"place":95,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":82.3},{"place":96,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":82.1},{"place":97,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":82},{"place":98,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":81.94},{"place":99,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":81.61},{"place":100,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":81.6},{"place":101,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":81.5},{"place":102,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":81.2},{"place":103,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":81.1},{"place":104,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":81.1},{"place":105,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":81},{"place":106,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":80.93},{"place":107,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.8},{"place":108,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":80.6},{"place":109,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":80.5},{"place":110,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":80.1},{"place":111,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":80},{"place":112,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":80},{"place":113,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":79.9},{"place":114,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":79.63},{"place":115,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":79.5},{"place":116,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":79.38},{"place":117,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":79.01},{"place":118,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":78.9},{"place":119,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":78.9},{"place":120,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":78.87},{"place":121,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":78.7},{"place":122,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":78.66},{"place":123,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":78.5},{"place":124,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":78.5},{"place":125,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":78.5},{"place":126,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":78},{"place":127,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":77.3},{"place":128,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":77.2},{"place":129,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":76.9},{"place":130,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":76.85},{"place":131,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":76.6},{"place":132,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":76.5},{"place":133,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":76.35},{"place":134,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":76.28},{"place":135,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":75.9},{"place":136,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":75.25},{"place":137,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":75.2},{"place":138,"model":"palm-62b","company":"google","family":"PaLM","version":"PaLM","score":75.2},{"place":139,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":75.2},{"place":140,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":74.8},{"place":141,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":74.6},{"place":142,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":74.58},{"place":143,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":74.45},{"place":144,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":74.33},{"place":145,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":74.3},{"place":146,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":74.3},{"place":147,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":74.28},{"place":148,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":73.9},{"place":149,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":73.78},{"place":150,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":73.6},{"place":151,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":73.2},{"place":152,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":73},{"place":153,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":73},{"place":154,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":72.9},{"place":155,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":72.8},{"place":156,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":72.01},{"place":157,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":71.8},{"place":158,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":71.78},{"place":159,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":71.6},{"place":160,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":71.5},{"place":161,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":71},{"place":162,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":70.9},{"place":163,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":70.8},{"place":164,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":70.41},{"place":165,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":70.2},{"place":166,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":70.2},{"place":167,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":70.2},{"place":168,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":70},{"place":169,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":69.99},{"place":170,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":69.9},{"place":171,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":69.8},{"place":172,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":69.1},{"place":173,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":68.8},{"place":174,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":68.7},{"place":175,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":68.6},{"place":176,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":68.1},{"place":177,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":67.9},{"place":178,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":67.7},{"place":179,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66},{"place":180,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":65.08},{"place":181,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":64.86},{"place":182,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":64.44},{"place":183,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":63.97},{"place":184,"model":"pythia-2.8b","company":"eleutherai","family":"Pythia","version":"Pythia","score":63.5},{"place":185,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":63.47},{"place":186,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":62.9},{"place":187,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":61.9},{"place":188,"model":"pythia-1.4b","company":"eleutherai","family":"Pythia","version":"Pythia","score":61.7},{"place":189,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.4},{"place":190,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":60.77},{"place":191,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":59.4},{"place":192,"model":"pythia-1b","company":"eleutherai","family":"Pythia","version":"Pythia","score":58.5},{"place":193,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":57.9},{"place":194,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":57.7},{"place":195,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54.7},{"place":196,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":54.1},{"place":197,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":53.2},{"place":198,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":52.7},{"place":199,"model":"pythia-410m","company":"eleutherai","family":"Pythia","version":"Pythia","score":51.7},{"place":200,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":50.5},{"place":201,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":49.1},{"place":202,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":48.8},{"place":203,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":47},{"place":204,"model":"pythia-160m","company":"eleutherai","family":"Pythia","version":"Pythia","score":44},{"place":205,"model":"pythia-70m","company":"eleutherai","family":"Pythia","version":"Pythia","score":38.5},{"place":206,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.92},{"place":207,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.911}]},{"id":"arc-easy-de","name":"ARC-Easy (DE)","topic":"Science QA (German)","description":"German translation of the ARC Easy science QA benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"norm_log_acc","stars":"","top_model":"Llama-3_1-70B-TFree-HAT-SFT","top_percent":0.848,"top_model_id":"llama-3_1-70b-tfree-hat-sft","top_generation":"Llama TFree HAT","top_model_base":"Llama 3.1 70B TFree HAT","top_model_family":"Llama TFree HAT","top_company":"alephalpha","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.848},{"place":2,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.825}]},{"id":"arena-hard","name":"Arena-Hard","topic":"Chat ability","description":"Hard prompts on Chatbot Arena.","url":"https://github.com/lm-sys/arena-hard-auto","leaderboard":"","github":"","paper":"","metric":"percent","stars":"920","top_model":"Mistral Medium 3","top_percent":97.1,"top_model_id":"mistral-medium-3","top_generation":"Mistral 3","top_model_base":"Mistral Medium 3","top_model_family":"Mistral","top_company":"mistral","top_open_source":0,"lower_is_better":false,"bench_models":89,"total_models":3854,"placements":[{"place":1,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":97.1},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":96.4},{"place":3,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":95.7},{"place":4,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.6},{"place":5,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":95.1},{"place":6,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.8},{"place":7,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":93.2},{"place":8,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":92.9},{"place":9,"model":"o1","company":"openai","family":"o1","version":"o1","score":92.1},{"place":10,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":92.1},{"place":11,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":91.8},{"place":12,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":91.7},{"place":13,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.5},{"place":14,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":89.5},{"place":15,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":89},{"place":16,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":88.3},{"place":17,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":87.9},{"place":18,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.8},{"place":19,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":85.8},{"place":20,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":85.6},{"place":21,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":85.5},{"place":22,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":85.2},{"place":23,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":85.1},{"place":24,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":81.8},{"place":25,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.4},{"place":26,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.2},{"place":27,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":80.4},{"place":28,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":79.3},{"place":29,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":79.1},{"place":30,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":77.9},{"place":31,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":76.2},{"place":32,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":74.9},{"place":33,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":74.6},{"place":34,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.5},{"place":35,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":74},{"place":36,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":73.1},{"place":37,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":71.2},{"place":38,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":71.02},{"place":39,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":69.3},{"place":40,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":68.98},{"place":41,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.4},{"place":42,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":68.3},{"place":43,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.3},{"place":44,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.1},{"place":45,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":66.3},{"place":46,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":65},{"place":47,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":57.56},{"place":48,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":57.5},{"place":49,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":55.7},{"place":50,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":55.25},{"place":51,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52},{"place":52,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":51.2},{"place":53,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":48.1},{"place":54,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":46.48},{"place":55,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":42.6},{"place":56,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":41.6},{"place":57,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":41.6},{"place":58,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":41.35},{"place":59,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":41.1},{"place":60,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":39.8},{"place":61,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":38.1},{"place":62,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":37.8},{"place":63,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":37.58},{"place":64,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":36.43},{"place":65,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":36.4},{"place":66,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":36.1},{"place":67,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":34.4},{"place":68,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":28.86},{"place":69,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":28.17},{"place":70,"model":"command-r7b","company":"cohere","family":"Command","version":"Command","score":27.95},{"place":71,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":27.8},{"place":72,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":26.7},{"place":73,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":25.84},{"place":74,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":25.52},{"place":75,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":25.44},{"place":76,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":25},{"place":77,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":24.86},{"place":78,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":24.2},{"place":79,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":24.19},{"place":80,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":23.6},{"place":81,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":23.4},{"place":82,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":23.3},{"place":83,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":20.6},{"place":84,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":17.9},{"place":85,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":17.8},{"place":86,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":17.17},{"place":87,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":12.6},{"place":88,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":11.5},{"place":89,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":11.4},{"place":90,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":10.36},{"place":91,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":10.2},{"place":92,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":10},{"place":93,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":7.5},{"place":94,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":4.6},{"place":95,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":1.7},{"place":96,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":1.2},{"place":97,"model":"grok-3-beta-think","company":"xai","family":"Grok","version":"Grok 3","score":null}]},{"id":"arena-hard-v2","name":"Arena-Hard V2","topic":"Chat ability","description":"Updated Arena-Hard v2 prompts on Chatbot Arena.","url":"https://github.com/lm-sys/arena-hard-auto","leaderboard":"","github":"https://github.com/lmarena/arena-hard-auto","paper":"","metric":"percent","stars":"920","top_model":"GPT-OSS 120B","top_percent":90.26,"top_model_id":"gpt-oss-120b","top_generation":"GPT-OSS","top_model_base":"GPT-OSS 120B","top_model_family":"GPT","top_company":"openai","top_open_source":1,"lower_is_better":false,"bench_models":104,"total_models":3854,"placements":[{"place":1,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":90.26},{"place":2,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.2},{"place":3,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":88.5},{"place":4,"model":"qwen3-moe-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.2},{"place":5,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":87},{"place":6,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":86.1},{"place":7,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":83.5},{"place":8,"model":"gpt-5-thinking-high","company":"openai","family":"GPT","version":"GPT-5","score":82.91},{"place":9,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":82.7},{"place":10,"model":"o4-mini-2025-04-16-high","company":"openai","family":"o4","version":"o4","score":81.7},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.7},{"place":12,"model":"ring-1t","company":"antgroup","family":"Ring","version":"Ring","score":81.59},{"place":13,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":80.6},{"place":14,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.18},{"place":15,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":79.7},{"place":16,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":79.6},{"place":17,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.2},{"place":18,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.2},{"place":19,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.66},{"place":20,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":78},{"place":21,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":77.92},{"place":22,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.7},{"place":23,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.15},{"place":24,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":74.85},{"place":25,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":74.8},{"place":26,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.88},{"place":27,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":73.41},{"place":28,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":73.2},{"place":29,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.8},{"place":30,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":72.7},{"place":31,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":72.54},{"place":32,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":72.1},{"place":33,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":71.04},{"place":34,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":71},{"place":35,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":69},{"place":36,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.6},{"place":37,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":68.2},{"place":38,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":68.1},{"place":39,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":67.93},{"place":40,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.7},{"place":41,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.7},{"place":42,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":67.3},{"place":43,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":66.7},{"place":44,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":66.5},{"place":45,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":66.1},{"place":46,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.4},{"place":47,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":65.19},{"place":48,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":64.8},{"place":49,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":62.9},{"place":50,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":62.5},{"place":51,"model":"solar-pro-3","company":"upstage","family":"Solar","version":"Solar Pro 3","score":62.5},{"place":52,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":62.3},{"place":53,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":61.5},{"place":54,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":61.5},{"place":55,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":60.27},{"place":56,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60.2},{"place":57,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":60},{"place":58,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60},{"place":59,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":58.7},{"place":60,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.5},{"place":61,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":58.3},{"place":62,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":58.3},{"place":63,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":58.1},{"place":64,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":57.8},{"place":65,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.8},{"place":66,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.7},{"place":67,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.7},{"place":68,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":56},{"place":69,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":56},{"place":70,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":55.8},{"place":71,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":55.1},{"place":72,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":55.1},{"place":73,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.8},{"place":74,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":51.5},{"place":75,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":50.9},{"place":76,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":50.2},{"place":77,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":50.1},{"place":78,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":50},{"place":79,"model":"gemini-2.5","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.1},{"place":80,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":49},{"place":81,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":48.6},{"place":82,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":48.6},{"place":83,"model":"gpt-oss-20b-a4b","company":"openai","family":"GPT","version":"GPT-OSS","score":48.5},{"place":84,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":48.4},{"place":85,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.4},{"place":86,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":48},{"place":87,"model":"claude-3-7-sonnet-20250219-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":47},{"place":88,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.7},{"place":89,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":45.1},{"place":90,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.8},{"place":91,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":43.6},{"place":92,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":43.1},{"place":93,"model":"gpt-4.5-preview","company":"openai","family":"GPT","version":"GPT-4.5","score":43},{"place":94,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":42.7},{"place":95,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":42},{"place":96,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":40.5},{"place":97,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.9},{"place":98,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.9},{"place":99,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":36.1},{"place":100,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.8},{"place":101,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":34.96},{"place":102,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":34.9},{"place":103,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":34.1},{"place":104,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":31.8},{"place":105,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":30.5},{"place":106,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.7},{"place":107,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.4},{"place":108,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.3},{"place":109,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":25.8},{"place":110,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":19.56},{"place":111,"model":"s1.1-32b","company":"scale","family":"s1","version":"s1","score":18.3},{"place":112,"model":"qwen3-4b-saferl-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":16.6},{"place":113,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":16.3},{"place":114,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":15.4},{"place":115,"model":"qwen3-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":13.7},{"place":116,"model":"athene-v2-chat","company":"nvidia","family":"Athene","version":"Athene V2","score":12.6},{"place":117,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":12.6},{"place":118,"model":"llama4-maverick-instruct-basic","company":"meta","family":"Llama","version":"Llama 4","score":12},{"place":119,"model":"qwen3-4b-saferl","company":"qwen","family":"Qwen","version":"Qwen3","score":10.7},{"place":120,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":9.7},{"place":121,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.5},{"place":122,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8},{"place":123,"model":"llama-3.1-nemotron-70b-instruct-hf","company":"nvidia","family":"Llama","version":"Llama 3.1","score":6.8},{"place":124,"model":"openthinker2-32b","company":"openthinker","family":"OpenThinker","version":"OpenThinker2","score":2.3}]},{"id":"arena-hard-v2-creative-writing","name":"Arena-Hard V2 Creative Writing","topic":"Creative writing","description":"Chatbot Arena Hard V2 creative writing win-rate subset.","url":"https://github.com/lm-sys/arena-hard-auto","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":93.6,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.6},{"place":2,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":92.2},{"place":3,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.8},{"place":4,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":86.2},{"place":5,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":86.2},{"place":6,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85},{"place":7,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":80.1},{"place":8,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":78.7},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.7},{"place":10,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.8},{"place":11,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":68.5},{"place":12,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.3},{"place":13,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66},{"place":14,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63.2},{"place":15,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":61.5},{"place":16,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.8},{"place":17,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":59.3},{"place":18,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":54.6},{"place":19,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":25.9}]},{"id":"arena-hard-v2-hard-prompt","name":"Arena-Hard V2 Hard Prompt","topic":"Chat ability","description":"Chatbot Arena Hard V2 benchmark using the hard prompt win-rate subset.","url":"https://github.com/lm-sys/arena-hard-auto","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nemotron-Cascade-2-30B-A3B","top_percent":88.2,"top_model_id":"nemotron-cascade-2-30b-a3b","top_generation":"Nemotron Cascade 2","top_model_base":"Nemotron Cascade 2 30B A3B","top_model_family":"Nemotron Cascade","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":88.2},{"place":2,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.9},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.6},{"place":4,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.1},{"place":5,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":71.9},{"place":6,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":71.9},{"place":7,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":71.2},{"place":8,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.5},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.3},{"place":10,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":59.7},{"place":11,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":54.5},{"place":12,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":54.1},{"place":13,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":53.4},{"place":14,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":51.7},{"place":15,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":51.6},{"place":16,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49.6},{"place":17,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.7},{"place":18,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":39.9},{"place":19,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.9}]},{"id":"arkitscenes","name":"ARKitScenes","topic":"3D scene understanding","description":"ARKitScenes benchmark for assessing 3D scene reconstruction and understanding from mixed reality captures.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen2.5-VL 72B Instruct","top_percent":61.5,"top_model_id":"qwen2.5-vl-72b-instruct","top_generation":"Qwen2.5 VL","top_model_base":"Qwen2.5-VL 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":61.5},{"place":2,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.8},{"place":3,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.6},{"place":4,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.2},{"place":5,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.1},{"place":6,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.6},{"place":7,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.7},{"place":8,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":45.8},{"place":9,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":36.2},{"place":10,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":30.3},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":7.4}]},{"id":"art-agent-red-teaming","name":"ART Agent Red Teaming","topic":"Agent robustness","description":"Evaluation suite for adversarial red-teaming of autonomous AI agents.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2507.20526","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":33.6,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":true,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33.6},{"place":2,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":40},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":40},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":44.9},{"place":5,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51.6},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.6},{"place":7,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":54.9},{"place":8,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":56.8},{"place":9,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":57.8},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":60.7},{"place":11,"model":"o3","company":"openai","family":"o3","version":"o3","score":62.7},{"place":12,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":63.6},{"place":13,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":64.5},{"place":14,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":65},{"place":15,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":65.5},{"place":16,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":65.9},{"place":17,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":70.9},{"place":18,"model":"o1","company":"openai","family":"o1","version":"o1","score":71.8},{"place":19,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":75},{"place":20,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":75.5},{"place":21,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":76.1},{"place":22,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":76.4},{"place":23,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":76.4},{"place":24,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":77.5},{"place":25,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":80.5},{"place":26,"model":"grok-2","company":"xai","family":"Grok","version":"Grok 2","score":82.7},{"place":27,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":84.5},{"place":28,"model":"gemini-2.5-pro-preview-05-06","company":"google","family":"Gemini","version":"Gemini 2.5","score":85},{"place":29,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":85},{"place":30,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":85.5},{"place":31,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86.4},{"place":32,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":86.4},{"place":33,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":87.7},{"place":34,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":89},{"place":35,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.6},{"place":36,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":90.9},{"place":37,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.7},{"place":38,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":92.2},{"place":39,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":93.6}]},{"id":"artifactsbench","name":"ArtifactsBench","topic":"Agentic coding","description":"Artifacts-focused coding and tool-use benchmark evaluating generated code artifacts.","url":"","leaderboard":"https://artifactsbenchmark.github.io/leaderboard.html","github":"https://github.com/Tencent-Hunyuan/ArtifactsBenchmark","paper":"https://arxiv.org/abs/2507.04952","metric":"percent","stars":"","top_model":"TeleChat3-Coder-36B-Thinking","top_percent":82.8,"top_model_id":"telechat3-coder-36b-thinking","top_generation":"TeleChat3","top_model_base":"TeleChat3 Coder 36B","top_model_family":"TeleChat","top_company":"teleai","top_open_source":1,"lower_is_better":false,"bench_models":55,"total_models":3854,"placements":[{"place":1,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":82.8},{"place":2,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":78.7},{"place":3,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":77},{"place":4,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.8},{"place":5,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":73},{"place":6,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":72.55},{"place":7,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":68.7},{"place":8,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":66.8},{"place":9,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":66.8},{"place":10,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":65.1},{"place":11,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64.3},{"place":12,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64},{"place":13,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.5},{"place":14,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61},{"place":15,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":60.28},{"place":16,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":59.8},{"place":17,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":59.76},{"place":18,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":59.31},{"place":19,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":59.3},{"place":20,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":59.2},{"place":21,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.74},{"place":22,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.7},{"place":23,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":57.3},{"place":24,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":57.28},{"place":25,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":56.91},{"place":26,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":55.9},{"place":27,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":55.8},{"place":28,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":55.8},{"place":29,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":55.01},{"place":30,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":54.2},{"place":31,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":54.04},{"place":32,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":51.6},{"place":33,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":51.33},{"place":34,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":51.32},{"place":35,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":50.62},{"place":36,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":49.8},{"place":37,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":48.9},{"place":38,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.08},{"place":39,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":47.93},{"place":40,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":47.73},{"place":41,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":47.65},{"place":42,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":47.15},{"place":43,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":45.95},{"place":44,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.14},{"place":45,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.87},{"place":46,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":43.5},{"place":47,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":43.4},{"place":48,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":43.29},{"place":49,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":42.8},{"place":50,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":41.41},{"place":51,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":41.09},{"place":52,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":41.04},{"place":53,"model":"hunyuan-80b-a13b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":40.95},{"place":54,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":39.85},{"place":55,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.8},{"place":56,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":36.6},{"place":57,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":36.4},{"place":58,"model":"kat-v1-40b","company":"kuaishou","family":"KAT","version":"KAT V1","score":35.21},{"place":59,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":33.54},{"place":60,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.61}]},{"id":"arxivmath","name":"ArxivMath","topic":"Research math","description":"Math problems derived from recent arXiv papers (reported in Anthropic Fable 5/Mythos 5 system card).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":79.5,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":79.5},{"place":2,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":78.5},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":71.8},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":71.5},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":71.5},{"place":6,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":68.7},{"place":7,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67.1},{"place":8,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":66.6},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.8},{"place":10,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.1},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":60.8},{"place":12,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.4},{"place":13,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":56},{"place":14,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":53.4},{"place":15,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.6},{"place":16,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":52.2},{"place":17,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":51.7},{"place":18,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":46.1},{"place":19,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":44.2}]},{"id":"asr-ami","name":"ASR AMI","topic":"ASR","description":"Automatic speech recognition benchmark on AMI meeting speech.","url":"","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"Qwen2.5-Omni-3B","top_percent":15.05,"top_model_id":"qwen2.5-omni-3b","top_generation":"Qwen2.5 Omni","top_model_base":"Qwen2.5-Omni-3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":true,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":15.05},{"place":2,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":15.36},{"place":3,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":15.63},{"place":4,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":15.95}]},{"id":"asr-commonvoice-8-ja","name":"ASR Common Voice 8 (Japanese)","topic":"ASR","description":"Japanese automatic speech recognition on the Common Voice 8.0 Japanese test set (character error rate).","url":"","leaderboard":"","github":"","paper":"","metric":"cer","stars":"","top_model":"LFM2.5-Audio-1.5B-JP","top_percent":4.42,"top_model_id":"lfm2.5-audio-1.5b-jp","top_generation":"LFM2.5-Audio","top_model_base":"LFM2.5-Audio 1.5B JP","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":true,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-audio-1.5b-jp","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":4.42},{"place":2,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":8.5},{"place":3,"model":"reazonspeech-nemo-v2","company":"reazon","family":"ReazonSpeech","version":"ReazonSpeech v2","score":9.1},{"place":4,"model":"distil-whisper-large-v3-ja-reazonspeech-all","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":9.2},{"place":5,"model":"distil-whisper-large-v3-ja-reazonspeech-large","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":9.4},{"place":6,"model":"whisper-large-v2","company":"openai","family":"Whisper","version":"Whisper v2","score":9.7},{"place":7,"model":"whisper-large","company":"openai","family":"Whisper","version":"Whisper","score":10},{"place":8,"model":"distil-whisper-large-v3-ja-reazonspeech-medium","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":10.9},{"place":9,"model":"whisper-medium","company":"openai","family":"Whisper","version":"Whisper","score":11.5},{"place":10,"model":"whisper-small","company":"openai","family":"Whisper","version":"Whisper","score":15.1},{"place":11,"model":"whisper-base","company":"openai","family":"Whisper","version":"Whisper","score":28.6},{"place":12,"model":"distil-whisper-large-v3-ja-reazonspeech-small","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":30.2},{"place":13,"model":"whisper-tiny","company":"openai","family":"Whisper","version":"Whisper","score":53.7},{"place":14,"model":"distil-whisper-large-v3-ja-reazonspeech-tiny","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":94.8}]},{"id":"asr-earnings22","name":"ASR Earnings22","topic":"ASR","description":"Automatic speech recognition benchmark on Earnings22 financial calls.","url":"","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"Whisper-large-V3","top_percent":11.29,"top_model_id":"whisper-large-v3","top_generation":"Whisper v3","top_model_base":"Whisper Large V3","top_model_family":"Whisper","top_company":"openai","top_open_source":1,"lower_is_better":true,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":11.29},{"place":2,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":14.56},{"place":3,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":14.81},{"place":4,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":19.75}]},{"id":"asr-gigaspeech","name":"ASR GigaSpeech","topic":"ASR","description":"Automatic speech recognition benchmark on GigaSpeech.","url":"","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"Whisper-large-V3","top_percent":10.02,"top_model_id":"whisper-large-v3","top_generation":"Whisper v3","top_model_base":"Whisper Large V3","top_model_family":"Whisper","top_company":"openai","top_open_source":1,"lower_is_better":true,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":10.02},{"place":2,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":10.47},{"place":3,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":10.63},{"place":4,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":11.76}]},{"id":"asr-jsut-basic5000","name":"ASR JSUT Basic5000","topic":"ASR","description":"Japanese automatic speech recognition on JSUT basic5000 (character error rate).","url":"","leaderboard":"","github":"","paper":"","metric":"cer","stars":"","top_model":"Whisper-large-V3","top_percent":7.1,"top_model_id":"whisper-large-v3","top_generation":"Whisper v3","top_model_base":"Whisper Large V3","top_model_family":"Whisper","top_company":"openai","top_open_source":1,"lower_is_better":true,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":7.1},{"place":2,"model":"reazonspeech-nemo-v2","company":"reazon","family":"ReazonSpeech","version":"ReazonSpeech v2","score":7.4},{"place":3,"model":"lfm2.5-audio-1.5b-jp","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":8.07},{"place":4,"model":"whisper-large-v2","company":"openai","family":"Whisper","version":"Whisper v2","score":8.2},{"place":5,"model":"distil-whisper-large-v3-ja-reazonspeech-all","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":8.4},{"place":6,"model":"distil-whisper-large-v3-ja-reazonspeech-large","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":8.5},{"place":7,"model":"whisper-large","company":"openai","family":"Whisper","version":"Whisper","score":8.9},{"place":8,"model":"whisper-medium","company":"openai","family":"Whisper","version":"Whisper","score":10},{"place":9,"model":"distil-whisper-large-v3-ja-reazonspeech-medium","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":11.3},{"place":10,"model":"whisper-small","company":"openai","family":"Whisper","version":"Whisper","score":14.2},{"place":11,"model":"whisper-base","company":"openai","family":"Whisper","version":"Whisper","score":24.9},{"place":12,"model":"whisper-tiny","company":"openai","family":"Whisper","version":"Whisper","score":36.5},{"place":13,"model":"distil-whisper-large-v3-ja-reazonspeech-small","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":39},{"place":14,"model":"distil-whisper-large-v3-ja-reazonspeech-tiny","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":96.3}]},{"id":"asr-librispeech-clean","name":"ASR LibriSpeech Clean","topic":"ASR","description":"Automatic speech recognition benchmark on LibriSpeech clean split.","url":"","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"Qwen3-Omni-30B-A3B-Instruct","top_percent":1.22,"top_model_id":"qwen3-omni-30b-a3b-instruct","top_generation":"Qwen3","top_model_base":"Qwen3 Omni 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":true,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1.22},{"place":2,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":1.39},{"place":3,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":1.41},{"place":4,"model":"qwen2-audio-7b","company":"qwen","family":"Qwen","version":"Qwen2-Audio","score":1.6},{"place":5,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":1.63},{"place":6,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":1.7},{"place":7,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":1.74},{"place":8,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":1.93},{"place":9,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":1.95},{"place":10,"model":"qwen-audio","company":"qwen","family":"Qwen","version":"Qwen-Audio","score":2},{"place":11,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":2.01},{"place":12,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":2.03},{"place":13,"model":"salmonn-13b","company":"tsinghua","family":"SALMONN","version":"SALMONN","score":2.1},{"place":14,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":2.14},{"place":15,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.89}]},{"id":"asr-librispeech-other","name":"ASR LibriSpeech Other","topic":"ASR","description":"Automatic speech recognition benchmark on LibriSpeech other split.","url":"","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"Ming-flash-omni 2.0","top_percent":2.2,"top_model_id":"ming-flash-omni-2.0","top_generation":"Ming 2.0","top_model_base":"Ming-flash-omni 2.0","top_model_family":"Ming","top_company":"antgroup","top_open_source":1,"lower_is_better":true,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":2.2},{"place":2,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":2.48},{"place":3,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":3.19},{"place":4,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":3.42},{"place":5,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":3.45},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.56},{"place":7,"model":"qwen2-audio-7b","company":"qwen","family":"Qwen","version":"Qwen2-Audio","score":3.6},{"place":8,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":3.75},{"place":9,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":3.91},{"place":10,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":4.01},{"place":11,"model":"qwen-audio","company":"qwen","family":"Qwen","version":"Qwen-Audio","score":4.2},{"place":12,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":4.3},{"place":13,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":4.39},{"place":14,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":4.4},{"place":15,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":4.47},{"place":16,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":4.52},{"place":17,"model":"salmonn-13b","company":"tsinghua","family":"SALMONN","version":"SALMONN","score":4.9}]},{"id":"asr-reazonspeech","name":"ASR ReazonSpeech","topic":"ASR","description":"Japanese automatic speech recognition on the ReazonSpeech held-out test set (character error rate).","url":"","leaderboard":"","github":"","paper":"","metric":"cer","stars":"","top_model":"ReazonSpeech-NeMo-v2","top_percent":11.2,"top_model_id":"reazonspeech-nemo-v2","top_generation":"ReazonSpeech v2","top_model_base":"ReazonSpeech NeMo v2","top_model_family":"ReazonSpeech","top_company":"reazon","top_open_source":1,"lower_is_better":true,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"reazonspeech-nemo-v2","company":"reazon","family":"ReazonSpeech","version":"ReazonSpeech v2","score":11.2},{"place":2,"model":"distil-whisper-large-v3-ja-reazonspeech-all","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":11.6},{"place":3,"model":"distil-whisper-large-v3-ja-reazonspeech-large","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":12.2},{"place":4,"model":"distil-whisper-large-v3-ja-reazonspeech-medium","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":14.8},{"place":5,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":14.9},{"place":6,"model":"lfm2.5-audio-1.5b-jp","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":24.24},{"place":7,"model":"whisper-large-v2","company":"openai","family":"Whisper","version":"Whisper v2","score":28.1},{"place":8,"model":"whisper-medium","company":"openai","family":"Whisper","version":"Whisper","score":33.2},{"place":9,"model":"whisper-large","company":"openai","family":"Whisper","version":"Whisper","score":34.1},{"place":10,"model":"distil-whisper-large-v3-ja-reazonspeech-small","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":40.7},{"place":11,"model":"whisper-small","company":"openai","family":"Whisper","version":"Whisper","score":41.5},{"place":12,"model":"whisper-base","company":"openai","family":"Whisper","version":"Whisper","score":70.4},{"place":13,"model":"distil-whisper-large-v3-ja-reazonspeech-tiny","company":"japanese-asr","family":"Whisper","version":"distil-whisper-large-v3","score":96.7},{"place":14,"model":"whisper-tiny","company":"openai","family":"Whisper","version":"Whisper","score":137.9}]},{"id":"asr-spgispeech","name":"ASR SPGISpeech","topic":"ASR","description":"Automatic speech recognition benchmark on SPGISpeech.","url":"","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"LFM2.5-Audio-1.5B","top_percent":2.76,"top_model_id":"lfm2.5-audio-1.5b","top_generation":"LFM2.5-Audio","top_model_base":"LFM2.5-Audio 1.5B","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":true,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":2.76},{"place":2,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":2.94},{"place":3,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":3.24},{"place":4,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":4.17}]},{"id":"asr-ted-lium","name":"ASR TED-LIUM","topic":"ASR","description":"Automatic speech recognition benchmark on TED-LIUM.","url":"","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"LFM2.5-Audio-1.5B","top_percent":3.47,"top_model_id":"lfm2.5-audio-1.5b","top_generation":"LFM2.5-Audio","top_model_base":"LFM2.5-Audio 1.5B","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":true,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":3.47},{"place":2,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":3.56},{"place":3,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":3.86},{"place":4,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":5.08}]},{"id":"asr-voxpopuli","name":"ASR VoxPopuli","topic":"ASR","description":"Automatic speech recognition benchmark on VoxPopuli.","url":"","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"Qwen2.5-Omni-3B","top_percent":5.6,"top_model_id":"qwen2.5-omni-3b","top_generation":"Qwen2.5 Omni","top_model_base":"Qwen2.5-Omni-3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":true,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":5.6},{"place":2,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":7.13},{"place":3,"model":"whisper-large-v3","company":"openai","family":"Whisper","version":"Whisper v3","score":9.54},{"place":4,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":9.93}]},{"id":"astabench","name":"AstaBench","topic":"Agent evaluation","description":"Evaluates science agents across literature understanding, data analysis, planning, tool use, coding, and search.","url":"","leaderboard":"https://huggingface.co/spaces/allenai/asta-bench-leaderboard","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":58,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":27,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":58},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":55.3},{"place":3,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":54.5},{"place":4,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":53},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":52.9},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":49.6},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":46.5},{"place":8,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":43.3},{"place":9,"model":"o3","company":"openai","family":"o3","version":"o3","score":39.8},{"place":10,"model":"o3","company":"openai","family":"o3","version":"o3","score":37.8},{"place":11,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":37.5},{"place":12,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":33},{"place":13,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":31.5},{"place":14,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":25.7},{"place":15,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":20.3},{"place":16,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":16.2},{"place":17,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":16},{"place":18,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":12.4},{"place":19,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":2.6},{"place":20,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":2.4},{"place":21,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":2.3},{"place":22,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.2},{"place":23,"model":"gemini-2.5-flash-2024-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.1},{"place":24,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1.9},{"place":25,"model":"youcom-search-api","company":"you.com","family":"You.com","version":"You.com","score":1.6},{"place":26,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":1.6},{"place":27,"model":"gpt-5-mini-2025-08","company":"openai","family":"GPT","version":"GPT-5","score":1.1},{"place":28,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":1.1},{"place":29,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":0.5}]},{"id":"attaq","name":"AttaQ","topic":"Safety / jailbreak","description":"Adversarial jailbreak suite measuring refusal robustness against targeted attack prompts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Granite 3.3 8B Instruct","top_percent":88.5,"top_model_id":"granite-3.3-8b-instruct","top_generation":"Granite 3.3","top_model_base":"Granite 3.3 8B","top_model_family":"Granite","top_company":"IBM","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":88.5},{"place":2,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":87.47},{"place":3,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":86.64},{"place":4,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":86.1},{"place":5,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":86.05},{"place":6,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":85.76},{"place":7,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":85.73},{"place":8,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":84.7},{"place":9,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":84.7},{"place":10,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":83.72},{"place":11,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":83.72},{"place":12,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":83.43},{"place":13,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":83.23},{"place":14,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.9},{"place":15,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":81.88},{"place":16,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":81.19},{"place":17,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":42.87},{"place":18,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":42.45}]},{"id":"audio-multichallenge","name":"Audio MultiChallenge","topic":"Spoken multi-turn conversation","description":"Scale AI Audio MultiChallenge: multi-turn spoken conversation benchmark; average pass rate (APR).","url":"https://thinkingmachines.ai/blog/interaction-models/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.8 Flash","top_percent":71.9,"top_model_id":"gemini-3.8-flash","top_generation":"Gemini 3.8","top_model_base":"Gemini 3.8 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":71.9},{"place":2,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":71.5},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":67},{"place":4,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.4},{"place":5,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":60.4},{"place":6,"model":"launa-omni-1","company":"salesforce","family":"Launa","version":"Launa-Omni","score":59.69},{"place":7,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":58.41},{"place":8,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":57.9},{"place":9,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":57.6},{"place":10,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":56.6},{"place":11,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":54.87},{"place":12,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":49.3},{"place":13,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":48.5},{"place":14,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":48.5},{"place":15,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":48.45},{"place":16,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":43.4},{"place":17,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":43.36},{"place":18,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":37.61},{"place":19,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":37.6},{"place":20,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":36.1},{"place":21,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":36.06},{"place":22,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":34.73},{"place":23,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":34.7},{"place":24,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":26.8},{"place":25,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":26.77},{"place":26,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":24.34},{"place":27,"model":"gpt-4o-audio-preview-2025-06-03","company":"openai","family":"GPT","version":"GPT-4o","score":23.23},{"place":28,"model":"gemini-2.5-flash-native-audio-preview-12-2025-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.46},{"place":29,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":20.35},{"place":30,"model":"gpt-realtime-mini-2025-12-15","company":"openai","family":"GPT","version":"GPT Realtime","score":13.94},{"place":31,"model":"gemini-2.5-flash-native-audio-preview-12-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":13.9},{"place":32,"model":"gpt-4o-mini-audio-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o","score":13.05},{"place":33,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":10.4},{"place":34,"model":"mimo-audio-7b-instruct","company":"xiaomi","family":"MiMo","version":"MiMo-Audio","score":10.1},{"place":35,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":9.29},{"place":36,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":8.08},{"place":37,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":8.08},{"place":38,"model":"glm-4-voice","company":"zai","family":"GLM","version":"GLM-4","score":6.06},{"place":39,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":1.01}]},{"id":"autocodebench","name":"AutoCodeBench","topic":"Autonomous coding","description":"End-to-end autonomous coding benchmark with unit-test based execution across diverse repositories and tasks.","url":"https://autocodebench.github.io/","leaderboard":"https://autocodebench.github.io/leaderboard.html","github":"https://github.com/Tencent-Hunyuan/AutoCodeBenchmark","paper":"https://arxiv.org/abs/2508.09101","metric":"percent","stars":"","top_model":"Claude Opus 4 (Thinking)","top_percent":52.4,"top_model_id":"claude-opus-4-thinking","top_generation":"Claude 4","top_model_base":"Claude Opus 4","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":45,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":52.4},{"place":2,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":51.1},{"place":3,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":51.1},{"place":4,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":50.9},{"place":5,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":50.9},{"place":6,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":50.2},{"place":7,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":50},{"place":8,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":49.3},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.7},{"place":10,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":48.1},{"place":11,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":48},{"place":12,"model":"kimi-k2-instruct-0711","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":47.8},{"place":13,"model":"kimi-k2-0711-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":47.8},{"place":14,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.7},{"place":15,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":46.6},{"place":16,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":45.9},{"place":17,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":45.7},{"place":18,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":45.3},{"place":19,"model":"seed1.6-enabled","company":"bytedance","family":"Seed","version":"Seed 1.6","score":45.3},{"place":20,"model":"seed1.6-thinking","company":"bytedance","family":"Seed","version":"Seed 1.6","score":45},{"place":21,"model":"seed1.6-thinking-250715","company":"bytedance","family":"Seed","version":"Seed 1.6","score":45},{"place":22,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":44.8},{"place":23,"model":"seed1.6-thinking","company":"bytedance","family":"Seed","version":"Seed 1.6","score":44.7},{"place":24,"model":"hunyuan-turbos","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":43.8},{"place":25,"model":"hunyuan-turbos-20250716","company":"tencent","family":"Hunyuan","version":"Hunyuan TurboS","score":43.8},{"place":26,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":43.1},{"place":27,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":42.9},{"place":28,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":41.7},{"place":29,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":41.1},{"place":30,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":40.8},{"place":31,"model":"ernie-x1","company":"baidu","family":"ERNIE","version":"ERNIE X1","score":39.6},{"place":32,"model":"ernie-x1-turbo-32k","company":"baidu","family":"ERNIE","version":"ERNIE X1","score":39.6},{"place":33,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":37.7},{"place":34,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.6},{"place":35,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.8},{"place":36,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.3},{"place":37,"model":"hunyuan-coder-b8-preview","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":33.4},{"place":38,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":32.3},{"place":39,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":31},{"place":40,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.6},{"place":41,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":28.5},{"place":42,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.5},{"place":43,"model":"qwen3-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":24.3},{"place":44,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.3},{"place":45,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":22.5},{"place":46,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":20.5},{"place":47,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":19.3}]},{"id":"autocodebench-lite","name":"AutoCodeBench-Lite","topic":"Autonomous coding","description":"Lite version of AutoCodeBench focusing on smaller tasks with the same end-to-end, unit-test-based evaluation.","url":"https://autocodebench.github.io/","leaderboard":"https://autocodebench.github.io/leaderboard.html","github":"https://github.com/Tencent-Hunyuan/AutoCodeBenchmark","paper":"https://arxiv.org/abs/2508.09101","metric":"percent","stars":"","top_model":"Claude Opus 4","top_percent":64.5,"top_model_id":"claude-opus-4","top_generation":"Claude 4","top_model_base":"Claude Opus 4","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":46,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":64.5},{"place":2,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":64.5},{"place":3,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":63.2},{"place":4,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":63},{"place":5,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":62},{"place":6,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":62},{"place":7,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":61.7},{"place":8,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":61.5},{"place":9,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":61.5},{"place":10,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":60.5},{"place":11,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":59.8},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.1},{"place":13,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":57.3},{"place":14,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.3},{"place":15,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":56.9},{"place":16,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":56.9},{"place":17,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":56.8},{"place":18,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":56.8},{"place":19,"model":"kimi-k2-0711-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":55.4},{"place":20,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":55},{"place":21,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.7},{"place":22,"model":"seed1.6-thinking-250715","company":"bytedance","family":"Seed","version":"Seed 1.6","score":53.9},{"place":23,"model":"seed1.6-enabled","company":"bytedance","family":"Seed","version":"Seed 1.6","score":53.2},{"place":24,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.9},{"place":25,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":51.5},{"place":26,"model":"seed1.6-thinking","company":"bytedance","family":"Seed","version":"Seed 1.6","score":51.2},{"place":27,"model":"hunyuan-turbos-20250716","company":"tencent","family":"Hunyuan","version":"Hunyuan TurboS","score":50.3},{"place":28,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49.8},{"place":29,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":48.8},{"place":30,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":47.6},{"place":31,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":46.2},{"place":32,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":45.8},{"place":33,"model":"ernie-x1-turbo-32k","company":"baidu","family":"ERNIE","version":"ERNIE X1","score":44.4},{"place":34,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":40.7},{"place":35,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":40.5},{"place":36,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37},{"place":37,"model":"hunyuan-coder-b8-preview","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":36.4},{"place":38,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.1},{"place":39,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":32.7},{"place":40,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":32.3},{"place":41,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":28.9},{"place":42,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.8},{"place":43,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":27.7},{"place":44,"model":"qwen3-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":23.2},{"place":45,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":21.5},{"place":46,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.4},{"place":47,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":20.5},{"place":48,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":20.1}]},{"id":"autologi","name":"AutoLogi","topic":"Logical reasoning","description":"AutoLogi benchmark evaluating automated logical reasoning accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4","top_percent":89.8,"top_model_id":"claude-sonnet-4","top_generation":"Claude 4","top_model_base":"Claude Sonnet 4","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":89.8},{"place":2,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.5},{"place":3,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":88.9},{"place":4,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":88.2},{"place":5,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":86.1},{"place":6,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.1},{"place":7,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.3}]},{"id":"automationbench","name":"AutomationBench","topic":"Agentic business workflows","description":"Zapier benchmark of end-to-end business workflows via REST APIs across 47 simulated apps; pass/fail on deterministic state assertions.","url":"https://arxiv.org/abs/2604.18934","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniMax M3.1 Flash (max)","top_percent":62.8,"top_model_id":"minimax-m3.1-flash-max","top_generation":"MiniMax M3.1","top_model_base":"MiniMax M3.1 Flash","top_model_family":"MiniMax","top_company":"minimax","top_open_source":1,"lower_is_better":false,"bench_models":72,"total_models":3854,"placements":[{"place":1,"model":"minimax-m3.1-flash-max","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":62.8},{"place":2,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":62.2},{"place":3,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":60.5},{"place":4,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":58.7},{"place":5,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":54.8},{"place":6,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":54.7},{"place":7,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":54.2},{"place":8,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":53.8},{"place":9,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":53.1},{"place":10,"model":"minimax-m3.1-flash-low","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":52.8},{"place":11,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":52.5},{"place":12,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":52.5},{"place":13,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":52.3},{"place":14,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":52.3},{"place":15,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":51.3},{"place":16,"model":"qwen3.8-max-0902","company":"qwen","family":"Qwen","version":"Qwen3.8","score":50.8},{"place":17,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":50.3},{"place":18,"model":"nex-n2.5-max","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":50.2},{"place":19,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":49.7},{"place":20,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":49.6},{"place":21,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":49.4},{"place":22,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":49.2},{"place":23,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":48.8},{"place":24,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":48.8},{"place":25,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":48.7},{"place":26,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":48.2},{"place":27,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":46.7},{"place":28,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.7},{"place":29,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":46.2},{"place":30,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":45.9},{"place":31,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":45.8},{"place":32,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":45.7},{"place":33,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":45.5},{"place":34,"model":"holo4-27b","company":"hcompany","family":"Holo","version":"Holo4","score":45.4},{"place":35,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":44.7},{"place":36,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":44.2},{"place":37,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":43.5},{"place":38,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":43.2},{"place":39,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":42.5},{"place":40,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":41.7},{"place":41,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":41.4},{"place":42,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":41},{"place":43,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":40.3},{"place":44,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":40},{"place":45,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":39.8},{"place":46,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":39.3},{"place":47,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.8},{"place":48,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":38.3},{"place":49,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":38.2},{"place":50,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.7},{"place":51,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":37.2},{"place":52,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":37},{"place":53,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":36.2},{"place":54,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":36.1},{"place":55,"model":"holo4-35b-a3b","company":"hcompany","family":"Holo","version":"Holo4","score":34.5},{"place":56,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":33.2},{"place":57,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":32.3},{"place":58,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":32.1},{"place":59,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":32.1},{"place":60,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":32},{"place":61,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":32},{"place":62,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":31.8},{"place":63,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":31.4},{"place":64,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":30.8},{"place":65,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":30.4},{"place":66,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":30.4},{"place":67,"model":"mimo-v2.6-distill-qwen-9b","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":30.3},{"place":68,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":29.7},{"place":69,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":29.7},{"place":70,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":29.1},{"place":71,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":28.8},{"place":72,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":28},{"place":73,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":27.69},{"place":74,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":27.6},{"place":75,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":27.3},{"place":76,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":27.2},{"place":77,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":26.9},{"place":78,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":26.2},{"place":79,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":26},{"place":80,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":25.7},{"place":81,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":25.1},{"place":82,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":24.9},{"place":83,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":23.6},{"place":84,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":22.7},{"place":85,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":20.7},{"place":86,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":19.6},{"place":87,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":18.5},{"place":88,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":18.1},{"place":89,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":17.4},{"place":90,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":17.1},{"place":91,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":17},{"place":92,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":17},{"place":93,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":17},{"place":94,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":16.1},{"place":95,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":16},{"place":96,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":15.5},{"place":97,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":15.2},{"place":98,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":15.2},{"place":99,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":14.9},{"place":100,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":14.8},{"place":101,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":14.5},{"place":102,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":14.2},{"place":103,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":13.5},{"place":104,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":12.9},{"place":105,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":12.9},{"place":106,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":12.8},{"place":107,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":10.8},{"place":108,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":10.7},{"place":109,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":9.9},{"place":110,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":9.7},{"place":111,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":9.6},{"place":112,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":8.72},{"place":113,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":7.5},{"place":114,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":5.7},{"place":115,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":5.46},{"place":116,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":5.3},{"place":117,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5},{"place":118,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":2.61},{"place":119,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":2.2}]},{"id":"automationbench-partial","name":"AutomationBench (partial credit)","topic":"Business workflows","description":"AutomationBench end-to-end business workflows scored with partial credit per task.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":81.2,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":81.2},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.2},{"place":3,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":70},{"place":4,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":69.1},{"place":5,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.7},{"place":6,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":58},{"place":7,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":47.4},{"place":8,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.4},{"place":9,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":27.9},{"place":10,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":14.7}]},{"id":"babe","name":"BABE","topic":"STEM reasoning","description":"STEM reasoning benchmark evaluating broad applied and basic engineering knowledge.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2 (high)","top_percent":58.1,"top_model_id":"gpt-5.2-high","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":58.1},{"place":2,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":57.9},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":55.2},{"place":4,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":53.5},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.3},{"place":6,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":50.2},{"place":7,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":50},{"place":8,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":49.3},{"place":9,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":49.2},{"place":10,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":49},{"place":11,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.7},{"place":12,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":40.4}]},{"id":"babyvision","name":"BabyVision","topic":"Visual reasoning","description":"Visual reasoning benchmark testing basic visual perception and understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":91.3,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":71,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.3},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.5},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":88.9},{"place":4,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":85.6},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":83.6},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":81.2},{"place":7,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":76.3},{"place":8,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":73.7},{"place":9,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":70.9},{"place":10,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":70.4},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":68.3},{"place":12,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.7},{"place":13,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":62.9},{"place":14,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":61.6},{"place":15,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":60.6},{"place":16,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":57.5},{"place":17,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":55.9},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":55.9},{"place":19,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.4},{"place":20,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":53.4},{"place":21,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":53.4},{"place":22,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":53.1},{"place":23,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.3},{"place":24,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":52.3},{"place":25,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":51.6},{"place":26,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":51.5},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":51.3},{"place":28,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":51.3},{"place":29,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":50},{"place":30,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":49.7},{"place":31,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":49.7},{"place":32,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":47.7},{"place":33,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":47.2},{"place":34,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":46.8},{"place":35,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":46.8},{"place":36,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.6},{"place":37,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.2},{"place":38,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":39.9},{"place":39,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":39.8},{"place":40,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":39.1},{"place":41,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.4},{"place":42,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37.4},{"place":43,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":36.5},{"place":44,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":36.5},{"place":45,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.7},{"place":46,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35.1},{"place":47,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":34.51},{"place":48,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":34.4},{"place":49,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":33.25},{"place":50,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":30.93},{"place":51,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":29.6},{"place":52,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":28.9},{"place":53,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":28.87},{"place":54,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":28.87},{"place":55,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.6},{"place":56,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":28.09},{"place":57,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":27.1},{"place":58,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":26.8},{"place":59,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":24.7},{"place":60,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":22.2},{"place":61,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":22.2},{"place":62,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":22.2},{"place":63,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":20.9},{"place":64,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":20.9},{"place":65,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":19.6},{"place":66,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":18.8},{"place":67,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":18.6},{"place":68,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":18.6},{"place":69,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":18.3},{"place":70,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":17.5},{"place":71,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":17.4},{"place":72,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":16.75},{"place":73,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":16.24},{"place":74,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":16.24},{"place":75,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":16},{"place":76,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":16},{"place":77,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":15.98},{"place":78,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":15.72},{"place":79,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":14.95},{"place":80,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":14.8},{"place":81,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":14.4},{"place":82,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":14.4},{"place":83,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":14.2},{"place":84,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":13.92},{"place":85,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":13.66},{"place":86,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":12.89},{"place":87,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":12.89},{"place":88,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":12.6},{"place":89,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":11.9},{"place":90,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":11.3}]},{"id":"babyvision-with-tools","name":"BabyVision (With Tools)","topic":"Visual reasoning","description":"BabyVision visual perception benchmark evaluated with tool access in an agent harness.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":97.68,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97.68},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":97.16},{"place":3,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":95.36},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":94.1},{"place":5,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":92.5},{"place":6,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":91},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.5},{"place":8,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":89.6},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":88.9},{"place":10,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":85.7},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":83.6},{"place":12,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":83.25},{"place":13,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":81.2},{"place":14,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":80.2},{"place":15,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":80.2},{"place":16,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":68.5},{"place":17,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":68.3},{"place":18,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":40.5},{"place":19,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":38.4},{"place":20,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":34.2}]},{"id":"balrog","name":"BALROG","topic":"Agent robustness","description":"Benchmark for assessing LLM agents under adversarial and out-of-distribution tool-use scenarios.","url":"https://balrogai.com/","leaderboard":"","github":"https://github.com/balrog-ai/BALROG","paper":"https://arxiv.org/abs/2411.13543","metric":"percent","stars":"","top_model":"Grok 4","top_percent":43.6,"top_model_id":"grok-4","top_generation":"Grok 4","top_model_base":"Grok 4","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":false,"bench_models":27,"total_models":3854,"placements":[{"place":1,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":43.6},{"place":2,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":43.3},{"place":3,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":34.9},{"place":4,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.5},{"place":5,"model":"gpt-5-minimal-think","company":"openai","family":"GPT","version":"GPT-5","score":32.8},{"place":6,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":32.6},{"place":7,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":32.3},{"place":8,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":29.5},{"place":9,"model":"reka-flash-3","company":"reka","family":"Reka Flash","version":"Reka Flash","score":29.2},{"place":10,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":27.9},{"place":11,"model":"llama-3.2-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":27.3},{"place":12,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":23},{"place":13,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":21},{"place":14,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":19.5},{"place":15,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":19.3},{"place":16,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":17.6},{"place":17,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":17.4},{"place":18,"model":"llama-3.2-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":16.8},{"place":19,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":16.2},{"place":20,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":15.1},{"place":21,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":14.6},{"place":22,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":12.8},{"place":23,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":11.6},{"place":24,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":10.1},{"place":25,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.8},{"place":26,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":6.6},{"place":27,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":3.7}]},{"id":"bankertoolbench","name":"BankerToolBench","topic":"Investment banking agent tasks","description":"BankerToolBench: tool-using agent tasks modeled on investment-banking workflows, scored with dataset rubrics.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":81.9,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.9},{"place":2,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":81.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":79},{"place":4,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":78.6},{"place":5,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":77.8},{"place":6,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":76.2},{"place":7,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":76.1},{"place":8,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":74.7},{"place":9,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":73.5},{"place":10,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.1},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":70},{"place":12,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":68.8},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":67},{"place":14,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":63.9}]},{"id":"banking77","name":"BANKING77","topic":"Intent classification","description":"Bank customer intent among 77 classes; macro-F1 (Jev Decision Index suite, posed as typed decisions).","url":"https://github.com/PolyAI-LDN/task-specific-datasets","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"https://arxiv.org/abs/2003.04807","metric":"f1","stars":"","top_model":"Clef-Omni","top_percent":94.8,"top_model_id":"clef-omni","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":94.8},{"place":2,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":94.2},{"place":3,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":92.8},{"place":4,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":92.7},{"place":5,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":92.2},{"place":6,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":92},{"place":7,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":91.3},{"place":8,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":91},{"place":9,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":90.9},{"place":10,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":90.3},{"place":11,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":90.1},{"place":12,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":90},{"place":13,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":88.1},{"place":14,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":88},{"place":15,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":88},{"place":16,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":84.8},{"place":17,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":84},{"place":18,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":83.7},{"place":19,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":83.7},{"place":20,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":80.4},{"place":21,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":79.9},{"place":22,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":79.7},{"place":23,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":79.6},{"place":24,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":79.5},{"place":25,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":78.5},{"place":26,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":78.3},{"place":27,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":74.3},{"place":28,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":74.2},{"place":29,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":72},{"place":30,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":71.6},{"place":31,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":69.4},{"place":32,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":65.6},{"place":33,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":62.6},{"place":34,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":14.3},{"place":35,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":12.9},{"place":36,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":11.8}]},{"id":"bbh","name":"BBH","topic":"Multi-task reasoning","description":"Hard subset of BIG-bench with diverse reasoning tasks.","url":"https://github.com/suzgunmirac/BIG-bench-Hard","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2210.09261","metric":"percent","stars":"510","top_model":"ERNIE 4.5 424B A47B","top_percent":94.3,"top_model_id":"ernie-4.5","top_generation":"ERNIE 4.5","top_model_base":"ERNIE 4.5 424B","top_model_family":"ERNIE","top_company":"baidu","top_open_source":1,"lower_is_better":false,"bench_models":457,"total_models":3854,"placements":[{"place":1,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":94.3},{"place":2,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.3},{"place":3,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":93.1},{"place":4,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":92.08},{"place":5,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":92},{"place":6,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.1},{"place":7,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":91},{"place":8,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":90.6},{"place":9,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.6},{"place":10,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":89.8},{"place":11,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":89.73},{"place":12,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":89.7},{"place":13,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89.5},{"place":14,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":89.5},{"place":15,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":89.36},{"place":16,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.3},{"place":17,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":89.2},{"place":18,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":89.17},{"place":19,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":89.1},{"place":20,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":89.04},{"place":21,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89},{"place":22,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89},{"place":23,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":88.9},{"place":24,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":88.87},{"place":25,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":88.8},{"place":26,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":88.8},{"place":27,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":88.7},{"place":28,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.7},{"place":29,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.7},{"place":30,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":88.69},{"place":31,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":88.6},{"place":32,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":88.6},{"place":33,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":88.6},{"place":34,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":88.5},{"place":35,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":88.4},{"place":36,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":88.4},{"place":37,"model":"seed1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":88.36},{"place":38,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":88.3},{"place":39,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":88.2},{"place":40,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":88.2},{"place":41,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":88.2},{"place":42,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":88.2},{"place":43,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":88},{"place":44,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":87.82},{"place":45,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.8},{"place":46,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":87.7},{"place":47,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":87.6},{"place":48,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":87.6},{"place":49,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":87.6},{"place":50,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.5},{"place":51,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":87.5},{"place":52,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.5},{"place":53,"model":"glm-5-base","company":"zai","family":"GLM","version":"GLM 5","score":87.4},{"place":54,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.38},{"place":55,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":87.3},{"place":56,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":87.2},{"place":57,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":87.19},{"place":58,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":87.1},{"place":59,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":87.1},{"place":60,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.9},{"place":61,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":86.88},{"place":62,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.8},{"place":63,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":86.8},{"place":64,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86.75},{"place":65,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":86.7},{"place":66,"model":"glm-5.3-flash-base","company":"zai","family":"GLM","version":"GLM 5.3","score":86.6},{"place":67,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":86.6},{"place":68,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.3},{"place":69,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.3},{"place":70,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":86.3},{"place":71,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.22},{"place":72,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":86.22},{"place":73,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":86.2},{"place":74,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":86.2},{"place":75,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.13},{"place":76,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":86.1},{"place":77,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.9},{"place":78,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.9},{"place":79,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":85.78},{"place":80,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":85.7},{"place":81,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.6},{"place":82,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.54},{"place":83,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":85.06},{"place":84,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84.9},{"place":85,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":84.82},{"place":86,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.8},{"place":87,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":84.72},{"place":88,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":84.7},{"place":89,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":84.6},{"place":90,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.52},{"place":91,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.5},{"place":92,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.5},{"place":93,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.4},{"place":94,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":84.3},{"place":95,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":84.1},{"place":96,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":84.1},{"place":97,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.1},{"place":98,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":84},{"place":99,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":83.9},{"place":100,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":83.74},{"place":101,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":83.7},{"place":102,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":83.7},{"place":103,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.68},{"place":104,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":83.62},{"place":105,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.4},{"place":106,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":83.4},{"place":107,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":83.3},{"place":108,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":83.3},{"place":109,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":83.2},{"place":110,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":83.1},{"place":111,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":82.9},{"place":112,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":82.9},{"place":113,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":82.7},{"place":114,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":82.68},{"place":115,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":82.4},{"place":116,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":82.4},{"place":117,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":82.32},{"place":118,"model":"glm-4-0116","company":"zai","family":"GLM","version":"GLM 4","score":82.3},{"place":119,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":82.2},{"place":120,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":82.16},{"place":121,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":82.1},{"place":122,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":82.1},{"place":123,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":82.1},{"place":124,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":82.1},{"place":125,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":82},{"place":126,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":81.8},{"place":127,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":81.62},{"place":128,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":81.6},{"place":129,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":81.55},{"place":130,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.54},{"place":131,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":81.54},{"place":132,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.5},{"place":133,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":81.34},{"place":134,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":81.3},{"place":135,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":81.3},{"place":136,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":81.3},{"place":137,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":81.3},{"place":138,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":81.3},{"place":139,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":81.1},{"place":140,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.07},{"place":141,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":81},{"place":142,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.9},{"place":143,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":80.64},{"place":144,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":80.58},{"place":145,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":80.51},{"place":146,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":80.46},{"place":147,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.4},{"place":148,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":80.4},{"place":149,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.11},{"place":150,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":80.1},{"place":151,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.97},{"place":152,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":79.97},{"place":153,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.8},{"place":154,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":79.76},{"place":155,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":79.76},{"place":156,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":79.7},{"place":157,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79.48},{"place":158,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":79.1},{"place":159,"model":"hy-1.8b","company":"tencent","family":"HY","version":"HY","score":79.08},{"place":160,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":79},{"place":161,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":78.9},{"place":162,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":78.9},{"place":163,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":78.9},{"place":164,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":78.8},{"place":165,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":78.42},{"place":166,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":78.41},{"place":167,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":78.4},{"place":168,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":78.4},{"place":169,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":78.34},{"place":170,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":78.21},{"place":171,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":78.2},{"place":172,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":78.13},{"place":173,"model":"internlm2.5-20b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":77.82},{"place":174,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":77.8},{"place":175,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":77.7},{"place":176,"model":"midm-2.0-base-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":77.7},{"place":177,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.65},{"place":178,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.6},{"place":179,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":77.5},{"place":180,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":77.37},{"place":181,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":77.3},{"place":182,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":77.3},{"place":183,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.21},{"place":184,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":77.1},{"place":185,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.79},{"place":186,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":76.72},{"place":187,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":76.6},{"place":188,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":76.5},{"place":189,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":76.46},{"place":190,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":76.4},{"place":191,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":76.3},{"place":192,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":76.3},{"place":193,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":76.3},{"place":194,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":76.3},{"place":195,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":76},{"place":196,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":75.83},{"place":197,"model":"hy-1.8b-2bit","company":"tencent","family":"HY","version":"HY","score":75.54},{"place":198,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":75.12},{"place":199,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":75.1},{"place":200,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":74.9},{"place":201,"model":"hy-1.8b-int4gptq","company":"tencent","family":"HY","version":"HY","score":74.8},{"place":202,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.8},{"place":203,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":74.8},{"place":204,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.8},{"place":205,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.8},{"place":206,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":74.77},{"place":207,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":74.34},{"place":208,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":74.28},{"place":209,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.17},{"place":210,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":73.8},{"place":211,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":73.7},{"place":212,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.7},{"place":213,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":73.5},{"place":214,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":73.4},{"place":215,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":73.1},{"place":216,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.8},{"place":217,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":72.7},{"place":218,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":72.6},{"place":219,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":72.48},{"place":220,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":72.4},{"place":221,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":72.2},{"place":222,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":72.1},{"place":223,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":72.09},{"place":224,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":72},{"place":225,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":71.9},{"place":226,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":71.89},{"place":227,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":71.86},{"place":228,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":71.74},{"place":229,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":71.7},{"place":230,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":71.7},{"place":231,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":71.6},{"place":232,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":71.56},{"place":233,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":71.5},{"place":234,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":71.36},{"place":235,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":71.2},{"place":236,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":71.1},{"place":237,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":71.02},{"place":238,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":71},{"place":239,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":70.97},{"place":240,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.95},{"place":241,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":70.7},{"place":242,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":70.68},{"place":243,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":70.5},{"place":244,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.47},{"place":245,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.4},{"place":246,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":70.3},{"place":247,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":70.2},{"place":248,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":70.1},{"place":249,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":70.1},{"place":250,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":70.1},{"place":251,"model":"internlm2.5-7b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":70.1},{"place":252,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":69.87},{"place":253,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":69.8},{"place":254,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.67},{"place":255,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":69.6},{"place":256,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":69.6},{"place":257,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":69.54},{"place":258,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69.4},{"place":259,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":69.4},{"place":260,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":69.39},{"place":261,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":69.36},{"place":262,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.3},{"place":263,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":69.3},{"place":264,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":69.2},{"place":265,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":69.15},{"place":266,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":69.13},{"place":267,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.1},{"place":268,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":69},{"place":269,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.8},{"place":270,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":68.8},{"place":271,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":68.8},{"place":272,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.72},{"place":273,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":68.7},{"place":274,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":68.6},{"place":275,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":68.5},{"place":276,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":68.4},{"place":277,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":68.3},{"place":278,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":68.3},{"place":279,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":68.2},{"place":280,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":68.2},{"place":281,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":67.9},{"place":282,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":67.8},{"place":283,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":67.79},{"place":284,"model":"rnd1-base-0910","company":"radicalnumerics","family":"RND1","version":"RND1","score":67.5},{"place":285,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.4},{"place":286,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":67.39},{"place":287,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":67.38},{"place":288,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":67.31},{"place":289,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.2},{"place":290,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":67},{"place":291,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":66.9},{"place":292,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.8},{"place":293,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":66.34},{"place":294,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.32},{"place":295,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":66.2},{"place":296,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":66.1},{"place":297,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":66},{"place":298,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":66},{"place":299,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":66},{"place":300,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":65.99},{"place":301,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":65.9},{"place":302,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":65.8},{"place":303,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":65.7},{"place":304,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":65.7},{"place":305,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":65.6},{"place":306,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":65.6},{"place":307,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":65.5},{"place":308,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":65.2},{"place":309,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":65.2},{"place":310,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":65},{"place":311,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":65},{"place":312,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":64.91},{"place":313,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":64.9},{"place":314,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":64.9},{"place":315,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":64.9},{"place":316,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":64.88},{"place":317,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":64.4},{"place":318,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":64.39},{"place":319,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":64.2},{"place":320,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":64.1},{"place":321,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":63.91},{"place":322,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":63.5},{"place":323,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":63.2},{"place":324,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":63.17},{"place":325,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":63.09},{"place":326,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":63},{"place":327,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":62.9},{"place":328,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":62.8},{"place":329,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":62.6},{"place":330,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":62.58},{"place":331,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.47},{"place":332,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":62.3},{"place":333,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":62.28},{"place":334,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":62},{"place":335,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":62},{"place":336,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":61.82},{"place":337,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":61.59},{"place":338,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":61.5},{"place":339,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":61.4},{"place":340,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":61.39},{"place":341,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":61.3},{"place":342,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":61.2},{"place":343,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":61.2},{"place":344,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":61.2},{"place":345,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":61.1},{"place":346,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":61},{"place":347,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":60.9},{"place":348,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":60.8},{"place":349,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":60.4},{"place":350,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":60.3},{"place":351,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":60.3},{"place":352,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":60},{"place":353,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":59.9},{"place":354,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":59.7},{"place":355,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":59.6},{"place":356,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":59.5},{"place":357,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":59.01},{"place":358,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":59},{"place":359,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":58.9},{"place":360,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":58.7},{"place":361,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":58.53},{"place":362,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":58.5},{"place":363,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":58.4},{"place":364,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":58.4},{"place":365,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":58.38},{"place":366,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":58.22},{"place":367,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":58.2},{"place":368,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":58.2},{"place":369,"model":"hy-0.5b","company":"tencent","family":"HY","version":"HY","score":58.1},{"place":370,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":58.09},{"place":371,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":58},{"place":372,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":57.9},{"place":373,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":57.9},{"place":374,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":57.84},{"place":375,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":57.7},{"place":376,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":57.32},{"place":377,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":57.3},{"place":378,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":57.3},{"place":379,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":57},{"place":380,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":56.7},{"place":381,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":56.7},{"place":382,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":56.5},{"place":383,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.3},{"place":384,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":56.2},{"place":385,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":56.12},{"place":386,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":56.1},{"place":387,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":56.1},{"place":388,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":56},{"place":389,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":55.8},{"place":390,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":55.71},{"place":391,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":55.7},{"place":392,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":55.7},{"place":393,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":55.6},{"place":394,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":55.5},{"place":395,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.37},{"place":396,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":55.33},{"place":397,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":55.2},{"place":398,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":55.2},{"place":399,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":55.1},{"place":400,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":55},{"place":401,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":54.98},{"place":402,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.7},{"place":403,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.58},{"place":404,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":54.5},{"place":405,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":54.43},{"place":406,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":54.4},{"place":407,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":54.3},{"place":408,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":54.23},{"place":409,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":54.2},{"place":410,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":54},{"place":411,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":53.77},{"place":412,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":53.76},{"place":413,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":53.72},{"place":414,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":53.7},{"place":415,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":53.7},{"place":416,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":53.69},{"place":417,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":53.6},{"place":418,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.51},{"place":419,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":53.4},{"place":420,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":53.3},{"place":421,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":52.71},{"place":422,"model":"yi-34b-200k","company":"01ai","family":"Yi","version":"Yi","score":52.7},{"place":423,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":52.51},{"place":424,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":52.51},{"place":425,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":52.5},{"place":426,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":52.45},{"place":427,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":52.2},{"place":428,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":52.12},{"place":429,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":51.2},{"place":430,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.07},{"place":431,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":51.06},{"place":432,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":51},{"place":433,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":50.4},{"place":434,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":50.3},{"place":435,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":50.1},{"place":436,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":50},{"place":437,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":49.98},{"place":438,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":49.9},{"place":439,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":49.87},{"place":440,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":49.8},{"place":441,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":49.7},{"place":442,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":49.6},{"place":443,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":49.54},{"place":444,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":49.1},{"place":445,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":49},{"place":446,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":48.98},{"place":447,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":48.9},{"place":448,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":48.8},{"place":449,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":48.78},{"place":450,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":48.58},{"place":451,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":48.3},{"place":452,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":48.1},{"place":453,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":48.1},{"place":454,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.86},{"place":455,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.47},{"place":456,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":47.44},{"place":457,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":47.4},{"place":458,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":47.4},{"place":459,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":47.3},{"place":460,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":47.3},{"place":461,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":47.26},{"place":462,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":47.2},{"place":463,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":47.2},{"place":464,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":47.2},{"place":465,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":47.15},{"place":466,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":47.15},{"place":467,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":46.98},{"place":468,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":46.9},{"place":469,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":46.9},{"place":470,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":46.9},{"place":471,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":46.7},{"place":472,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.55},{"place":473,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":46.47},{"place":474,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":46.4},{"place":475,"model":"exaone-3.5-2.4b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":46.4},{"place":476,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":46.4},{"place":477,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":45.62},{"place":478,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":45.6},{"place":479,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":45.58},{"place":480,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":45.5},{"place":481,"model":"jamba-v0.1","company":"ai21","family":"Jamba","version":"Jamba","score":45.4},{"place":482,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.2},{"place":483,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":45.2},{"place":484,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.1},{"place":485,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":45.02},{"place":486,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":45},{"place":487,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":44.6},{"place":488,"model":"midm-2.0-mini-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":44.5},{"place":489,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":44.3},{"place":490,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":44.1},{"place":491,"model":"llama-2-34b","company":"meta","family":"Llama","version":"Llama 2","score":44.1},{"place":492,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":43.8},{"place":493,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":43.7},{"place":494,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.66},{"place":495,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":43.62},{"place":496,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":43.6},{"place":497,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":43.4},{"place":498,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":43.4},{"place":499,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":43.39},{"place":500,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":43.1},{"place":501,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":43.04},{"place":502,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":43.01},{"place":503,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":42.91},{"place":504,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":42.8},{"place":505,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":42.5},{"place":506,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.41},{"place":507,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":42.4},{"place":508,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":42.3},{"place":509,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":42.2},{"place":510,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":42.2},{"place":511,"model":"yi-6b-200k","company":"01ai","family":"Yi","version":"Yi","score":42},{"place":512,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":41.9},{"place":513,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":41.9},{"place":514,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":41.9},{"place":515,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":41.8},{"place":516,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":41.7},{"place":517,"model":"skywork-13b","company":"skywork","family":"Skywork","version":"Skywork","score":41.7},{"place":518,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":41.7},{"place":519,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":41.6},{"place":520,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":41.56},{"place":521,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":41.5},{"place":522,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":41.47},{"place":523,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":41.4},{"place":524,"model":"internlm2.5-1.8b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":41.16},{"place":525,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":41.06},{"place":526,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":40.9},{"place":527,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":40.4},{"place":528,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":40.2},{"place":529,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":40.2},{"place":530,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":40.1},{"place":531,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":39.86},{"place":532,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":39.81},{"place":533,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":39.6},{"place":534,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":39.52},{"place":535,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":39.5},{"place":536,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":39.45},{"place":537,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":39.3},{"place":538,"model":"minicpm-moe-8x2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":39.22},{"place":539,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":39.19},{"place":540,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":39.16},{"place":541,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39.1},{"place":542,"model":"qwen1.5-moe-a2.7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":39.1},{"place":543,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":38.9},{"place":544,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":38.8},{"place":545,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":38.5},{"place":546,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":38.22},{"place":547,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":38.2},{"place":548,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":38.06},{"place":549,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":38},{"place":550,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":37.93},{"place":551,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":37.92},{"place":552,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":37.9},{"place":553,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":37.9},{"place":554,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":37.89},{"place":555,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.8},{"place":556,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":37.75},{"place":557,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":37.7},{"place":558,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":37.68},{"place":559,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":37.46},{"place":560,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":37.43},{"place":561,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":37.4},{"place":562,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":37.34},{"place":563,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":37.2},{"place":564,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":37.1},{"place":565,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":37.1},{"place":566,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":37},{"place":567,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":36.9},{"place":568,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":36.87},{"place":569,"model":"trlm-135m","company":"loka","family":"TRLM","version":"TRLM","score":36.8},{"place":570,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":36.7},{"place":571,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":36.68},{"place":572,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":36.5},{"place":573,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":36.5},{"place":574,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":36.3},{"place":575,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":36.24},{"place":576,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":36.22},{"place":577,"model":"internlm2-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":36.03},{"place":578,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":35.9},{"place":579,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":35.8},{"place":580,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":35.75},{"place":581,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":35.7},{"place":582,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":35.6},{"place":583,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":35.6},{"place":584,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":35.54},{"place":585,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.3},{"place":586,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":35.3},{"place":587,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":35.3},{"place":588,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":35.2},{"place":589,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":35.2},{"place":590,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.18},{"place":591,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":35},{"place":592,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":34.7},{"place":593,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":34.47},{"place":594,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":34.3},{"place":595,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":34.28},{"place":596,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":33.7},{"place":597,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":33.7},{"place":598,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":33.68},{"place":599,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":33.68},{"place":600,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":33.5},{"place":601,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":33.38},{"place":602,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":33.27},{"place":603,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":33.26},{"place":604,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":33.23},{"place":605,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":33.21},{"place":606,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":32.95},{"place":607,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":32.7},{"place":608,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":32.6},{"place":609,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":32.5},{"place":610,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":32.5},{"place":611,"model":"qwen1.5-4b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":32.5},{"place":612,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":32.48},{"place":613,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":32.38},{"place":614,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":32.2},{"place":615,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":31.8},{"place":616,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":31},{"place":617,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":30.93},{"place":618,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":30.72},{"place":619,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":30.54},{"place":620,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":30.5},{"place":621,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":30.26},{"place":622,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":30},{"place":623,"model":"llama-spark-8b","company":"arcee","family":"Llama Spark","version":"Llama Spark 8B","score":29.77},{"place":624,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":29.2},{"place":625,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":29.1},{"place":626,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":29.07},{"place":627,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":28.94},{"place":628,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":28.82},{"place":629,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":28.8},{"place":630,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":28.78},{"place":631,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":28.77},{"place":632,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":28.5},{"place":633,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":28.4},{"place":634,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":28.2},{"place":635,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":28.2},{"place":636,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":28},{"place":637,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":27.6},{"place":638,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":27.1},{"place":639,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":26.7},{"place":640,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":25.7},{"place":641,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":25},{"place":642,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":24.2},{"place":643,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":22.9},{"place":644,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":21.7},{"place":645,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":20.3},{"place":646,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":19.5},{"place":647,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":18.73},{"place":648,"model":"qwen1.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":18.3},{"place":649,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":18.2},{"place":650,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":13.3},{"place":651,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":12.64},{"place":652,"model":"falcon-e-1b-base","company":"tii","family":"Falcon","version":"Falcon E","score":12.28},{"place":653,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.75},{"place":654,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":7.6},{"place":655,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":6.76},{"place":656,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":5.54},{"place":657,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.706},{"place":658,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.652},{"place":659,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":0}]},{"id":"bbh-decision","name":"BBH (decision)","topic":"Multi-task reasoning","description":"BIG-Bench Hard fixed-option tasks answered directly with no working; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/suzgunmirac/BIG-Bench-Hard","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Jev 1.14","top_percent":93.2,"top_model_id":"jev-1.14","top_generation":"Jev 1.14","top_model_base":"Jev 1.14","top_model_family":"Jev","top_company":"typesafe","top_open_source":0,"lower_is_better":false,"bench_models":39,"total_models":3854,"placements":[{"place":1,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":93.2},{"place":2,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":92.9},{"place":3,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":85.7},{"place":4,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":85.2},{"place":5,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":84.5},{"place":6,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":82.8},{"place":7,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":80.7},{"place":8,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":78.9},{"place":9,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":78.3},{"place":10,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":75.9},{"place":11,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":75.7},{"place":12,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":75.2},{"place":13,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":73.7},{"place":14,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":73.4},{"place":15,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":72.4},{"place":16,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":71.5},{"place":17,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":70.7},{"place":18,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":70.2},{"place":19,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":69},{"place":20,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":68.9},{"place":21,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":67.4},{"place":22,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":67.3},{"place":23,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":66.3},{"place":24,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":65.2},{"place":25,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":63.5},{"place":26,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":62.1},{"place":27,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":54.4},{"place":28,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":49.6},{"place":29,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":47.3},{"place":30,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":46.6},{"place":31,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":46.5},{"place":32,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":43.6},{"place":33,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":43.2},{"place":34,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":42.7},{"place":35,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":42.6},{"place":36,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":38.3},{"place":37,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":37.9},{"place":38,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":34.1},{"place":39,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":31.1}]},{"id":"bbh-zh","name":"BBH-ZH","topic":"Multi-task reasoning (Chinese)","description":"Chinese translation of BIG-Bench Hard reasoning tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LLaDA2.0 Flash","top_percent":87.52,"top_model_id":"llada2.0-flash","top_generation":"LLaDA 2.0","top_model_base":"LLaDA 2.0 Flash","top_model_family":"LLaDA","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":87.52},{"place":2,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":87.15},{"place":3,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":86.23},{"place":4,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.18},{"place":5,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":85.82},{"place":6,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":83.91},{"place":7,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":83.59},{"place":8,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":82.55},{"place":9,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.09},{"place":10,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":75.75},{"place":11,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":75.09},{"place":12,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":70.4},{"place":13,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":67.65},{"place":14,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":66.11}]},{"id":"bbq","name":"BBQ","topic":"Bias evaluation","description":"Bias Benchmark for Question Answering evaluating social biases across contexts.","url":"https://huggingface.co/datasets/heegyu/bbq","leaderboard":"","github":"https://github.com/jinjh0123/BBG","paper":"https://arxiv.org/abs/2110.08193","metric":"percent","stars":"","top_model":"Mixtral 8x 7B","top_percent":55.98,"top_model_id":"mixtral-8x7b","top_generation":"Mixtral","top_model_base":"Mixtral 8x 7B","top_model_family":"Mixtral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":55.98},{"place":2,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":51.5},{"place":3,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.6866},{"place":4,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":0.6405},{"place":5,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":0.6362},{"place":6,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":0.6362},{"place":7,"model":"hcx","company":"hcx","family":"HCX","version":"HCX","score":0.6345},{"place":8,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":0.6228},{"place":9,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":0.6026},{"place":10,"model":"hcx-dash","company":"hcx","family":"HCX","version":"HCX","score":0.5966},{"place":11,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0.5733},{"place":12,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0.547}]},{"id":"beam-128k","name":"BEAM 128K","topic":"Long-context memory","description":"BEAM long-context memory benchmark at 128K tokens.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Glimmer 30B","top_percent":65.1,"top_model_id":"muse-glimmer-30b","top_generation":"Muse Glimmer","top_model_base":"Muse Glimmer","top_model_family":"Muse","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":65.1},{"place":2,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63},{"place":3,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.2}]},{"id":"beavertails","name":"BeaverTails","topic":"Safety / harmfulness","description":"Safety benchmark evaluating harmfulness in model responses.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"IQuest-Coder-V1-40B-Thinking","top_percent":76.7,"top_model_id":"iquest-coder-v1-40b-thinking","top_generation":"IQuest Coder V1","top_model_base":"IQuest Coder V1 40B","top_model_family":"IQuest Coder","top_company":"iquest","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":76.7},{"place":2,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":70.5},{"place":3,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68},{"place":4,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":67.5}]},{"id":"belebele","name":"Belebele","topic":"Multilingual reading comprehension","description":"Parallel multiple-choice reading-comprehension benchmark over FLORES passages in 122 language variants.","url":"https://huggingface.co/datasets/facebook/belebele","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":95.9,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":34,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":95.9},{"place":2,"model":"jais-3-375b-a23b","company":"g42","family":"Jais","version":"Jais 3","score":95.6},{"place":3,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":95.5},{"place":4,"model":"jais-3-32b","company":"g42","family":"Jais","version":"Jais 3","score":95},{"place":5,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":95},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94.8},{"place":7,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.4},{"place":8,"model":"jais-3-mova-36b-a4b","company":"g42","family":"Jais","version":"Jais 3","score":94.4},{"place":9,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":94.3},{"place":10,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":94},{"place":11,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":93.6},{"place":12,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":93.1},{"place":13,"model":"jais-3-7b","company":"g42","family":"Jais","version":"Jais 3","score":92.9},{"place":14,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":92.3},{"place":15,"model":"jais-3-3.7b","company":"g42","family":"Jais","version":"Jais 3","score":91.9},{"place":16,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.2},{"place":17,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.7},{"place":18,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":86.81},{"place":19,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":86.6},{"place":20,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.98},{"place":21,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":85.54},{"place":22,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84},{"place":23,"model":"acegpt-v2-32b-chat","company":"freedomintelligence","family":"AceGPT","version":"AceGPT-v2","score":83.96},{"place":24,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":83.26},{"place":25,"model":"jais-3-0.9b","company":"g42","family":"Jais","version":"Jais 3","score":81.6},{"place":26,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":79.9},{"place":27,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.6},{"place":28,"model":"allam-7b-instruct-preview","company":"humain","family":"ALLaM","version":"ALLaM","score":78.8},{"place":29,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":72.9},{"place":30,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.6},{"place":31,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":62.2},{"place":32,"model":"granite-4.0-h-3b-ar","company":"IBM","family":"Granite","version":"Granite 4.0","score":61.9},{"place":33,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":61.8},{"place":34,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":57.9},{"place":35,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":57.8},{"place":36,"model":"hala-1.2b","company":"hala","family":"Hala","version":"Hala","score":39.9}]},{"id":"benchcad","name":"BenchCAD","topic":"CAD generation","description":"CAD modelling benchmark for agents producing 3D CAD artifacts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":95.9,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":95.9},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":84.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.3},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":82.1},{"place":5,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":73},{"place":6,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":72.8},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":70.6},{"place":8,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":67.5},{"place":9,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":63.1},{"place":10,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":62.3},{"place":11,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":60.6},{"place":12,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":44.4},{"place":13,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":41.2},{"place":14,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":38.4},{"place":15,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":35.5},{"place":16,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":27.3}]},{"id":"benchcad-python-tool","name":"BenchCAD (python tool)","topic":"CAD","description":"BenchCAD with a Python tool available.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":96.2,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":96.2},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":95.9},{"place":3,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":92.7},{"place":4,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":92.6},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.4},{"place":6,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":81.6},{"place":7,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":78.2},{"place":8,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":73.9},{"place":9,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":65},{"place":10,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":61},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":55.8},{"place":12,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":51.8}]},{"id":"beyondaime","name":"BeyondAIME","topic":"Math (beyond AIME)","description":"Advanced math problems exceeding AIME difficulty.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":91,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":91},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":90},{"place":3,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":88},{"place":4,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":87},{"place":5,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":86.5},{"place":6,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":86},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":83},{"place":8,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":82},{"place":9,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":80},{"place":10,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":79},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":79},{"place":12,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":77},{"place":13,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":76},{"place":14,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":74},{"place":15,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.3},{"place":16,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":72},{"place":17,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":69.1},{"place":18,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69},{"place":19,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":69},{"place":20,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":68},{"place":21,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":66.9},{"place":22,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64},{"place":23,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62},{"place":25,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":61.5},{"place":26,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":61},{"place":27,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":60.3},{"place":28,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":60},{"place":29,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.8},{"place":30,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":58.3},{"place":31,"model":"qwen3-moe-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.6},{"place":32,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57},{"place":33,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":51},{"place":34,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":48.5},{"place":35,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":47.3},{"place":36,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":46},{"place":37,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":44.2}]},{"id":"bfcl","name":"BFCL","topic":"Code reasoning","description":"Benchmark for functional code correctness and logic.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-4B","top_percent":95,"top_model_id":"qwen3-4b","top_generation":"Qwen3","top_model_base":"Qwen3 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":95},{"place":2,"model":"llama-3.1-3b","company":"meta","family":"Llama","version":"Llama 3.1","score":92.3},{"place":3,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":92.3},{"place":4,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.5},{"place":5,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":88.5},{"place":6,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":84.8},{"place":7,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":83},{"place":8,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":82.94},{"place":9,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":81.76},{"place":10,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":81.24},{"place":11,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":81},{"place":12,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":80.94},{"place":13,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":76.1},{"place":14,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":15,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.3},{"place":16,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":69.1},{"place":17,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.4},{"place":18,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63},{"place":19,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.5},{"place":20,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":60.3},{"place":21,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":58.88},{"place":22,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.6},{"place":23,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":57.88},{"place":24,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":55.34}]},{"id":"bfcl-decision","name":"BFCL (decision)","topic":"Function calling","description":"Yes/no per supplied function on BFCL cases; case exact accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/gorilla-llm/gorilla","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef-Flash","top_percent":98.8,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":98.8},{"place":2,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":98.5},{"place":3,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":98.2},{"place":4,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":97.8},{"place":5,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":97.8},{"place":6,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":97.5},{"place":7,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":97.3},{"place":8,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":96.5},{"place":9,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":96.4},{"place":10,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":96.3},{"place":11,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":96.2},{"place":12,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":96},{"place":13,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":95.8},{"place":14,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":95.8},{"place":15,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":95.6},{"place":16,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":95.5},{"place":17,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":94.6},{"place":18,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":94.5},{"place":19,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":94},{"place":20,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":92.7},{"place":21,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":92.6},{"place":22,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":92.2},{"place":23,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":91.6},{"place":24,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":90.8},{"place":25,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":90.2},{"place":26,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":89.4},{"place":27,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":86},{"place":28,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":82.2},{"place":29,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":81.3},{"place":30,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":72.5},{"place":31,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":71},{"place":32,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":66.1},{"place":33,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":64.5},{"place":34,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":57.9},{"place":35,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":47.6},{"place":36,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":46.2},{"place":37,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":41.6},{"place":38,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":38.1}]},{"id":"bfcl-live-v2","name":"BFCL Live v2","topic":"Finance QA","description":"Financial compliance and literacy questions from the BFCL Live v2 benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"o1 Mini","top_percent":81,"top_model_id":"o1-mini","top_generation":"o1","top_model_base":"o1 Mini","top_model_family":"o1","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":81},{"place":2,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":79},{"place":3,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":75.43},{"place":4,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":75.4},{"place":5,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":75.4},{"place":6,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":74.11},{"place":7,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.19},{"place":8,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":67.57},{"place":9,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":63.9},{"place":10,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":54.1}]},{"id":"bfcl-v2","name":"BFCL v2","topic":"Code reasoning","description":"Second release of the BFCL benchmark focusing on functional code correctness and logic.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniCPM3-4B","top_percent":76,"top_model_id":"minicpm3-4b","top_generation":"MiniCPM3","top_model_base":"MiniCPM3-4B","top_model_family":"MiniCPM","top_company":"openbmb","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":76},{"place":2,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":75.4},{"place":3,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":73.3},{"place":4,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":71.6},{"place":5,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":70.1},{"place":6,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":48.4},{"place":7,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":29.4},{"place":8,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":25.7},{"place":9,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":19.2}]},{"id":"bfcl-v3","name":"BFCL v3","topic":"Code reasoning","description":"Benchmark for functional code correctness and logic (v3).","url":"","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM 4.5","top_percent":77.8,"top_model_id":"glm-4.5","top_generation":"GLM 4.5","top_model_base":"GLM 4.5","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":134,"total_models":3854,"placements":[{"place":1,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":77.8},{"place":2,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.74},{"place":3,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":76.5},{"place":4,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":75.61},{"place":5,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.05},{"place":6,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":74.94},{"place":7,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":74.92},{"place":8,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":74.86},{"place":9,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":74.6},{"place":10,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.9},{"place":11,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":73.68},{"place":12,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":73.61},{"place":13,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.41},{"place":14,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.39},{"place":15,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":72.4},{"place":16,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":72.06},{"place":17,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":72.06},{"place":18,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":72},{"place":19,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.9},{"place":20,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.06},{"place":21,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.95},{"place":22,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.8},{"place":23,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.8},{"place":24,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":70.72},{"place":25,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":70.6},{"place":26,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.56},{"place":27,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":70.5},{"place":28,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.5},{"place":29,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":30,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.3},{"place":31,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.3},{"place":32,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":70.3},{"place":33,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":70.28},{"place":34,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.12},{"place":35,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":69.57},{"place":36,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":69.4},{"place":37,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.1},{"place":38,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":69.02},{"place":39,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.87},{"place":40,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":68.7},{"place":41,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.6},{"place":42,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.6},{"place":43,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":68.51},{"place":44,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.5},{"place":45,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":68.27},{"place":46,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.1},{"place":47,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":68},{"place":48,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":68},{"place":49,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":67.9},{"place":50,"model":"o1","company":"openai","family":"o1","version":"o1","score":67.8},{"place":51,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":67.8},{"place":52,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":67.69},{"place":53,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":67.5},{"place":54,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.31},{"place":55,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":67},{"place":56,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":66.9},{"place":57,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":66.5},{"place":58,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":66.46},{"place":59,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":66.39},{"place":60,"model":"gka-primed-hqwen3-32b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":66.34},{"place":61,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.3},{"place":62,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.3},{"place":63,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.3},{"place":64,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":66.3},{"place":65,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.2},{"place":66,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":65.9},{"place":67,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":65.25},{"place":68,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.1},{"place":69,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.1},{"place":70,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":65.03},{"place":71,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":65},{"place":72,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":64.79},{"place":73,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":64.69},{"place":74,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":64.6},{"place":75,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64.5},{"place":76,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":64.4},{"place":77,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":64.4},{"place":78,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":64.36},{"place":79,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.1},{"place":80,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":63.5},{"place":81,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.3},{"place":82,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63.2},{"place":83,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63},{"place":84,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.9},{"place":85,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":62.7},{"place":86,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":62.52},{"place":87,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":62.2},{"place":88,"model":"gka-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":62.2},{"place":89,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":61.9},{"place":90,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.7},{"place":91,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":61.7},{"place":92,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":61.1},{"place":93,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":61.1},{"place":94,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":60.8},{"place":95,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":60.5},{"place":96,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":60.2},{"place":97,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.2},{"place":98,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":60.2},{"place":99,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":59.98},{"place":100,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":59.67},{"place":101,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":59.2},{"place":102,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":59.07},{"place":103,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":58.21},{"place":104,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":58},{"place":105,"model":"gdn-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":57.44},{"place":106,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.31},{"place":107,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":56.97},{"place":108,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":56.9},{"place":109,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":56.89},{"place":110,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.6},{"place":111,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":56.44},{"place":112,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":55.93},{"place":113,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.8},{"place":114,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.5},{"place":115,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":55.41},{"place":116,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":53.75},{"place":117,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":53.61},{"place":118,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":52.9},{"place":119,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":52.7},{"place":120,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":52.43},{"place":121,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52.2},{"place":122,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":52.2},{"place":123,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":51.88},{"place":124,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":50.69},{"place":125,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":50.62},{"place":126,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":50.6},{"place":127,"model":"codestral-12b-instruct","company":"mistral","family":"Codestral","version":"Codestral","score":50.5},{"place":128,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":50},{"place":129,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":49.8},{"place":130,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":49.6},{"place":131,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":49.12},{"place":132,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":48.9},{"place":133,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.4},{"place":134,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.3},{"place":135,"model":"gpt-oss-20b-moe","company":"openai","family":"GPT","version":"GPT-OSS","score":45.9},{"place":136,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":45.9},{"place":137,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":45.07},{"place":138,"model":"magistral-small-2509","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":44.25},{"place":139,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":44.11},{"place":140,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":43.26},{"place":141,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":43.1},{"place":142,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":43.07},{"place":143,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":41.9},{"place":144,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":39.75},{"place":145,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":39.75},{"place":146,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.64},{"place":147,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":39.58},{"place":148,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":37.1},{"place":149,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.08},{"place":150,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":31.5},{"place":151,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":25.9},{"place":152,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":22.95},{"place":153,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":21.44},{"place":154,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":17.62},{"place":155,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":16.64},{"place":156,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":16.61}]},{"id":"bfcl-v3-ja","name":"BFCL v3 (Japanese)","topic":"Function calling (Japanese)","description":"Japanese translation of BFCL v3 function-calling benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"NVIDIA-Nemotron-Nano-9B-v2-Japanese","top_percent":64.9,"top_model_id":"nemotron-nano-9b-v2-japanese","top_generation":"Nemotron Nano v2","top_model_base":"NVIDIA Nemotron Nano 9B Japanese","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"nemotron-nano-9b-v2-japanese","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":64.9},{"place":2,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.8},{"place":3,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":52.45},{"place":4,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":50.57},{"place":5,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":48},{"place":6,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":46.29},{"place":7,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":21.06},{"place":8,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":17.26},{"place":9,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":13.86},{"place":10,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":11.85},{"place":11,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":11.76},{"place":12,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":11.7}]},{"id":"bfcl-v3-live","name":"BFCL v3 (Live)","topic":"Tool calling","description":"BFCL v3 Live subset for real-time tool calling evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":84.9,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.9},{"place":2,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.9},{"place":3,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.3},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":78.9},{"place":5,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.6},{"place":6,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":78.4},{"place":7,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":77},{"place":8,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":76.66},{"place":9,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":76.2},{"place":10,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.9},{"place":11,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.6},{"place":12,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":74.5},{"place":13,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":74.3},{"place":14,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.93},{"place":15,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":71.94},{"place":16,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":69.64},{"place":17,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.14},{"place":18,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":68.74},{"place":19,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.96},{"place":20,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.48}]},{"id":"bfcl-v3-multi-turn","name":"BFCL v3 (Multi-Turn)","topic":"Tool calling","description":"BFCL v3 Multi-Turn subset for multi-turn tool calling evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniMax M2.5","top_percent":76.8,"top_model_id":"minimax-m2.5","top_generation":"MiniMax M2.5","top_model_base":"MiniMax M2.5","top_model_family":"MiniMax","top_company":"minimax","top_open_source":1,"lower_is_better":false,"bench_models":37,"total_models":3854,"placements":[{"place":1,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":76.8},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":63.3},{"place":4,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":61.6},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":61},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":60.3},{"place":7,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.8},{"place":8,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":58.2},{"place":9,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54},{"place":10,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":53.6},{"place":11,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":53.5},{"place":12,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.4},{"place":13,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":51.4},{"place":14,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":48.6},{"place":15,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":48.4},{"place":16,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":47.9},{"place":17,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":45.6},{"place":18,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":45.3},{"place":19,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":44.6},{"place":20,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":43.7},{"place":21,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":42.5},{"place":22,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.1},{"place":23,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":39.8},{"place":24,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":38.77},{"place":25,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":38.63},{"place":26,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":37.4},{"place":27,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":36.2},{"place":28,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.6},{"place":29,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":35.38},{"place":30,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":34.3},{"place":31,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":24.6},{"place":32,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":22.8},{"place":33,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":17.12},{"place":34,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.88},{"place":35,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":11.38},{"place":36,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.27},{"place":37,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":5.5},{"place":38,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.38},{"place":39,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":0.6}]},{"id":"bfcl-v4","name":"BFCL v4","topic":"Code reasoning","description":"BFCL v4 benchmark for functional code correctness and logic.","url":"","leaderboard":"https://gorilla.cs.berkeley.edu/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.6-27B","top_percent":80.2,"top_model_id":"qwen3.6-27b","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 27B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":161,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.2},{"place":2,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.6},{"place":3,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":78.4},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.5},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77},{"place":6,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":77},{"place":7,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":76.7},{"place":8,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":75},{"place":9,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.6},{"place":10,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":74.1},{"place":11,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":73.8},{"place":12,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.65},{"place":13,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.2},{"place":14,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.1},{"place":15,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":73},{"place":16,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.9},{"place":17,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":72.9},{"place":18,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":72.7},{"place":19,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.5},{"place":20,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":72.4},{"place":21,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.2},{"place":22,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":71.8},{"place":23,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":71.4},{"place":24,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":71.3},{"place":25,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":71.2},{"place":26,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":70.9},{"place":27,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":70.8},{"place":28,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":70.64},{"place":29,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":70.6},{"place":30,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":70.6},{"place":31,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.5},{"place":32,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":70.33},{"place":33,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":70.1},{"place":34,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":69.87},{"place":35,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":69.1},{"place":36,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":68.9},{"place":37,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.7},{"place":38,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":68.51},{"place":39,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.5},{"place":40,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":68.3},{"place":41,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":68.3},{"place":42,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":68.3},{"place":43,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.2},{"place":44,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68.14},{"place":45,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":67.7},{"place":46,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":67.57},{"place":47,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":67.43},{"place":48,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.3},{"place":49,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":67.28},{"place":50,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.2},{"place":51,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":67.2},{"place":52,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67.1},{"place":53,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":67},{"place":54,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":66.81},{"place":55,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":66.6},{"place":56,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":66.47},{"place":57,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.1},{"place":58,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.83},{"place":59,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":65.8},{"place":60,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":65.7},{"place":61,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":65.4},{"place":62,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":65.4},{"place":63,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":65.4},{"place":64,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":65.2},{"place":65,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":65.1},{"place":66,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":65.03},{"place":67,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":65.01},{"place":68,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":65},{"place":69,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.88},{"place":70,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":64.8},{"place":71,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64.7},{"place":72,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":64.6},{"place":73,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.33},{"place":74,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":63.72},{"place":75,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":63.71},{"place":76,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":63.6},{"place":77,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":63.3},{"place":78,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.19},{"place":79,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":63.1},{"place":80,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":63.1},{"place":81,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":63.05},{"place":82,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":62.96},{"place":83,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":62.81},{"place":84,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":62.72},{"place":85,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.5},{"place":86,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.47},{"place":87,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":62.3},{"place":88,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62.06},{"place":89,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.96},{"place":90,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.8},{"place":91,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":61.79},{"place":92,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":61.6},{"place":93,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":61.6},{"place":94,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":61.6},{"place":95,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":61.5},{"place":96,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":61.4},{"place":97,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":61.39},{"place":98,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":61.2},{"place":99,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":61.18},{"place":100,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":61.1},{"place":101,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.02},{"place":102,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":61},{"place":103,"model":"llada2.2-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":60.78},{"place":104,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":60.66},{"place":105,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60.6},{"place":106,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.6},{"place":107,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":60.3},{"place":108,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":60.2},{"place":109,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.13},{"place":110,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":60.1},{"place":111,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":60.06},{"place":112,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60.05},{"place":113,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":59.8},{"place":114,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":59.68},{"place":115,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.5},{"place":116,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":58.9},{"place":117,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.5},{"place":118,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":58.3},{"place":119,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":58},{"place":120,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":57.86},{"place":121,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":57.3},{"place":122,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":57.23},{"place":123,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":57.2},{"place":124,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.09},{"place":125,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":56.88},{"place":126,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.8},{"place":127,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":56.5},{"place":128,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":56.09},{"place":129,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":56},{"place":130,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.9},{"place":131,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55.87},{"place":132,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.7},{"place":133,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":55.5},{"place":134,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":55.3},{"place":135,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.8},{"place":136,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.01},{"place":137,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":53.9},{"place":138,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":53.8},{"place":139,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":53.8},{"place":140,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":53.78},{"place":141,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":53.74},{"place":142,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.6},{"place":143,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":52.9},{"place":144,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.5},{"place":145,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":52.41},{"place":146,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":52.39},{"place":147,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.3},{"place":148,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":52.2},{"place":149,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":52.06},{"place":150,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52},{"place":151,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":51.8},{"place":152,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":51},{"place":153,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":50.8},{"place":154,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.56},{"place":155,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":50.53},{"place":156,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.3},{"place":157,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":49.88},{"place":158,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":49.73},{"place":159,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":49.72},{"place":160,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":49.7},{"place":161,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49.7},{"place":162,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":49.6},{"place":163,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":49.2},{"place":164,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.6},{"place":165,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.6},{"place":166,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":48.5},{"place":167,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.9},{"place":168,"model":"g9v3-3b","company":"ai9stars","family":"G9","version":"G9v3","score":47.9},{"place":169,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":47.68},{"place":170,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47.18},{"place":171,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47},{"place":172,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":46.9},{"place":173,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":46.6},{"place":174,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":46.4},{"place":175,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.39},{"place":176,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":45.99},{"place":177,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":45.6},{"place":178,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":45.4},{"place":179,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.2},{"place":180,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":45.14},{"place":181,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":44.9},{"place":182,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":44.87},{"place":183,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":44.2},{"place":184,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":43.7},{"place":185,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.6},{"place":186,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":43.3},{"place":187,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.9},{"place":188,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.7},{"place":189,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":42.4},{"place":190,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":42.2},{"place":191,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.64},{"place":192,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40},{"place":193,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":39.9},{"place":194,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":39.22},{"place":195,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":38.8},{"place":196,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":38.8},{"place":197,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":38},{"place":198,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37.4},{"place":199,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":36.98},{"place":200,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":36.9},{"place":201,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":36.8},{"place":202,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":36.6},{"place":203,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":36.4},{"place":204,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":35.9},{"place":205,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":35.12},{"place":206,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.92},{"place":207,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.9},{"place":208,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.2},{"place":209,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":33.2},{"place":210,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":32.5},{"place":211,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":31.91},{"place":212,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":31.8},{"place":213,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":31.7},{"place":214,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.2},{"place":215,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":28.52},{"place":216,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":28.44},{"place":217,"model":"k2-horizon-0.9b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":28},{"place":218,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.53},{"place":219,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":25.52},{"place":220,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.43},{"place":221,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.39},{"place":222,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.3},{"place":223,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.3},{"place":224,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":25.2},{"place":225,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":25.15},{"place":226,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":25.05},{"place":227,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":21.86},{"place":228,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":21.08},{"place":229,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":21.03},{"place":230,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":20.5},{"place":231,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":19.8},{"place":232,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.7},{"place":233,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":13.73},{"place":234,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":13.28},{"place":235,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":12.29},{"place":236,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":10.6},{"place":237,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":7.17}]},{"id":"bfcl-v4-multi-turn","name":"BFCL v4 Multi-Turn","topic":"Function calling","description":"Multi-turn category of the Berkeley Function Calling Leaderboard v4.","url":"https://gorilla.cs.berkeley.edu/leaderboard.html","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Mercury Voice","top_percent":60.5,"top_model_id":"mercury-voice","top_generation":"Mercury 2.5","top_model_base":"Mercury Voice","top_model_family":"Mercury","top_company":"inception","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"mercury-voice","company":"inception","family":"Mercury","version":"Mercury 2.5","score":60.5},{"place":2,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55.6},{"place":3,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":45.5}]},{"id":"bharatmath","name":"BharatMath","topic":"Indic languages","description":"Math word problems in Indian languages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":78.61,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":78.61},{"place":2,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.48},{"place":3,"model":"gnani-evon-v3.3-30b-a3b","company":"gnani","family":"gnani-evon","version":"gnani-evon-v3.3","score":73.97},{"place":4,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":60.32}]},{"id":"big-bench","name":"BIG-Bench","topic":"Multi-task reasoning","description":"BIG-bench overall performance (original).","url":"https://github.com/google/BIG-bench","leaderboard":"","github":"https://github.com/google/BIG-bench","paper":"","metric":"percent","stars":"3110","top_model":"Gemma 2 7B","top_percent":55.1,"top_model_id":"gemma-2-7b","top_generation":"Gemma 2","top_model_base":"Gemma 2 7B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":55.1},{"place":2,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":35.2}]},{"id":"big-bench-audio","name":"Big Bench Audio","topic":"Speech reasoning","description":"Artificial Analysis Big Bench Audio: spoken-question reasoning benchmark adapted from BIG-Bench Hard.","url":"https://huggingface.co/datasets/ArtificialAnalysis/big_bench_audio","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"StepAudio 3 Realtime","top_percent":99.7,"top_model_id":"stepaudio-3-realtime","top_generation":"StepAudio 3","top_model_base":"StepAudio 3 Realtime","top_model_family":"Step","top_company":"stepfun","top_open_source":0,"lower_is_better":false,"bench_models":70,"total_models":3854,"placements":[{"place":1,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":99.7},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":99.6},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":99.4},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":99.2},{"place":5,"model":"qwen-audio-3.0-realtime-plus","company":"qwen","family":"Qwen","version":"Qwen Audio 3.0","score":99.2},{"place":6,"model":"eleven-realtime-v1-max","company":"elevenlabs","family":"Eleven","version":"Eleven Realtime v1","score":98.8},{"place":7,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":98.8},{"place":8,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":98.7},{"place":9,"model":"grok-voice-3.0","company":"xai","family":"Grok","version":"Grok Voice","score":98.5},{"place":10,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":98.1},{"place":11,"model":"gemini-3.8-live-extended-thinking-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":97.7},{"place":12,"model":"step-audio-r1.1-realtime","company":"stepfun","family":"Step","version":"Step-Audio-R1","score":97.6},{"place":13,"model":"grok-voice-2.0","company":"xai","family":"Grok","version":"Grok Voice","score":97.2},{"place":14,"model":"grok-voice-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":97.1},{"place":15,"model":"ultravox-v0.7-glm-4.6-thinking","company":"fixie","family":"Ultravox","version":"Ultravox v0.7","score":97},{"place":16,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":96.6},{"place":17,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":96.6},{"place":18,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":96.6},{"place":19,"model":"step-audio-r1.1","company":"stepfun","family":"Step","version":"Step-Audio-R1","score":96.4},{"place":20,"model":"qwen-audio-3.0-realtime-flash","company":"qwen","family":"Qwen","version":"Qwen Audio 3.0","score":96.1},{"place":21,"model":"step-audio-r1-realtime","company":"stepfun","family":"Step","version":"Step-Audio-R1","score":96.1},{"place":22,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":95.8},{"place":23,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":94},{"place":24,"model":"grok-voice-fast-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":93.33},{"place":25,"model":"gpt-realtime-2.0-medium","company":"openai","family":"GPT","version":"GPT-realtime-2","score":93.3},{"place":26,"model":"grok-voice-agent","company":"xai","family":"Grok","version":"Grok Voice","score":92.3},{"place":27,"model":"gemini-2.5-flash-native-audio-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.1},{"place":28,"model":"ultravox-v0.7-glm-4.6","company":"fixie","family":"Ultravox","version":"Ultravox v0.7","score":91.8},{"place":29,"model":"gemini-3.8-live","company":"google","family":"Gemini","version":"Gemini 3.8","score":91.7},{"place":30,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.2},{"place":31,"model":"gemini-2.5-flash-native-audio-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.7},{"place":32,"model":"gpt-live-1-medium","company":"openai","family":"GPT","version":"GPT-Live-1","score":90.1},{"place":33,"model":"gpt-live-1-low","company":"openai","family":"GPT","version":"GPT-Live-1","score":89},{"place":34,"model":"nova-2-sonic-2026-03","company":"amazon","family":"Nova","version":"Nova 2","score":88.1},{"place":35,"model":"nova-2-sonic","company":"amazon","family":"Nova","version":"Nova 2","score":87.1},{"place":36,"model":"nova-2-sonic","company":"amazon","family":"Nova","version":"Nova 2","score":87},{"place":37,"model":"gpt-realtime-2.1","company":"openai","family":"GPT","version":"GPT-realtime-2","score":86.8},{"place":38,"model":"ultravox-v0.6-llama-3.3-70b","company":"fixie","family":"Ultravox","version":"Ultravox v0.6","score":85.48},{"place":39,"model":"deepslate-opal","company":"deepslate","family":"Deepslate","version":"Deepslate Opal","score":85},{"place":40,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":83.3},{"place":41,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":83},{"place":42,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":82.8},{"place":43,"model":"ultravox-v0.5-llama-3.3-70b","company":"fixie","family":"Ultravox","version":"Ultravox v0.5","score":82.7},{"place":44,"model":"gpt-4o-realtime-preview-2025-06-03","company":"openai","family":"GPT","version":"GPT-4o","score":81.5},{"place":45,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":81.4},{"place":46,"model":"nova-sonic","company":"amazon","family":"Nova","version":"Nova 1","score":77},{"place":47,"model":"eleven-realtime-v1-mini","company":"elevenlabs","family":"Eleven","version":"Eleven Realtime v1","score":75.9},{"place":48,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":75.7},{"place":49,"model":"gpt-realtime-2.1-mini-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":74.7},{"place":50,"model":"gemini-2.5-flash-live-preview","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.2},{"place":51,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73},{"place":52,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":71.8},{"place":53,"model":"gemini-2.5-flash-native-audio","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.5},{"place":54,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.3},{"place":55,"model":"gemini-2.5-flash-live-preview","company":"google","family":"Gemini","version":"Gemini 2.5","score":71},{"place":56,"model":"gpt-4o-mini-realtime-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o mini","score":68.92},{"place":57,"model":"gpt-4o-mini-realtime-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o mini","score":68.9},{"place":58,"model":"gemini-2.5-flash-native-audio","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.6},{"place":59,"model":"higgs-realtime","company":"bosonai","family":"Higgs","version":"Higgs Realtime","score":68.6},{"place":60,"model":"gpt-4o-realtime-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o","score":68.4},{"place":61,"model":"gpt-realtime-mini","company":"openai","family":"GPT","version":"GPT Realtime","score":67.5},{"place":62,"model":"gpt-4o-audio-preview","company":"openai","family":"GPT","version":"GPT-4o","score":67.2},{"place":63,"model":"gpt-4o-realtime-preview","company":"openai","family":"GPT","version":"GPT-4o","score":66.2},{"place":64,"model":"gpt-4o-realtime-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o","score":65.6},{"place":65,"model":"gpt-realtime-mini","company":"openai","family":"GPT","version":"GPT Realtime","score":63.6},{"place":66,"model":"gpt-realtime-2.1-mini","company":"openai","family":"GPT","version":"GPT-realtime-2","score":62.7},{"place":67,"model":"mimo-audio-7b-instruct","company":"xiaomi","family":"MiMo","version":"MiMo-Audio","score":60.2},{"place":68,"model":"qwen3-omni-30b-a3b-realtime","company":"qwen","family":"Qwen","version":"Qwen3","score":59.2},{"place":69,"model":"qwen3.5-omni-flash-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":70,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":58.7},{"place":71,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":58.1},{"place":72,"model":"raon-speechchat-9b","company":"krafton","family":"Raon","version":"Raon-SpeechChat","score":57.5},{"place":73,"model":"qwen3-omni-30b-a3b-realtime","company":"qwen","family":"Qwen","version":"Qwen3","score":56.8},{"place":74,"model":"gpt-4o-audio-preview","company":"openai","family":"GPT","version":"GPT-4o","score":54.3},{"place":75,"model":"gpt-4o-audio-preview","company":"openai","family":"GPT","version":"GPT-4o","score":54.27},{"place":76,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":53.6},{"place":77,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":51},{"place":78,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":47.5},{"place":79,"model":"glm-4-voice","company":"zai","family":"GLM","version":"GLM-4","score":42.7},{"place":80,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":35.6},{"place":81,"model":"freeze-omni","company":"vita","family":"VITA","version":"Freeze-Omni","score":33.4},{"place":82,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":27},{"place":83,"model":"personaplex-7b-v1","company":"nvidia","family":"PersonaPlex","version":"PersonaPlex","score":19.1},{"place":84,"model":"flm-audio","company":"cofe","family":"FLM","version":"FLM-Audio","score":16},{"place":85,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":4.4}]},{"id":"big-bench-extra-hard","name":"BIG-Bench Extra Hard","topic":"Multi-task reasoning","description":"Extra hard subset of BIG-bench tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":78.8,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":47,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78.8},{"place":2,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.4},{"place":3,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":69.7},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":69},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.8},{"place":6,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.04},{"place":7,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":66.63},{"place":8,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.8},{"place":9,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":62.5},{"place":10,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":55},{"place":11,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53},{"place":12,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":52.37},{"place":13,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":51.99},{"place":14,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":51.5},{"place":15,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":48.43},{"place":16,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":48.04},{"place":17,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":47.6},{"place":18,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":47.34},{"place":19,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":47.25},{"place":20,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":43.12},{"place":21,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":42.86},{"place":22,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":39.75},{"place":23,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":37.8},{"place":24,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":35.77},{"place":25,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":34.83},{"place":26,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":33.51},{"place":27,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.1},{"place":28,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":29.8},{"place":29,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":29.08},{"place":30,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":27.86},{"place":31,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":27.8},{"place":32,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":27.2},{"place":33,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":25.7},{"place":34,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":25.4},{"place":35,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":23.24},{"place":36,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21.9},{"place":37,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":19.3},{"place":38,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":18.27},{"place":39,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":16.47},{"place":40,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":16.3},{"place":41,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":15.78},{"place":42,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":15.3},{"place":43,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":14.81},{"place":44,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":12.14},{"place":45,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":11},{"place":46,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":8.64},{"place":47,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.53},{"place":48,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":7.2},{"place":49,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.78}]},{"id":"big-finance-bench","name":"Big Finance Bench","topic":"Finance","description":"Finance benchmark reported in the GPT-5.6 announcement.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":53,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":53},{"place":2,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":51},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":49},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":44},{"place":5,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":36}]},{"id":"bigcodebench","name":"BigCodeBench","topic":"Code Generation","description":"BigCodeBench evaluates large language models on practical code generation tasks with unit-test verification.","url":"https://huggingface.co/datasets/bigcode/bigcodebench","leaderboard":"https://huggingface.co/spaces/bigcode/bigcodebench-leaderboard","github":"https://github.com/bigcode-project/BigCodeBench","paper":"https://arxiv.org/abs/2409.00001","metric":"pass@1","stars":"","top_model":"MiMo V2 Flash Base","top_percent":70.1,"top_model_id":"mimo-v2-flash-base","top_generation":"MiMo V2","top_model_base":"MiMo V2 Flash Base","top_model_family":"MiMo","top_company":"xiaomi","top_open_source":1,"lower_is_better":false,"bench_models":233,"total_models":3854,"placements":[{"place":1,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":70.1},{"place":2,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":63.9},{"place":3,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":63},{"place":4,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.9},{"place":5,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":61.7},{"place":6,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":60.6},{"place":7,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.2},{"place":8,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":57.1},{"place":9,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":56.9},{"place":10,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.8},{"place":11,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":56.1},{"place":12,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":56.1},{"place":13,"model":"gpt-oss-20b-moe","company":"openai","family":"GPT","version":"GPT-OSS","score":55.7},{"place":14,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":55.7},{"place":15,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":55.6},{"place":16,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":55.5},{"place":17,"model":"quasar-alpha","company":"quasar","family":"Quasar","version":"Quasar","score":55.1},{"place":18,"model":"stable-diffcoder-8b-instruct","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":54.8},{"place":19,"model":"gemini-exp-1206","company":"google","family":"Gemini","version":"Gemini 1.0","score":54.7},{"place":20,"model":"gemini-exp-1114","company":"google","family":"Gemini","version":"Gemini 1.0","score":54.3},{"place":21,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":54.2},{"place":22,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":54.2},{"place":23,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":54.1},{"place":24,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":54.1},{"place":25,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":54},{"place":26,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":53.6},{"place":27,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":53.5},{"place":28,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":53.5},{"place":29,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.3},{"place":30,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":53.3},{"place":31,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":53.2},{"place":32,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":52.9},{"place":33,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":52.7},{"place":34,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":52.6},{"place":35,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":52.5},{"place":36,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52.5},{"place":37,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":52.2},{"place":38,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":52.19},{"place":39,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":52.02},{"place":40,"model":"athene-v2-chat","company":"nvidia","family":"Athene","version":"Athene V2","score":52},{"place":41,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":51.8},{"place":42,"model":"gemini-exp-1121","company":"google","family":"Gemini","version":"Gemini 1.0","score":51.8},{"place":43,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":51.8},{"place":44,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.7},{"place":45,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":51.6},{"place":46,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":51.5},{"place":47,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51.4},{"place":48,"model":"athene-v2-agent","company":"nvidia","family":"Athene","version":"Athene V2","score":51.2},{"place":49,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.1},{"place":50,"model":"deepseek-v2.5-1210","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":50.9},{"place":51,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":50.9},{"place":52,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.8},{"place":53,"model":"gemini-1.5-pro-api-0514","company":"google","family":"Gemini","version":"Gemini 1.5","score":50.7},{"place":54,"model":"gemini-1.5-pro-api-0514","company":"google","family":"Gemini","version":"Gemini 1.5","score":50.6},{"place":55,"model":"hermes-2-theta-llama-3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":50.6},{"place":56,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":50.5},{"place":57,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":50.5},{"place":58,"model":"codestral-12b-instruct","company":"mistral","family":"Codestral","version":"Codestral","score":50.5},{"place":59,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":50.35},{"place":60,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.2},{"place":61,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":50.18},{"place":62,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":50.1},{"place":63,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":49.9},{"place":64,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":49.9},{"place":65,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":49.8},{"place":66,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":49.74},{"place":67,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.6},{"place":68,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":49.5},{"place":69,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":49.4},{"place":70,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":49.4},{"place":71,"model":"gemini-1.5-flash-api-0514","company":"google","family":"Gemini","version":"Gemini 1.0","score":49.3},{"place":72,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":49.3},{"place":73,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.1},{"place":74,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":49.1},{"place":75,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":49.1},{"place":76,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":49},{"place":77,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":49},{"place":78,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.8},{"place":79,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":48.8},{"place":80,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.7},{"place":81,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":48.7},{"place":82,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.6},{"place":83,"model":"llama-3-70b-synthia-v3.5","company":"meta","family":"Llama","version":"Llama 1","score":48.5},{"place":84,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.4},{"place":85,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":48.3},{"place":86,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":48.3},{"place":87,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":48.3},{"place":88,"model":"sky-t1-32b-flash","company":"novasky","family":"Sky","version":"Sky T1","score":48.2},{"place":89,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":48.2},{"place":90,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":48.2},{"place":91,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":48.1},{"place":92,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48},{"place":93,"model":"sky-t1-32b-preview","company":"novasky","family":"Sky","version":"Sky T1","score":48},{"place":94,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":47.8},{"place":95,"model":"iquest-coder-v1-14b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":47.7},{"place":96,"model":"reflectioncoder-ds-33b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":47.7},{"place":97,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":47.7},{"place":98,"model":"reflectioncoder-ds-33b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":47.6},{"place":99,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":47.6},{"place":100,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.4},{"place":101,"model":"whiterabbitneo-33b-v1","company":"whiterabbit","family":"WhiteRabbitNeo-33B-v1","version":"WhiteRabbitNeo-33B-v1","score":47.2},{"place":102,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":47.2},{"place":103,"model":"whiterabbitneo-33b-v1.5","company":"whiterabbitneo","family":"WhiteRabbitNeo","version":"WhiteRabbitNeo v1.5","score":47.2},{"place":104,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":47.1},{"place":105,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":47.1},{"place":106,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":47.1},{"place":107,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47},{"place":108,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":46.9},{"place":109,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":46.9},{"place":110,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":46.8},{"place":111,"model":"autocoder","company":"autocoder","family":"Autocoder","version":"Autocoder","score":46.6},{"place":112,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":46.6},{"place":113,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":46.5},{"place":114,"model":"qwen2-72b-chat","company":"qwen","family":"Qwen","version":"Qwen2","score":46.3},{"place":115,"model":"iquest-coder-v1-14b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":46.3},{"place":116,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":46.3},{"place":117,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":46.23},{"place":118,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":46.2},{"place":119,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46},{"place":120,"model":"hermes-2-pro-llama-3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":45.9},{"place":121,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":45.8},{"place":122,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":45.7},{"place":123,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":45.6},{"place":124,"model":"mixtral-8x22b-instruct","company":"mistral","family":"Mixtral","version":"Mixtral","score":45.4},{"place":125,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":45.4},{"place":126,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":45.3},{"place":127,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":45.3},{"place":128,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":45.2},{"place":129,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":44.9},{"place":130,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":44.8},{"place":131,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":44.7},{"place":132,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":44.6},{"place":133,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":44.6},{"place":134,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":44.5},{"place":135,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":44.5},{"place":136,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":44.5},{"place":137,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":44.1},{"place":138,"model":"deepcoder-14b-preview","company":"deepcoder","family":"Deepcoder","version":"Deepcoder","score":43.9},{"place":139,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":43.8},{"place":140,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":43.6},{"place":141,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":43.6},{"place":142,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":43.5},{"place":143,"model":"llama-3.1-nemotron-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":43.5},{"place":144,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.5},{"place":145,"model":"deepseek-r1-distill-qwen-14b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":43.3},{"place":146,"model":"phi-3-medium-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":43.2},{"place":147,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":42.9},{"place":148,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":42.89},{"place":149,"model":"deepseek-r1-distill-llama-70b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":42.6},{"place":150,"model":"artigenz-coder-ds-6.7b","company":"artigenz","family":"Artigenz-Coder-DS-6.7B","version":"Artigenz Coder DS","score":42.6},{"place":151,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":42.54},{"place":152,"model":"artigenz-coder-ds-6.7b","company":"artigenz","family":"Artigenz-Coder-DS-6.7B","version":"Artigenz Coder DS","score":42.5},{"place":153,"model":"yi-large","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":42.5},{"place":154,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":42.5},{"place":155,"model":"reflectioncoder-ds-6.7b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":42.3},{"place":156,"model":"reflectioncoder-cl-34b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":42.3},{"place":157,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":42.2},{"place":158,"model":"athene-70b","company":"nvidia","family":"Athene","version":"Athene V2","score":42.2},{"place":159,"model":"athene-70b","company":"nvidia","family":"Athene","version":"Athene V2","score":42.1},{"place":160,"model":"nxcode-cq-7b-orpo","company":"nexusflow","family":"Nxcode","version":"Nxcode","score":42.1},{"place":161,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":42},{"place":162,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":41.9},{"place":163,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":41.9},{"place":164,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":41.8},{"place":165,"model":"tess-v2.5.2-qwen2-72b","company":"tess","family":"Tess","version":"Tess","score":41.7},{"place":166,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":41.6},{"place":167,"model":"tess-v2.5.2-qwen2-72b","company":"tess","family":"Tess","version":"Tess","score":41.6},{"place":168,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":41.58},{"place":169,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":41.58},{"place":170,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":41.5},{"place":171,"model":"phi-3.1-mini-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":41.5},{"place":172,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":41.49},{"place":173,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":41.49},{"place":174,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":41.4},{"place":175,"model":"mistral-small-instruct-2409","company":"mistral","family":"Mistral","version":"Mistral","score":41.4},{"place":176,"model":"autocoder-s-6.7b","company":"autocoder","family":"Autocoder","version":"Autocoder","score":41.3},{"place":177,"model":"c4ai-command-r-08-2024","company":"cohere","family":"C4ai","version":"C4ai","score":41.2},{"place":178,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":41.1},{"place":179,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":41.1},{"place":180,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":41},{"place":181,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":40.92},{"place":182,"model":"opencodeinterpreter-ds-6.7b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":40.9},{"place":183,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":40.84},{"place":184,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":40.7},{"place":185,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":40.7},{"place":186,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":40.7},{"place":187,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":40.5},{"place":188,"model":"iquest-coder-v1-7b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":40.5},{"place":189,"model":"granite-code-34b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":40.3},{"place":190,"model":"codestral-mamba","company":"mistral","family":"Codestral","version":"Codestral","score":40.3},{"place":191,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":39.7},{"place":192,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39.7},{"place":193,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.7},{"place":194,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.6},{"place":195,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":39.6},{"place":196,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":39.21},{"place":197,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":39.21},{"place":198,"model":"iquest-coder-v1-7b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":38.9},{"place":199,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":38.8},{"place":200,"model":"wavecoder-ultra-6.7b","company":"wavecoder","family":"WaveCoder-Ultra-6.7B","version":"WaveCoder-Ultra-6.7B","score":38.8},{"place":201,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":38.77},{"place":202,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":38.5},{"place":203,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":38.4},{"place":204,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":38.3},{"place":205,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":38.3},{"place":206,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":38.1},{"place":207,"model":"granite-code-20b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":38},{"place":208,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":37.8},{"place":209,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":37.8},{"place":210,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37.8},{"place":211,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":37.7},{"place":212,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.2},{"place":213,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":37.2},{"place":214,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":37.11},{"place":215,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.1},{"place":216,"model":"dream-coder-7b-instruct","company":"huawei","family":"Dream","version":"Dream-Coder v0","score":37.1},{"place":217,"model":"autocoder-qw-7b","company":"autocoder","family":"Autocoder","version":"Autocoder","score":37},{"place":218,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":36.8},{"place":219,"model":"opencoder-1.5b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder-8B-Instruct","score":36.8},{"place":220,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":36.8},{"place":221,"model":"mistral-small-2402","company":"mistral","family":"Mistral","version":"Mistral","score":36.7},{"place":222,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":36.7},{"place":223,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":36.6},{"place":224,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":36.05},{"place":225,"model":"codegemma-7b-it","company":"google","family":"Codegemma","version":"Codegemma","score":35.8},{"place":226,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":35.8},{"place":227,"model":"diffucoder-7b-instruct","company":"apple","family":"DiffuCoder","version":"DiffuCoder","score":35.7},{"place":228,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":35.7},{"place":229,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":35.6},{"place":230,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":35.6},{"place":231,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":35.5},{"place":232,"model":"phi-3-small-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":35.3},{"place":233,"model":"phi-3-mini-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":35.1},{"place":234,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":35.1},{"place":235,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":35},{"place":236,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":35},{"place":237,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":34.6},{"place":238,"model":"reflectioncoder-cl-7b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":34.5},{"place":239,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":34.4},{"place":240,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":34.39},{"place":241,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":34.2},{"place":242,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":34.1},{"place":243,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":34.1},{"place":244,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":33.4},{"place":245,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":32.89},{"place":246,"model":"openchat-3.6-8b-20240522","company":"openchat","family":"OpenChat-3.5-7B-0106","version":"OpenChat-3.5-7B-0106","score":32.6},{"place":247,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.5},{"place":248,"model":"granite-3.0-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":32.4},{"place":249,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":32.3},{"place":250,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":32.19},{"place":251,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":30.9},{"place":252,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":30.7},{"place":253,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":30.6},{"place":254,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":30.44},{"place":255,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":30.18},{"place":256,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":30.1},{"place":257,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":29.9},{"place":258,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":29.8},{"place":259,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":29.5},{"place":260,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.39},{"place":261,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":29},{"place":262,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":28.5},{"place":263,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":27.7},{"place":264,"model":"opencodeinterpreter-ds-1.3b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":27.6},{"place":265,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":26.2},{"place":266,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":26.1},{"place":267,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":25.9},{"place":268,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":25.7},{"place":269,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":25.53},{"place":270,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.39},{"place":271,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":23.8},{"place":272,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":23.8},{"place":273,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":23.7},{"place":274,"model":"mistral-7b-instruct-v0.3","company":"mistral","family":"Mistral","version":"Mistral 0.3","score":23.4},{"place":275,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":22.8},{"place":276,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":21.9},{"place":277,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":21.5},{"place":278,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":21.4},{"place":279,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":21.2},{"place":280,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":20.9},{"place":281,"model":"llada-moe-7b-a1b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":20.4},{"place":282,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":16.5},{"place":283,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":16.1},{"place":284,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":13},{"place":285,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":12.9},{"place":286,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":11.1},{"place":287,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":10.6},{"place":288,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":10.1},{"place":289,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":9.8},{"place":290,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":8.8},{"place":291,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":7.5},{"place":292,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":0.4}]},{"id":"bigcodebench-hard","name":"BigCodeBench Hard","topic":"Code generation (hard)","description":"Harder variant of BigCodeBench testing complex programming and library tasks with function-level code generation.","url":"https://bigcode-project.github.io/bigcodebench/","leaderboard":"https://bigcode-project.github.io/bigcodebench/","github":"https://github.com/bigcode-project/bigcodebench","paper":"","metric":"pass@1","stars":"","top_model":"Claude 3.7 Sonnet (2025-02-19)","top_percent":35.8,"top_model_id":"claude-3.7-sonnet-20250219","top_generation":"Claude 3.7","top_model_base":"Claude 3.7 Sonnet","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":212,"total_models":3854,"placements":[{"place":1,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":35.8},{"place":2,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":35.8},{"place":3,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":35.5},{"place":4,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":35.5},{"place":5,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":35.5},{"place":6,"model":"o3-mini-2025-01-31-med","company":"openai","family":"o3","version":"o3","score":35.5},{"place":7,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":35.1},{"place":8,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":35.1},{"place":9,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":35.1},{"place":10,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":35.1},{"place":11,"model":"quasar-alpha","company":"quasar","family":"Quasar","version":"Quasar","score":34.8},{"place":12,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":34.5},{"place":13,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":34.5},{"place":14,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":34.5},{"place":15,"model":"o1-2024-12-17-low","company":"openai","family":"GPT","version":"o1","score":34.5},{"place":16,"model":"o3-mini-2025-01-31-low","company":"openai","family":"o3","version":"o3","score":34.5},{"place":17,"model":"gemini-exp-1206","company":"google","family":"Gemini","version":"Gemini 1.0","score":34.1},{"place":18,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.1},{"place":19,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":33.1},{"place":20,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":33.1},{"place":21,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":32.8},{"place":22,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":32.8},{"place":23,"model":"optimus-alpha","company":"openbmb","family":"Optimus","version":"Optimus","score":32.8},{"place":24,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":32.8},{"place":25,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":32.8},{"place":26,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.5},{"place":27,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":32.1},{"place":28,"model":"athene-v2-chat","company":"nvidia","family":"Athene","version":"Athene V2","score":32.1},{"place":29,"model":"gemini-2.0-pro-exp-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":31.8},{"place":30,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":31.8},{"place":31,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":31.8},{"place":32,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":31.8},{"place":33,"model":"stable-diffcoder-8b-instruct","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":31.8},{"place":34,"model":"athene-v2-agent","company":"nvidia","family":"Athene","version":"Athene V2","score":31.4},{"place":35,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":31.1},{"place":36,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":31.1},{"place":37,"model":"grok-3-mini-beta-low","company":"xai","family":"Grok","version":"Grok 3","score":31.1},{"place":38,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":30.8},{"place":39,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":30.8},{"place":40,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":30.4},{"place":41,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":30.4},{"place":42,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":30.1},{"place":43,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":30.1},{"place":44,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":29.4},{"place":45,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":29.4},{"place":46,"model":"gemini-1.5-pro-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":29.4},{"place":47,"model":"gemini-exp-1114","company":"google","family":"Gemini","version":"Gemini 1.0","score":29.4},{"place":48,"model":"chatgpt-4o-latest-20250129","company":"openai","family":"GPT","version":"GPT-4o","score":29.4},{"place":49,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":29.4},{"place":50,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":29.1},{"place":51,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":29},{"place":52,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":28.8},{"place":53,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.7},{"place":54,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":28.7},{"place":55,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.7},{"place":56,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":28.4},{"place":57,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":28.4},{"place":58,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":28.4},{"place":59,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":28.4},{"place":60,"model":"sky-t1-32b-preview","company":"novasky","family":"Sky","version":"Sky T1","score":28},{"place":61,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":27.7},{"place":62,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":27.7},{"place":63,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":27.7},{"place":64,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":27.7},{"place":65,"model":"gemini-1.5-pro-exp-0801","company":"google","family":"Gemini","version":"Gemini 1.0","score":27.4},{"place":66,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":27.4},{"place":67,"model":"gemini-exp-1121","company":"google","family":"Gemini","version":"Gemini 1.0","score":27.4},{"place":68,"model":"gemini-2.0-flash-thinking-exp-1219","company":"google","family":"Gemini","version":"Gemini 2.0","score":27.4},{"place":69,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":27.4},{"place":70,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":27.1},{"place":71,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":27},{"place":72,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":27},{"place":73,"model":"gemini-2.0-flash-thinking-exp-01-21","company":"google","family":"Gemini","version":"Gemini 2.0","score":27},{"place":74,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27},{"place":75,"model":"sky-t1-32b-flash","company":"novasky","family":"Sky","version":"Sky T1","score":26.7},{"place":76,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":26.7},{"place":77,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":26.7},{"place":78,"model":"grok-beta","company":"xai","family":"Grok","version":"Grok","score":26.7},{"place":79,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.7},{"place":80,"model":"grok-3-mini-beta-high","company":"xai","family":"Grok","version":"Grok 3","score":26.7},{"place":81,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":26.6},{"place":82,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":26.6},{"place":83,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.6},{"place":84,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":26.6},{"place":85,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":26.4},{"place":86,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":26.4},{"place":87,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":26.4},{"place":88,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":26.4},{"place":89,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":26.4},{"place":90,"model":"deepseek-v2.5-1210","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":26.4},{"place":91,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":26.4},{"place":92,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":26.1},{"place":93,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":26},{"place":94,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":26},{"place":95,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":26},{"place":96,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":25.7},{"place":97,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":25.7},{"place":98,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":25.7},{"place":99,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":25.6},{"place":100,"model":"gemini-1.5-pro-api-0514","company":"google","family":"Gemini","version":"Gemini 1.5","score":25.4},{"place":101,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":25.4},{"place":102,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":25.4},{"place":103,"model":"gemini-2.0-flash-lite-preview-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":25.4},{"place":104,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":25.3},{"place":105,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":25},{"place":106,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":25},{"place":107,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":24.7},{"place":108,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.7},{"place":109,"model":"llama-3.1-nemotron-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":24.7},{"place":110,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":24.6},{"place":111,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.6},{"place":112,"model":"llama-3.1-nemotron-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":24.6},{"place":113,"model":"dracarys-llama-3.1-70b-instruct","company":"dracarys","family":"Dracarys","version":"Dracarys Llama 3.1","score":24.3},{"place":114,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.3},{"place":115,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":24.3},{"place":116,"model":"gemini-1.5-flash-api-0514","company":"google","family":"Gemini","version":"Gemini 1.0","score":23.7},{"place":117,"model":"llama-3-70b-synthia-v3.5","company":"meta","family":"Llama","version":"Llama 1","score":23.7},{"place":118,"model":"gemini-1.5-flash-api-0514","company":"google","family":"Gemini","version":"Gemini 1.0","score":23.6},{"place":119,"model":"llama-3-70b-synthia-v3.5","company":"meta","family":"Llama","version":"Llama 1","score":23.6},{"place":120,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":23.6},{"place":121,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":23.6},{"place":122,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":23.6},{"place":123,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":23.4},{"place":124,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":23},{"place":125,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":23},{"place":126,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":23},{"place":127,"model":"dracarys-72b-instruct","company":"dracarys","family":"Dracarys","version":"Dracarys","score":22.6},{"place":128,"model":"hermes-2-theta-llama-3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":22.3},{"place":129,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":22.3},{"place":130,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":22.2},{"place":131,"model":"phi-3.1-mini-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":22},{"place":132,"model":"hermes-2-pro-llama-3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":21.7},{"place":133,"model":"hermes-2-pro-llama-3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":21.6},{"place":134,"model":"gemini-1.5-flash-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":21.6},{"place":135,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":21.6},{"place":136,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":20.9},{"place":137,"model":"deepseek-r1-distill-qwen-14b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":20.9},{"place":138,"model":"qwen2-72b-chat","company":"qwen","family":"Qwen","version":"Qwen2","score":20.7},{"place":139,"model":"qwen2-72b-chat","company":"qwen","family":"Qwen","version":"Qwen2","score":20.6},{"place":140,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":20.6},{"place":141,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":20.6},{"place":142,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":20.3},{"place":143,"model":"deepseek-r1-distill-llama-70b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":20.3},{"place":144,"model":"deepcoder-14b-preview","company":"deepcoder","family":"Deepcoder","version":"Deepcoder","score":20.3},{"place":145,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":20.3},{"place":146,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":20},{"place":147,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":19.9},{"place":148,"model":"mixtral-8x22b-instruct","company":"mistral","family":"Mixtral","version":"Mixtral","score":19.9},{"place":149,"model":"athene-70b","company":"nvidia","family":"Athene","version":"Athene V2","score":19.9},{"place":150,"model":"deepcoder-14b-preview","company":"deepcoder","family":"Deepcoder","version":"Deepcoder","score":19.6},{"place":151,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":19.3},{"place":152,"model":"whiterabbitneo-33b-v1","company":"whiterabbit","family":"WhiteRabbitNeo-33B-v1","version":"WhiteRabbitNeo-33B-v1","score":19.3},{"place":153,"model":"whiterabbitneo-33b-v1.5","company":"whiterabbitneo","family":"WhiteRabbitNeo","version":"WhiteRabbitNeo v1.5","score":19.3},{"place":154,"model":"reflectioncoder-ds-33b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":18.9},{"place":155,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":18.9},{"place":156,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":18.9},{"place":157,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":18.9},{"place":158,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":18.6},{"place":159,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":18.5},{"place":160,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":18.3},{"place":161,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":18.2},{"place":162,"model":"yi-large","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":17.6},{"place":163,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":17.6},{"place":164,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":17.6},{"place":165,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":17.6},{"place":166,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":17.2},{"place":167,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":17.2},{"place":168,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":17.2},{"place":169,"model":"nxcode-cq-7b-orpo","company":"nexusflow","family":"Nxcode","version":"Nxcode","score":17.2},{"place":170,"model":"autocoder","company":"autocoder","family":"Autocoder","version":"Autocoder","score":16.9},{"place":171,"model":"llama-4-scout","company":"meta","family":"Llama","version":"Llama 1","score":16.9},{"place":172,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":16.9},{"place":173,"model":"mistral-nemo-12b-instruct","company":"mistral","family":"Mistral","version":"Mistral","score":16.6},{"place":174,"model":"tess-v2.5.2-qwen2-72b","company":"tess","family":"Tess","version":"Tess","score":16.6},{"place":175,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":16.2},{"place":176,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":16.2},{"place":177,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":15.9},{"place":178,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":15.5},{"place":179,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":15.5},{"place":180,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":15.5},{"place":181,"model":"opencodeinterpreter-ds-6.7b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":15.2},{"place":182,"model":"reflectioncoder-ds-6.7b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":15.2},{"place":183,"model":"granite-code-34b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":14.9},{"place":184,"model":"wavecoder-ultra-6.7b","company":"wavecoder","family":"WaveCoder-Ultra-6.7B","version":"WaveCoder-Ultra-6.7B","score":14.9},{"place":185,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":14.9},{"place":186,"model":"mistral-small-instruct-2409","company":"mistral","family":"Mistral","version":"Mistral","score":14.9},{"place":187,"model":"granite-code-34b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":14.8},{"place":188,"model":"wavecoder-ultra-6.7b","company":"wavecoder","family":"WaveCoder-Ultra-6.7B","version":"WaveCoder-Ultra-6.7B","score":14.8},{"place":189,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":14.8},{"place":190,"model":"mistral-small-instruct-2409","company":"mistral","family":"Mistral","version":"Mistral","score":14.8},{"place":191,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":14.6},{"place":192,"model":"artigenz-coder-ds-6.7b","company":"artigenz","family":"Artigenz-Coder-DS-6.7B","version":"Artigenz Coder DS","score":14.2},{"place":193,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":14.2},{"place":194,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":14.2},{"place":195,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":14.2},{"place":196,"model":"mistral-small-2402","company":"mistral","family":"Mistral","version":"Mistral","score":13.9},{"place":197,"model":"codestral-mamba","company":"mistral","family":"Codestral","version":"Codestral","score":13.9},{"place":198,"model":"inversecoder-cl-13b","company":"inverse","family":"Inversecoder","version":"Inversecoder","score":13.9},{"place":199,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":13.9},{"place":200,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":13.8},{"place":201,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":13.6},{"place":202,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":13.5},{"place":203,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":13.5},{"place":204,"model":"inversecoder-cl-7b","company":"inverse","family":"Inversecoder","version":"Inversecoder","score":13.5},{"place":205,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":13.5},{"place":206,"model":"c4ai-command-r-08-2024","company":"cohere","family":"C4ai","version":"C4ai","score":13.5},{"place":207,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":13.2},{"place":208,"model":"phi-3-medium-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":13.2},{"place":209,"model":"reflectioncoder-cl-34b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":13.2},{"place":210,"model":"c4ai-command-r-plus-08.2024","company":"cohere","family":"C4ai","version":"C4ai","score":13.2},{"place":211,"model":"inversecoder-ds-6.7b","company":"inverse","family":"Inversecoder","version":"Inversecoder","score":12.9},{"place":212,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":12.8},{"place":213,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":12.5},{"place":214,"model":"phi-3-small-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":12.5},{"place":215,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":12.2},{"place":216,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":12.2},{"place":217,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":11.8},{"place":218,"model":"openchat-3.6-8b-20240522","company":"openchat","family":"OpenChat-3.5-7B-0106","version":"OpenChat-3.5-7B-0106","score":11.5},{"place":219,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":11.5},{"place":220,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":11.5},{"place":221,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":11.5},{"place":222,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":11.5},{"place":223,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":11.5},{"place":224,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":11.5},{"place":225,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":11.2},{"place":226,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":11.1},{"place":227,"model":"granite-code-20b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":10.8},{"place":228,"model":"autocoder-qw-7b","company":"autocoder","family":"Autocoder","version":"Autocoder","score":10.8},{"place":229,"model":"phi-3-mini-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":10.8},{"place":230,"model":"autocoder-s-6.7b","company":"autocoder","family":"Autocoder","version":"Autocoder","score":10.5},{"place":231,"model":"codegemma-7b-it","company":"google","family":"Codegemma","version":"Codegemma","score":10.5},{"place":232,"model":"codegemma-7b-it","company":"google","family":"Codegemma","version":"Codegemma","score":10.4},{"place":233,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":10.1},{"place":234,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":10.1},{"place":235,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":9.8},{"place":236,"model":"reflectioncoder-cl-7b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":9.5},{"place":237,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":9.5},{"place":238,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":9.5},{"place":239,"model":"reflectioncoder-cl-7b","company":"reflection","family":"Reflectioncoder","version":"Reflectioncoder","score":9.4},{"place":240,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":9.2},{"place":241,"model":"opencoder-1.5b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder-8B-Instruct","score":9.2},{"place":242,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":8.8},{"place":243,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":8.8},{"place":244,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":8.5},{"place":245,"model":"granite-3.0-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":8.5},{"place":246,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":8.4},{"place":247,"model":"granite-3.0-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":8.4},{"place":248,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":8.2},{"place":249,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":8.1},{"place":250,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":7.4},{"place":251,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":6.8},{"place":252,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":6.1},{"place":253,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":5.8},{"place":254,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":5.4},{"place":255,"model":"mistral-7b-instruct-v0.3","company":"mistral","family":"Mistral","version":"Mistral 0.3","score":5.4},{"place":256,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":5.4},{"place":257,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":5.4},{"place":258,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":4.8},{"place":259,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":4.7},{"place":260,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":4.7},{"place":261,"model":"opencodeinterpreter-ds-1.3b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":4.4},{"place":262,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":4.1},{"place":263,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":3.8},{"place":264,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":3.4},{"place":265,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":3.4},{"place":266,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":3.4},{"place":267,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":3.1},{"place":268,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":2.7},{"place":269,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":2.7},{"place":270,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1.4},{"place":271,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":1.4},{"place":272,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1}]},{"id":"biobench","name":"BIOBench","topic":"Biology reasoning","description":"Biology knowledge and reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":51.9,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.9},{"place":2,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":48},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.6},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":42.3},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":41.5}]},{"id":"biology-instruction","name":"Biology-Instruction","topic":"Biology multi-omics","description":"Multi-omics sequence reasoning benchmark for biological data understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-S2-Preview-397B","top_percent":56.92,"top_model_id":"intern-s2-preview-397b","top_generation":"Intern-S2","top_model_base":"Intern-S2-Preview-397B","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":56.92},{"place":2,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":55.71},{"place":3,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":52.5},{"place":4,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":52.45},{"place":5,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":51.4},{"place":6,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":43.95},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":13.87},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":12},{"place":9,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":10.7},{"place":10,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":10.52},{"place":11,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":10.2},{"place":12,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":9.62},{"place":13,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":9.14},{"place":14,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":7.68},{"place":15,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":7.67},{"place":16,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":6.83},{"place":17,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":6.78},{"place":18,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":6.34},{"place":19,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":6.2},{"place":20,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.75},{"place":21,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":4.49},{"place":22,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.16},{"place":23,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":3.77},{"place":24,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":2.77}]},{"id":"biolp-bench","name":"BioLP-Bench","topic":"Biomedical NLP","description":"Comprehensive biomedical language processing benchmark evaluating LLMs across tasks like NER, relation extraction, and QA.","url":"https://github.com/baceolus/BioLP-bench","leaderboard":"","github":"https://github.com/baceolus/BioLP-bench","paper":"","metric":"percent","stars":"","top_model":"Grok 4","top_percent":47,"top_model_id":"grok-4","top_generation":"Grok 4","top_model_base":"Grok 4","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":47},{"place":2,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":37},{"place":3,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":19.9}]},{"id":"biomysterybench","name":"BioMysteryBench","topic":"Biology research","description":"Anthropic biology research benchmark of open-ended data-analysis 'mysteries'; human-solved subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":90.1,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.1},{"place":2,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89},{"place":3,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":88.8},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":88.5},{"place":5,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87.5},{"place":6,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":87.1},{"place":7,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.9},{"place":8,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":83.8},{"place":9,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":82.6},{"place":10,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":80.6},{"place":11,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80.4},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":79.5},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":76.7},{"place":14,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":75.3},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.1},{"place":16,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":72.1},{"place":17,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":71.3},{"place":18,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":69},{"place":19,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":68},{"place":20,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.4},{"place":21,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.6},{"place":22,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":61.3},{"place":23,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":58.9},{"place":24,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":57.5},{"place":25,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":57.5},{"place":26,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":54.9},{"place":27,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":50.2},{"place":28,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":49.4},{"place":29,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":48.9},{"place":30,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":44.8},{"place":31,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":42.9},{"place":32,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":35.3},{"place":33,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":29.6},{"place":34,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":27},{"place":35,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":23.5},{"place":36,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":23.5},{"place":37,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":17.6}]},{"id":"biomysterybench-hard","name":"BioMysteryBench (Hard)","topic":"Biology research","description":"BioMysteryBench hard subset (problems not solved by human experts).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.8 Flash","top_percent":56.5,"top_model_id":"gemini-3.8-flash","top_generation":"Gemini 3.8","top_model_base":"Gemini 3.8 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":56.5},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":49.4},{"place":3,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":49.4},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":46.5},{"place":5,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":46.1},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":44.7},{"place":7,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":43.5},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":42.4},{"place":9,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":41.2},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":40},{"place":11,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":34.1},{"place":12,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":29.6},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":23.5},{"place":14,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":23.5},{"place":15,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":21.6},{"place":16,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":15.7},{"place":17,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":13.7},{"place":18,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":11.8},{"place":19,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":5.9},{"place":20,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":5.9},{"place":21,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":2},{"place":22,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":2}]},{"id":"bioreason-coding","name":"BioReason Coding","topic":"Genomics","description":"Coding variant-effect prediction from DNA (balanced accuracy).","url":"https://huggingface.co/HuggingFaceBio/Carbon-X","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Carbon-X","top_percent":74.9,"top_model_id":"carbon-x","top_generation":"Carbon","top_model_base":"Carbon-X","top_model_family":"Carbon","top_company":"huggingface","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"carbon-x","company":"huggingface","family":"Carbon","version":"Carbon","score":74.9},{"place":2,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":71},{"place":3,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":70.3},{"place":4,"model":"kimi-k3-low","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":53.9},{"place":5,"model":"glm-5.3-low","company":"zai","family":"GLM","version":"GLM 5.3","score":52.1},{"place":6,"model":"deepseek-v4.1-flash-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":51.4},{"place":7,"model":"gemini-4-argon-low","company":"google","family":"Gemini","version":"Gemini 4","score":6.5}]},{"id":"bioreason-non-snv","name":"BioReason Non-SNV","topic":"Genomics","description":"Complex (non-SNV) variant-effect prediction from DNA (balanced accuracy).","url":"https://huggingface.co/HuggingFaceBio/Carbon-X","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5 (max)","top_percent":94.8,"top_model_id":"claude-opus-5.5-max","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":94.8},{"place":2,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":91.7},{"place":3,"model":"gemini-4-argon-low","company":"google","family":"Gemini","version":"Gemini 4","score":90.3},{"place":4,"model":"carbon-x","company":"huggingface","family":"Carbon","version":"Carbon","score":85.1},{"place":5,"model":"kimi-k3-low","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":65.3},{"place":6,"model":"glm-5.3-low","company":"zai","family":"GLM","version":"GLM 5.3","score":60.1},{"place":7,"model":"deepseek-v4.1-flash-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":55.9}]},{"id":"bird-sql","name":"Bird-SQL","topic":"Text-to-SQL","description":"Natural language to SQL generation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.0 Pro","top_percent":59.3,"top_model_id":"gemini-2.0-pro","top_generation":"Gemini 2.0","top_model_base":"Gemini 2.0 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":34,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":59.3},{"place":2,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":58.7},{"place":3,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":54.4},{"place":4,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":54.4},{"place":5,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":54.4},{"place":6,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":47.9},{"place":7,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.75},{"place":8,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":47.49},{"place":9,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":46.7},{"place":10,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":45.76},{"place":11,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":45.6},{"place":12,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":44.59},{"place":13,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":44.04},{"place":14,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":43.5},{"place":15,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":42.7},{"place":16,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":42.18},{"place":17,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":41.85},{"place":18,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":41.8},{"place":19,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":41.07},{"place":20,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":39.67},{"place":21,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.6},{"place":22,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":39.34},{"place":23,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":39.2},{"place":24,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":38.9},{"place":25,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":38.69},{"place":26,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":38.4},{"place":27,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":38.4},{"place":28,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":38.25},{"place":29,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":37.32},{"place":30,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":36.3},{"place":31,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":36.11},{"place":32,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":33.8},{"place":33,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":12.2},{"place":34,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":6.4}]},{"id":"bixbench","name":"BixBench","topic":"Bioinformatics","description":"Benchmark of real-world bioinformatics and data-analysis tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":80.5,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":80.5},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":74}]},{"id":"blend","name":"BLEnD","topic":"Cultural understanding","description":"Benchmark assessing cultural knowledge, sensitivity, and language use across contexts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen2.5-72B-Instruct","top_percent":75.4,"top_model_id":"qwen2.5-72b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.4},{"place":2,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":35.91},{"place":3,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":33.47},{"place":4,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.48},{"place":5,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":30.49},{"place":6,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":28.31},{"place":7,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27.88},{"place":8,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.99},{"place":9,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":26.61},{"place":10,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":25.9},{"place":11,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":23.66},{"place":12,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":22.49},{"place":13,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":19.47}]},{"id":"blink","name":"BLINK","topic":"Multimodal grounding","description":"Evaluates visual-language grounding and reference resolution to reduce hallucinations.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.6 Flash","top_percent":89.2,"top_model_id":"gemini-3.6-flash","top_generation":"Gemini 3.6","top_model_base":"Gemini 3.6 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":169,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":89.2},{"place":2,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.9},{"place":3,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":87.9},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.4},{"place":5,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":87.3},{"place":6,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":86.1},{"place":7,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85.5},{"place":8,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":84.8},{"place":9,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":82.7},{"place":10,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":81.9},{"place":11,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.7},{"place":12,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":81.4},{"place":13,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":80.6},{"place":14,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":80.6},{"place":15,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":80.4},{"place":16,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":79.4},{"place":17,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":79.1},{"place":18,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":78.6},{"place":19,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":78.3},{"place":20,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":77.8},{"place":21,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77.49},{"place":22,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77.1},{"place":23,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":74.3},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.7},{"place":25,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":72.5},{"place":26,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":72.38},{"place":27,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":72.1},{"place":28,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.86},{"place":29,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.6},{"place":30,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":71.3},{"place":31,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.3},{"place":32,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":71.1},{"place":33,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":71},{"place":34,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.6},{"place":35,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":70.4},{"place":36,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":70.39},{"place":37,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":70.33},{"place":38,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":70.22},{"place":39,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.2},{"place":40,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":70.2},{"place":41,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":70.02},{"place":42,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.01},{"place":43,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.6},{"place":44,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":69.5},{"place":45,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.33},{"place":46,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.2},{"place":47,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.1},{"place":48,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":69},{"place":49,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":68.96},{"place":50,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":68.8},{"place":51,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":68.7},{"place":52,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":68.64},{"place":53,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.5},{"place":54,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":68.4},{"place":55,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":68},{"place":56,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67.81},{"place":57,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.7},{"place":58,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":67.7},{"place":59,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.3},{"place":60,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.1},{"place":61,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":66.91},{"place":62,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":66.79},{"place":63,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":66.65},{"place":64,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.6},{"place":65,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.6},{"place":66,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":66.59},{"place":67,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":66.5},{"place":68,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":66.33},{"place":69,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.8},{"place":70,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.64},{"place":71,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":65.5},{"place":72,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":65.5},{"place":73,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":65.3},{"place":74,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":65.2},{"place":75,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.2},{"place":76,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":65.11},{"place":77,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":65.1},{"place":78,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":65.1},{"place":79,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":65.1},{"place":80,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.1},{"place":81,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65},{"place":82,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":64.9},{"place":83,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.8},{"place":84,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":64.59},{"place":85,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":64.49},{"place":86,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":64.4},{"place":87,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":64.3},{"place":88,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":64.1},{"place":89,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":63.96},{"place":90,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":63.8},{"place":91,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":63.8},{"place":92,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":63.5},{"place":93,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":63.4},{"place":94,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":63.3},{"place":95,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":63.2},{"place":96,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":62.8},{"place":97,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.78},{"place":98,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":62.7},{"place":99,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":62.57},{"place":100,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":62.5},{"place":101,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":62.4},{"place":102,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":62.3},{"place":103,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":62},{"place":104,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":61.8},{"place":105,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":61.7},{"place":106,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":61.5},{"place":107,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61},{"place":108,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":60.7},{"place":109,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":60.1},{"place":110,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":60},{"place":111,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":59.9},{"place":112,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":59.5},{"place":113,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.3},{"place":114,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":59.2},{"place":115,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":59.1},{"place":116,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":58.9},{"place":117,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":58.71},{"place":118,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.7},{"place":119,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":58.7},{"place":120,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.4},{"place":121,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":58.3},{"place":122,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":58.2},{"place":123,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":58.1},{"place":124,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":57.8},{"place":125,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":57.8},{"place":126,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":57.5},{"place":127,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57.4},{"place":128,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57.2},{"place":129,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":57.2},{"place":130,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.8},{"place":131,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":56.8},{"place":132,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":56.7},{"place":133,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":56.4},{"place":134,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":56.4},{"place":135,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":56.4},{"place":136,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.3},{"place":137,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":56.2},{"place":138,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":56.1},{"place":139,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":56},{"place":140,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":55.5},{"place":141,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":55.5},{"place":142,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":55.4},{"place":143,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":55.4},{"place":144,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":55.4},{"place":145,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":54.9},{"place":146,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":54.8},{"place":147,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":54.7},{"place":148,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":54.6},{"place":149,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":54.6},{"place":150,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":54.39},{"place":151,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.8},{"place":152,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":53.5},{"place":153,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":53.3},{"place":154,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":53.2},{"place":155,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":53.1},{"place":156,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":53},{"place":157,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":52.9},{"place":158,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":52.7},{"place":159,"model":"llava-next-interleave-14b","company":"llava","family":"LLaVA","version":"LLaVA-Next-Interleave","score":52.6},{"place":160,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":52.5},{"place":161,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.2},{"place":162,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":52.1},{"place":163,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":52},{"place":164,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.8},{"place":165,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":51.7},{"place":166,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.6},{"place":167,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.4},{"place":168,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":51.3},{"place":169,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":51.03},{"place":170,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":50.97},{"place":171,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":50.9},{"place":172,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":50.8},{"place":173,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":50.8},{"place":174,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":50.8},{"place":175,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.6},{"place":176,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":50.5},{"place":177,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":50.5},{"place":178,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":50.2},{"place":179,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.2},{"place":180,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":48.97},{"place":181,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":48.9},{"place":182,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":48.82},{"place":183,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":48.8},{"place":184,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.6},{"place":185,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":48.4},{"place":186,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":47.8},{"place":187,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":47.3},{"place":188,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":47.1},{"place":189,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.8},{"place":190,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":46.6},{"place":191,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.3},{"place":192,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":46.2},{"place":193,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":46.1},{"place":194,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":45.9},{"place":195,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":45.8},{"place":196,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.2},{"place":197,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":44.5},{"place":198,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":44.4},{"place":199,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":44.2},{"place":200,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":44.19},{"place":201,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":44.1},{"place":202,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":44},{"place":203,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":44},{"place":204,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":43.92},{"place":205,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":43.8},{"place":206,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":43.29},{"place":207,"model":"vpg-c-7b","company":"zju","family":"VPG-C","version":"VPG-C","score":43.1},{"place":208,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":42.61},{"place":209,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":42.3},{"place":210,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":42.2},{"place":211,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":42.2},{"place":212,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":42},{"place":213,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":42},{"place":214,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":42},{"place":215,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":41.1},{"place":216,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":40.7},{"place":217,"model":"llama-3-vila1.5-8b","company":"nvidia","family":"LLaVA","version":"Llama-3-VILA1.5","score":39.3},{"place":218,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":38.6},{"place":219,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":36.6},{"place":220,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":36.2},{"place":221,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":35.24}]},{"id":"blueprint-bench-2","name":"Blueprint-Bench 2","topic":"Spatial reasoning","description":"Andon Labs agentic spatial-reasoning benchmark: reconstruct 2D floor plans from ~20 interior photos per apartment (50 apartments).","url":"https://arxiv.org/abs/2509.25229","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":38.6,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":38.6},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":36.2},{"place":3,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":33.6},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":26.5},{"place":5,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":24.5},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":14.5},{"place":7,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":6.7},{"place":8,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":0}]},{"id":"bob-hvr","name":"BoB-HVR","topic":"Composite capability index","description":"Hard, Versatile, and Relevant composite score across eight capability buckets.","url":"","leaderboard":"","github":"","paper":"","metric":"index (0-100)","stars":"","top_model":"Gemini 3 Pro","top_percent":18.25,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":18.25},{"place":2,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":18.04},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":16.23},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.09},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":15.63},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.4},{"place":7,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":12.13},{"place":8,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":8.07},{"place":9,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":8.07},{"place":10,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":7.52},{"place":11,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":7.09},{"place":12,"model":"gpt-o3","company":"openai","family":"o3","version":"o3","score":7},{"place":13,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":6.09},{"place":14,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":5.03}]},{"id":"bold","name":"BOLD","topic":"Bias evaluation","description":"Bias in Open-ended Language Dataset probing demographic biases in text generation.","url":"https://huggingface.co/datasets/AmazonScience/bold","leaderboard":"","github":"https://github.com/amazon-science/bold","paper":"https://arxiv.org/abs/2101.11718","metric":"score","stars":"","top_model":"Mixtral 8x 7B","top_percent":0.084,"top_model_id":"mixtral-8x7b","top_generation":"Mixtral","top_model_base":"Mixtral 8x 7B","top_model_family":"Mixtral","top_company":"mistral","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":0.084},{"place":2,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":0.094}]},{"id":"boolq","name":"BoolQ","topic":"Reading comprehension","description":"Yes/no QA from naturally occurring questions.","url":"https://github.com/google-research-datasets/boolean-questions","leaderboard":"https://llm-evals.formula-labs.com/","github":"https://github.com/google-research-datasets/boolean-questions","paper":"https://arxiv.org/pdf/1905.10044","metric":"percent","stars":"171","top_model":"ST-MoE-32B","top_percent":92.4,"top_model_id":"st-moe-32b","top_generation":"ST-MoE-32B","top_model_base":"ST-MoE-32B","top_model_family":"ST","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":154,"total_models":3854,"placements":[{"place":1,"model":"st-moe-32b","company":"google","family":"ST","version":"ST-MoE-32B","score":92.4},{"place":2,"model":"turing-nlr-v5","company":"microsoft","family":"Turing","version":"Turing NLR v5","score":92},{"place":3,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":91.9},{"place":4,"model":"hairuo","company":"generic","family":"Hairuo","version":"Hairuo","score":91.7},{"place":5,"model":"t5-plus-udg-single-model-google-brain","company":"google","family":"T5","version":"T5 + UDG, Single Model (Google Brain)","score":91.4},{"place":6,"model":"t5","company":"google","family":"T5","version":"T5","score":91.2},{"place":7,"model":"frozen-t5-1.1-plus-spot","company":"google","family":"Frozen","version":"Frozen T5 1.1 + SPoT","score":91.1},{"place":8,"model":"ernie-3.0","company":"baidu","family":"ERNIE","version":"ERNIE 3.0","score":91},{"place":9,"model":"vega-v2","company":"jd","family":"Vega","version":"Vega v2","score":90.5},{"place":10,"model":"deberta-turingnlrv4","company":"microsoft","family":"DeBERTa","version":"DeBERTa / TuringNLRv4","score":90.4},{"place":11,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.8},{"place":12,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":89.6},{"place":13,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":89.4},{"place":14,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":89.4},{"place":15,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":89.2},{"place":16,"model":"mapika-decider-4b","company":"mapika","family":"Decider","version":"Decider","score":89},{"place":17,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":88.9},{"place":18,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":88.84},{"place":19,"model":"roberta-icets","company":"infosys","family":"RoBERTa","version":"RoBERTa-iCETS","score":88.5},{"place":20,"model":"roberta-ensemble","company":"tencent","family":"RoBERTa","version":"RoBERTa (ensemble)","score":88.2},{"place":21,"model":"ailabs-team-transformers","company":"unknown","family":"AILabs","version":"AILabs Team, Transformers","score":88.1},{"place":22,"model":"pai-albert","company":"alibaba","family":"PAI","version":"PAI Albert","score":88.1},{"place":23,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":88},{"place":24,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":87.9},{"place":25,"model":"nezha-plus","company":"huawei","family":"NEZHA","version":"NEZHA-Plus","score":87.8},{"place":26,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":87.74},{"place":27,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.7},{"place":28,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":87.7},{"place":29,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":87.5},{"place":30,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":87.46},{"place":31,"model":"mapika-decider-2b","company":"mapika","family":"Decider","version":"Decider","score":87.3},{"place":32,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":87.2},{"place":33,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":87.1},{"place":34,"model":"roberta-mtl-adv","company":"zhuiyi","family":"RoBERTa","version":"RoBERTa-mtl-adv","score":87.1},{"place":35,"model":"roberta","company":"meta","family":"RoBERTa","version":"RoBERTa","score":87.1},{"place":36,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":86.7},{"place":37,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":86.67},{"place":38,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":86.61},{"place":39,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":86.6},{"place":40,"model":"hrm-text-1b","company":"sapient","family":"HRM","version":"HRM-Text","score":86.2},{"place":41,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":86.2},{"place":42,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":86.1},{"place":43,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":85.9},{"place":44,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.8},{"place":45,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.4},{"place":46,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":85.3},{"place":47,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":85},{"place":48,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":84.9},{"place":49,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":84.89},{"place":50,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":84.8},{"place":51,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":84.8},{"place":52,"model":"palm-62b","company":"google","family":"PaLM","version":"PaLM","score":84.8},{"place":53,"model":"bert-mtl","company":"ibm","family":"BERT","version":"BERT-mtl","score":84.8},{"place":54,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":84.7},{"place":55,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":84.6},{"place":56,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":84.59},{"place":57,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":84.43},{"place":58,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":84.4},{"place":59,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":84.3},{"place":60,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":84.2},{"place":61,"model":"palm-cont-62b","company":"google","family":"PaLM","version":"PaLM","score":83.9},{"place":62,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":83.9},{"place":63,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":83.8},{"place":64,"model":"chinchilla-70b","company":"google","family":"Chinchilla","version":"Chinchilla","score":83.7},{"place":65,"model":"bort-alexa-ai","company":"amazon","family":"Bort","version":"Bort (Alexa AI)","score":83.7},{"place":66,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":83.7},{"place":67,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":83.6},{"place":68,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":83.39},{"place":69,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":83.3},{"place":70,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":83.2},{"place":71,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":83.1},{"place":72,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":83.1},{"place":73,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":83},{"place":74,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":82.9},{"place":75,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":82.87},{"place":76,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":82.42},{"place":77,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":82.4},{"place":78,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":82.4},{"place":79,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":82.1},{"place":80,"model":"text-to-text-petl","company":"berkeley","family":"Text","version":"Text to Text PETL","score":82},{"place":81,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":81.7},{"place":82,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":81.7},{"place":83,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":81.7},{"place":84,"model":"gemma-3n-e4b","company":"google","family":"Gemma","version":"Gemma 3n","score":81.6},{"place":85,"model":"gemma-3n-e4b-instructed-litert-preview","company":"google","family":"Gemma","version":"Gemma 3n","score":81.6},{"place":86,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":81.28},{"place":87,"model":"phi-4-mini","company":"microsoft","family":"Phi","version":"Phi 4","score":81.2},{"place":88,"model":"ipet-albert-few-shot-32-examples","company":"lmu","family":"iPET","version":"iPET (ALBERT) - Few-Shot (32 Examples)","score":81.2},{"place":89,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":81.1},{"place":90,"model":"fsl-plus-plus-albert-few-shot-32-examples","company":"unknown","family":"FSL++(ALBERT)","version":"FSL++(ALBERT)-Few-Shot(32 Examples)","score":81.1},{"place":91,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":81.07},{"place":92,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":80.9},{"place":93,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":80.7},{"place":94,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":80.67},{"place":95,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.5},{"place":96,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":80.3},{"place":97,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":80},{"place":98,"model":"adapet-albert-few-shot","company":"unc","family":"ADAPET","version":"ADAPET (ALBERT) - few-shot","score":80},{"place":99,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":79.8},{"place":100,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":79.4},{"place":101,"model":"gopher-280b","company":"google","family":"Gopher","version":"Gopher","score":79.3},{"place":102,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":79.3},{"place":103,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":79.1},{"place":104,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":79},{"place":105,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":79},{"place":106,"model":"bert-plus-plus","company":"nyu","family":"BERT++","version":"BERT++","score":79},{"place":107,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":79},{"place":108,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":79},{"place":109,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":78.9},{"place":110,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":78.87},{"place":111,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":78.8},{"place":112,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":78.8},{"place":113,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":78.75},{"place":114,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":78.7},{"place":115,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":78.5},{"place":116,"model":"install-albert-few-shot-32examples","company":"casia","family":"INSTALL(ALBERT)","version":"INSTALL(ALBERT)-few-shot(32examples)","score":78.4},{"place":117,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":78.32},{"place":118,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":78.1},{"place":119,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":78},{"place":120,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":78},{"place":121,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":77.89},{"place":122,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":77.7},{"place":123,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":77.7},{"place":124,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":77.6},{"place":125,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":77.6},{"place":126,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":77.4},{"place":127,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":76.5},{"place":128,"model":"gemma-3n-e2b","company":"google","family":"Gemma","version":"Gemma 3n","score":76.4},{"place":129,"model":"gemma-3n-e2b-instructed-litert-preview","company":"google","family":"Gemma","version":"Gemma 3n","score":76.4},{"place":130,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":76.4},{"place":131,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":76.4},{"place":132,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":76.24},{"place":133,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":76.2},{"place":134,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":75.7},{"place":135,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":75.05},{"place":136,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":75},{"place":137,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":75},{"place":138,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":74.77},{"place":139,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":74.2},{"place":140,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":73},{"place":141,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":72.7},{"place":142,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":72.3},{"place":143,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":72.2},{"place":144,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.7},{"place":145,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":71.5},{"place":146,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":71},{"place":147,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":70.67},{"place":148,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":70.49},{"place":149,"model":"huginn-3.5b","company":"tomg-umd","family":"Huginn","version":"Huginn","score":69.8},{"place":150,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.69},{"place":151,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":69.4},{"place":152,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":68.8},{"place":153,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":68.5},{"place":154,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":68.5},{"place":155,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":68.41},{"place":156,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":68.01},{"place":157,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":68},{"place":158,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":67.52},{"place":159,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":67.5},{"place":160,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":67},{"place":161,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":66.82},{"place":162,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":66.51},{"place":163,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":65.5},{"place":164,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":64.2},{"place":165,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":64.1},{"place":166,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":64.1},{"place":167,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":63.9},{"place":168,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":63.52},{"place":169,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":63.2},{"place":170,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":63.2},{"place":171,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":63.18},{"place":172,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":62.51},{"place":173,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.5},{"place":174,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":62.45},{"place":175,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":62.29},{"place":176,"model":"select-step-by-step","company":"unknown","family":"select","version":"select-step-by-step","score":62.2},{"place":177,"model":"warp-albert-xxl-v2-few-shot-32-examples","company":"yerevann","family":"WARP","version":"WARP (ALBERT-XXL-V2) - Few-Shot (32 Examples)","score":62.2},{"place":178,"model":"trlm-135m","company":"loka","family":"TRLM","version":"TRLM","score":62.17},{"place":179,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":61.4},{"place":180,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":61.07},{"place":181,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":60.5},{"place":182,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":57.4},{"place":183,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":56.1},{"place":184,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":51.8},{"place":185,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":43.88},{"place":186,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":43.55},{"place":187,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":42.5}]},{"id":"borda-count-multilingual","name":"Borda Count (Multilingual)","topic":"Aggregate ranking","description":"Borda count aggregate ranking across multilingual benchmarks; lower is better.","url":"","leaderboard":"","github":"","paper":"","metric":"borda_count","stars":"","top_model":"Qwen3-32B","top_percent":2.9,"top_model_id":"qwen3-32b","top_generation":"Qwen3","top_model_base":"Qwen3 32B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":true,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.9},{"place":2,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.9},{"place":3,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":3.3},{"place":4,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":3.7},{"place":5,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":4.7},{"place":6,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":4.9},{"place":7,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":6.6},{"place":8,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":7.1}]},{"id":"bpomp-decision","name":"BPoMP (decision)","topic":"Preference prediction","description":"BPoMP preference decisions; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://huggingface.co/spaces/multimodalart/jev-decision-index","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef","top_percent":96.9,"top_model_id":"clef","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":96.9},{"place":2,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":96.8},{"place":3,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":95.8},{"place":4,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":95.4},{"place":5,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":95.1},{"place":6,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":94.1},{"place":7,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":93.8},{"place":8,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":92.6},{"place":9,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":91.3},{"place":10,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":91.1},{"place":11,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":90.6},{"place":12,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":90.5},{"place":13,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":90.3},{"place":14,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":90.1},{"place":15,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":89.5},{"place":16,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":87.1},{"place":17,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":86.9},{"place":18,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":86.7},{"place":19,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":85.1},{"place":20,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":82.4},{"place":21,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":81.8},{"place":22,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":80.8},{"place":23,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":76.6},{"place":24,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":73.4},{"place":25,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":71.3},{"place":26,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":67},{"place":27,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":61.3},{"place":28,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":58.9},{"place":29,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":58.2},{"place":30,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56.6},{"place":31,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":56},{"place":32,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":54.9},{"place":33,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":51.6},{"place":34,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":51.5},{"place":35,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":50.7},{"place":36,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":50.4},{"place":37,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":49.2},{"place":38,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":45.7}]},{"id":"brevity-benchmark","name":"Brevity Benchmark","topic":"Response conciseness","description":"NVIDIA benchmark measuring how concisely a model answers while staying correct (reported on Nemotron 3.5 Bolt cards).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nemotron-3.5-Bolt-E4B-4GB","top_percent":82.84,"top_model_id":"nemotron-3.5-bolt-e4b-4gb","top_generation":"Nemotron 3.5","top_model_base":"Nemotron-3.5 Bolt E4B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":82.84},{"place":2,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":82.52},{"place":3,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.99},{"place":4,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":78.49},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.35},{"place":6,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.17},{"place":7,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.6},{"place":8,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70.98}]},{"id":"bridgebench","name":"BridgeBench","topic":"Reasoning","description":"BridgeBench evaluation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":60.1,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":60.1},{"place":2,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":59.7},{"place":3,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":58.3},{"place":4,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":41.5}]},{"id":"bright-decision","name":"BRIGHT (decision)","topic":"Reasoning-intensive retrieval","description":"Rate candidate documents for BRIGHT queries; nDCG@10. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://brightbenchmark.github.io/","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"ndcg@10","stars":"","top_model":"GLiDE (no thinking, 28B)","top_percent":50.1,"top_model_id":"glide-no-thinking","top_generation":"GLiDE","top_model_base":"GLiDE","top_model_family":"GLiDE","top_company":"fastino","top_open_source":0,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":50.1},{"place":2,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":50.1},{"place":3,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":49.3},{"place":4,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":48.8},{"place":5,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":48.8},{"place":6,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":48.4},{"place":7,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":47.5},{"place":8,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":47.3},{"place":9,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":47},{"place":10,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":46},{"place":11,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":45.9},{"place":12,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":45.6},{"place":13,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":45.1},{"place":14,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":44.4},{"place":15,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":44.2},{"place":16,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":43.2},{"place":17,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":43},{"place":18,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":42.9},{"place":19,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":42},{"place":20,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":40.6},{"place":21,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":39.3},{"place":22,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":39.2},{"place":23,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":39},{"place":24,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":38.8},{"place":25,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":38.5},{"place":26,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":36.8},{"place":27,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":36.7},{"place":28,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":34.3},{"place":29,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":33.1},{"place":30,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":31.1},{"place":31,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":29.4},{"place":32,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":28.1},{"place":33,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":27.3},{"place":34,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":22.4},{"place":35,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":21.4},{"place":36,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":20.1},{"place":37,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":19.9},{"place":38,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":10.4}]},{"id":"brokenarxiv","name":"BrokenArXiv","topic":"Research math","description":"Benchmark of subtly broken/false statements derived from recent arXiv math papers; models must detect and prove or refute them.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":77.7,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":77.7},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.4},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":56.3},{"place":4,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":54.6},{"place":5,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":43.1},{"place":6,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":42.7},{"place":7,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":26.7}]},{"id":"browsecomp","name":"BrowseComp","topic":"Web browsing","description":"Web browsing comprehension and competence benchmark.","url":"https://openai.com/index/browsecomp/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nex-N2.5-Max","top_percent":92.6,"top_model_id":"nex-n2.5-max","top_generation":"Nex-N2.5","top_model_base":"Nex-N2.5 Max","top_model_family":"Nex","top_company":"nex-agi","top_open_source":1,"lower_is_better":false,"bench_models":212,"total_models":3854,"placements":[{"place":1,"model":"nex-n2.5-max","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":92.6},{"place":2,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":92.5},{"place":3,"model":"gpt-5.6-sol-ultra","company":"openai","family":"GPT","version":"GPT-5.6","score":92.2},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":92.2},{"place":5,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":91.67},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":91.5},{"place":7,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":91.3},{"place":8,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":91.2},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.8},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":90.4},{"place":11,"model":"apodex-h1","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":90.3},{"place":12,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":90.1},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":90.1},{"place":14,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":89.7},{"place":15,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":89.6},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":89.4},{"place":17,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":89.3},{"place":18,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":89},{"place":19,"model":"iris-pro","company":"allspark","family":"Iris","version":"Iris","score":88.6},{"place":20,"model":"mirothinker-h1","company":"miromind","family":"MiroThinker","version":"MiroThinker H1","score":88.2},{"place":21,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88},{"place":22,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88},{"place":23,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":87.9},{"place":24,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":87.5},{"place":25,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87.4},{"place":26,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":86.9},{"place":27,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":86.6},{"place":28,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":86.6},{"place":29,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":86.2},{"place":30,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.9},{"place":31,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":85.6},{"place":32,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":84.9},{"place":33,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84.8},{"place":34,"model":"xyz-aquila-pro","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":84.8},{"place":35,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84.7},{"place":36,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.4},{"place":37,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":84.3},{"place":38,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84.2},{"place":39,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":84.2},{"place":40,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84},{"place":41,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84},{"place":42,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":84},{"place":43,"model":"arex-2","company":"baai","family":"AREX","version":"AREX-2","score":84},{"place":44,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":83.7},{"place":45,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":83.7},{"place":46,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":83.5},{"place":47,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.4},{"place":48,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.4},{"place":49,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":83.4},{"place":50,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.4},{"place":51,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":83.3},{"place":52,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":83.2},{"place":53,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":83.2},{"place":54,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":82.8},{"place":55,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":82.7},{"place":56,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":82.7},{"place":57,"model":"arex-base","company":"baai","family":"AREX","version":"AREX","score":82.5},{"place":58,"model":"iris-mini","company":"allspark","family":"Iris","version":"Iris","score":82.2},{"place":59,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.4},{"place":60,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.2},{"place":61,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":79.9},{"place":62,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":79.8},{"place":63,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":79.8},{"place":64,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":79.7},{"place":65,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":79.3},{"place":66,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":79.3},{"place":67,"model":"xyz-aquila-mini","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":78.8},{"place":68,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.6},{"place":69,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":78.5},{"place":70,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.4},{"place":71,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":78},{"place":72,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":77.9},{"place":73,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":77.9},{"place":74,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":77.9},{"place":75,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":77.4},{"place":76,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":77.4},{"place":77,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":77.3},{"place":78,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.3},{"place":79,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":77.1},{"place":80,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":76.8},{"place":81,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":76.5},{"place":82,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":76.33},{"place":83,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":76.3},{"place":84,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":76.3},{"place":85,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":76.2},{"place":86,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":76.2},{"place":87,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":75.9},{"place":88,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":75.8},{"place":89,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":75.51},{"place":90,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":75.5},{"place":91,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":75.5},{"place":92,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.3},{"place":93,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":74.9},{"place":94,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":74.9},{"place":95,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":74.7},{"place":96,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":74.1},{"place":97,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":74.1},{"place":98,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":74},{"place":99,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":74},{"place":100,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":73.9},{"place":101,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.2},{"place":102,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.2},{"place":103,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":72.8},{"place":104,"model":"jais-3-375b-a23b","company":"g42","family":"Jais","version":"Jais 3","score":72.6},{"place":105,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":72.2},{"place":106,"model":"fort-searcher","company":"unknown","family":"FORT","version":"FORT","score":72.2},{"place":107,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":72.1},{"place":108,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":71.7},{"place":109,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":71.5},{"place":110,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":71.4},{"place":111,"model":"arex-turbo","company":"baai","family":"AREX","version":"AREX","score":70.7},{"place":112,"model":"nemotron-3.5-bolt-74b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70},{"place":113,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":69.8},{"place":114,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69},{"place":115,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":69},{"place":116,"model":"chatgpt-agent","company":"openai","family":"GPT","version":"ChatGPT","score":68.9},{"place":117,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":68.7},{"place":118,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":68},{"place":119,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.93},{"place":120,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":67.9},{"place":121,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.9},{"place":122,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.85},{"place":123,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.8},{"place":124,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.8},{"place":125,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":67.6},{"place":126,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.6},{"place":127,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.6},{"place":128,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":67.6},{"place":129,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":67.6},{"place":130,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":67.5},{"place":131,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":67.1},{"place":132,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":66.8},{"place":133,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":65.8},{"place":134,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":65.8},{"place":135,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":65.8},{"place":136,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":65.7},{"place":137,"model":"quest-35b","company":"osunlp","family":"QUEST","version":"QUEST","score":64.6},{"place":138,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64},{"place":139,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.8},{"place":140,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":63.5},{"place":141,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63},{"place":142,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":62},{"place":143,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":62},{"place":144,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62},{"place":145,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":61.3},{"place":146,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":61.3},{"place":147,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61},{"place":148,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61},{"place":149,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":61},{"place":150,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":60.6},{"place":151,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":60.6},{"place":152,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":60.2},{"place":153,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":59.4},{"place":154,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.4},{"place":155,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":59.2},{"place":156,"model":"gemini-deepresearch","company":"google","family":"Gemini","version":"Gemini DeepResearch","score":59.2},{"place":157,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":59},{"place":158,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":58.3},{"place":159,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.1},{"place":160,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":57.4},{"place":161,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":57},{"place":162,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":56.6},{"place":163,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":56.4},{"place":164,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":56.1},{"place":165,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":55.2},{"place":166,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":54.9},{"place":167,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":54.9},{"place":168,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":54.9},{"place":169,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":54.1},{"place":170,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":53.9},{"place":171,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53.5},{"place":172,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":53.1},{"place":173,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":52},{"place":174,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":52},{"place":175,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":51.6},{"place":176,"model":"openai-deepresearch","company":"openai","family":"DeepResearch","version":"DeepResearch","score":51.5},{"place":177,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":51.4},{"place":178,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":51.4},{"place":179,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":50.8},{"place":180,"model":"o3","company":"openai","family":"o3","version":"o3","score":49.7},{"place":181,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":49.5},{"place":182,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":49.2},{"place":183,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":48.74},{"place":184,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":48.62},{"place":185,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":48.6},{"place":186,"model":"smtl-30b","company":"oppo","family":"SMTL","version":"SMTL","score":48.6},{"place":187,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":48.5},{"place":188,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":48.1},{"place":189,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":47.4},{"place":190,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.2},{"place":191,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":47.1},{"place":192,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46.9},{"place":193,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":46.4},{"place":194,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":45.4},{"place":195,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":45.1},{"place":196,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":44.8},{"place":197,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":44.4},{"place":198,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":44},{"place":199,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":44},{"place":200,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.9},{"place":201,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.9},{"place":202,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":43.4},{"place":203,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":42.8},{"place":204,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":41.5},{"place":205,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":41.5},{"place":206,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.5},{"place":207,"model":"mirothinker-v1.0-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker-v1.0","score":41.2},{"place":208,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":41.1},{"place":209,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":40.9},{"place":210,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.5},{"place":211,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.1},{"place":212,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.1},{"place":213,"model":"webleaper-30b-a3b","company":"tongyi","family":"WebLeaper","version":"WebLeaper","score":38.8},{"place":214,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":38.5},{"place":215,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":38},{"place":216,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.8},{"place":217,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":37.3},{"place":218,"model":"iterresearch-30b-a3b","company":"tongyi","family":"IterResearch","version":"IterResearch","score":37.3},{"place":219,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":37},{"place":220,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":37},{"place":221,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":36.97},{"place":222,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":36.81},{"place":223,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.5},{"place":224,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":35.5},{"place":225,"model":"websailor-v2-30b-a3b","company":"tongyi","family":"WebSailor","version":"WebSailor-V2","score":35.3},{"place":226,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":33.89},{"place":227,"model":"deepminer-32b-rl","company":"alibaba","family":"DeepMiner","version":"DeepMiner","score":33.5},{"place":228,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":31.4},{"place":229,"model":"marco-deepresearch-8b","company":"alibaba","family":"Marco","version":"Marco DeepResearch","score":31.4},{"place":230,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":31.3},{"place":231,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":31.28},{"place":232,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":31.2},{"place":233,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":31.1},{"place":234,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":30},{"place":235,"model":"re-trac-4b","company":"microsoft","family":"RE-TRAC","version":"RE-TRAC","score":30},{"place":236,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":29.7},{"place":237,"model":"openseeker-v1-30b-sft","company":"polarseeker","family":"OpenSeeker","version":"OpenSeeker-v1","score":29.5},{"place":238,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":29.4},{"place":239,"model":"dr-venus-4b-rl","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":29.1},{"place":240,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":29.1},{"place":241,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":28.7},{"place":242,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":28.3},{"place":243,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":28.3},{"place":244,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":26.9},{"place":245,"model":"dr-venus-4b-sft","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":26.8},{"place":246,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":26.4},{"place":247,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.3},{"place":248,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25.5},{"place":249,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":25},{"place":250,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":24.1},{"place":251,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":24.1},{"place":252,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":24.1},{"place":253,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":23.8},{"place":254,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":22.77},{"place":255,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":21.3},{"place":256,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":21.3},{"place":257,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":19.6},{"place":258,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":19.6},{"place":259,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":19.43},{"place":260,"model":"toolmind-web-3b","company":"boss","family":"Nanbeige","version":"ToolMind-Web","score":17.4},{"place":261,"model":"mirothinker-v0.2-32b","company":"miromind","family":"MiroThinker","version":"MiroThinker v0.2","score":17.2},{"place":262,"model":"webexplorer-8b","company":"hkust","family":"WebExplorer","version":"WebExplorer","score":15.7},{"place":263,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":14.7},{"place":264,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":14.5},{"place":265,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.3},{"place":266,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":14.1},{"place":267,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":14.1},{"place":268,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":13.74},{"place":269,"model":"offseeker-8b-dpo","company":"offseeker","family":"OffSeeker","version":"OffSeeker","score":12.8},{"place":270,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":12.2},{"place":271,"model":"offseeker-8b-sft","company":"offseeker","family":"OffSeeker","version":"OffSeeker","score":10.6},{"place":272,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":10},{"place":273,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":10},{"place":274,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":9.9},{"place":275,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.3},{"place":276,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.3},{"place":277,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":7.8},{"place":278,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":7.6},{"place":279,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":7.4},{"place":280,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":7.1},{"place":281,"model":"websailor-7b","company":"tongyi","family":"WebSailor","version":"WebSailor","score":6.7},{"place":282,"model":"deepdive-9b-rl","company":"zai","family":"DeepDive","version":"DeepDive","score":6.3},{"place":283,"model":"deepdive-9b-sft","company":"zai","family":"DeepDive","version":"DeepDive","score":5.6},{"place":284,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":4.4},{"place":285,"model":"webdancer-32b","company":"tongyi","family":"WebDancer","version":"WebDancer","score":3.8},{"place":286,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.7},{"place":287,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":3.1},{"place":288,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":2.9},{"place":289,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":2.8},{"place":290,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":2.29}]},{"id":"browsecomp-agent-swarm","name":"BrowseComp (Agent Swarm)","topic":"Web browsing agents","description":"BrowseComp evaluated with Moonshot's Agent Swarm multi-agent orchestration (parallel sub-agents) instead of a single agent.","url":"https://openai.com/index/browsecomp/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2.6 Thinking","top_percent":86.3,"top_model_id":"kimi-k2.6-thinking","top_generation":"Kimi K2.6","top_model_base":"Kimi K2.6","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":86.3},{"place":2,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.4}]},{"id":"browsecomp-plus","name":"BrowseComp-Plus","topic":"Deep research","description":"BrowseComp-Plus: BrowseComp questions over a fixed, curated document corpus for reproducible deep-research agent evaluation.","url":"https://github.com/texttron/BrowseComp-Plus","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Jais-3-32B","top_percent":71.9,"top_model_id":"jais-3-32b","top_generation":"Jais 3","top_model_base":"Jais 3-32B","top_model_family":"Jais","top_company":"g42","top_open_source":1,"lower_is_better":false,"bench_models":34,"total_models":3854,"placements":[{"place":1,"model":"jais-3-32b","company":"g42","family":"Jais","version":"Jais 3","score":71.9},{"place":2,"model":"jais-3-mova-36b-a4b","company":"g42","family":"Jais","version":"Jais 3","score":71.8},{"place":3,"model":"jais-3-7b","company":"g42","family":"Jais","version":"Jais 3","score":67.7},{"place":4,"model":"jais-3-3.7b","company":"g42","family":"Jais","version":"Jais 3","score":64.8},{"place":5,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":58},{"place":6,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":55.7},{"place":7,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":55.18},{"place":8,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":53},{"place":9,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":52.8},{"place":10,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.6},{"place":11,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":50.5},{"place":12,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.5},{"place":13,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":45.78},{"place":14,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.5},{"place":15,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":41.1},{"place":16,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34.8},{"place":17,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":32.2},{"place":18,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.23},{"place":19,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":26.89},{"place":20,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.46},{"place":21,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21.9},{"place":22,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21.2},{"place":23,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":16.4},{"place":24,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15.9},{"place":25,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":14.1},{"place":26,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.7},{"place":27,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":11.3},{"place":28,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":9.9},{"place":29,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.31},{"place":30,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":8.3},{"place":31,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":7.7},{"place":32,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":3.9},{"place":33,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":1.8},{"place":34,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":1.7},{"place":35,"model":"granite-4.0-h-3b-ar","company":"IBM","family":"Granite","version":"Granite 4.0","score":0.6},{"place":36,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":0.4},{"place":37,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":0.4},{"place":38,"model":"allam-7b-instruct-preview","company":"humain","family":"ALLaM","version":"ALLaM","score":0.1},{"place":39,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":0.1},{"place":40,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":0}]},{"id":"browsecomp-vl","name":"BrowseComp-VL","topic":"Multimodal browsing","description":"Vision-language variant of BrowseComp requiring multimodal web browsing.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":65.68,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":65.68},{"place":2,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":58.96},{"place":3,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":57.12},{"place":4,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":51.9},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":45.4},{"place":6,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":42.9},{"place":7,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":40.8},{"place":8,"model":"skywork-r1v4","company":"skywork","family":"Skywork","version":"Skywork R1V4","score":38.4},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":35.9},{"place":10,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":31.6},{"place":11,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30}]},{"id":"browsecomp-with-content-manager","name":"BrowseComp (With Content Manager)","topic":"Web browsing","description":"BrowseComp benchmark evaluated with content manager assistance.","url":"https://openai.com/index/browsecomp/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":91.2,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":91.2},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":86.2},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.9},{"place":4,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":84.9},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.4},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":84.3},{"place":7,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":84.2},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84},{"place":9,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.4},{"place":10,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":83.3},{"place":11,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":82.7},{"place":12,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":79.3},{"place":13,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":76.6},{"place":14,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":76.3},{"place":15,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":75.9},{"place":16,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":74.9},{"place":17,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":74.9},{"place":18,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.5},{"place":19,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.2},{"place":20,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":73.1},{"place":21,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":70},{"place":22,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":69},{"place":23,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.8},{"place":24,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.6},{"place":25,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.6},{"place":26,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":67.5},{"place":27,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":67.5},{"place":28,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":65.8},{"place":29,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":62},{"place":30,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":62},{"place":31,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":60.2},{"place":32,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":59.2},{"place":33,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":58.3},{"place":34,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.8},{"place":35,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":57.5},{"place":36,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":56.9},{"place":37,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":26.1}]},{"id":"browsecomp-zh","name":"BrowseComp_zh","topic":"Web browsing (Chinese)","description":"Chinese variant of the BrowseComp web browsing benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"XYZ-Aquila-pro","top_percent":85.1,"top_model_id":"xyz-aquila-pro","top_generation":"XYZ-Aquila","top_model_base":"XYZ-Aquila pro","top_model_family":"XYZ-Aquila","top_company":"xyzlab","top_open_source":1,"lower_is_better":false,"bench_models":101,"total_models":3854,"placements":[{"place":1,"model":"xyz-aquila-pro","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":85.1},{"place":2,"model":"iris-pro","company":"allspark","family":"Iris","version":"Iris","score":85.1},{"place":3,"model":"iris-mini","company":"allspark","family":"Iris","version":"Iris","score":84.8},{"place":4,"model":"mirothinker-h1","company":"miromind","family":"MiroThinker","version":"MiroThinker H1","score":84.4},{"place":5,"model":"apodex-h1","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":84.1},{"place":6,"model":"xyz-aquila-mini","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":82.9},{"place":7,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":82.6},{"place":8,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":82.4},{"place":9,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":81.3},{"place":10,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.6},{"place":11,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":80.6},{"place":12,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80.3},{"place":13,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":79.6},{"place":14,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":79.6},{"place":15,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":77.7},{"place":16,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":76.1},{"place":17,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":75.8},{"place":18,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":75.3},{"place":19,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":75.1},{"place":20,"model":"fort-searcher","company":"unknown","family":"FORT","version":"FORT","score":75},{"place":21,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":73.7},{"place":22,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73},{"place":23,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":72.7},{"place":24,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":72.3},{"place":25,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":71.9},{"place":26,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":71.9},{"place":27,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":71.5},{"place":28,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.3},{"place":29,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":30,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.6},{"place":31,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.5},{"place":32,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":69.2},{"place":33,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":69},{"place":34,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67.1},{"place":35,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":66.9},{"place":36,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":66.8},{"place":37,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":66.8},{"place":38,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":66.6},{"place":39,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":66.6},{"place":40,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":65},{"place":41,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":65},{"place":42,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":65},{"place":43,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65},{"place":44,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":65},{"place":45,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":64.71},{"place":46,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":63.67},{"place":47,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":63},{"place":48,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":63},{"place":49,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.4},{"place":50,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":62.3},{"place":51,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":62.3},{"place":52,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.1},{"place":53,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":61.94},{"place":54,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":61.9},{"place":55,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":60.9},{"place":56,"model":"o3","company":"openai","family":"o3","version":"o3","score":58.1},{"place":57,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":55.6},{"place":58,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.6},{"place":59,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":51.2},{"place":60,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":49.5},{"place":61,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":49.5},{"place":62,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":49.2},{"place":63,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":49.2},{"place":64,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":48.5},{"place":65,"model":"openseeker-v1-30b-sft","company":"polarseeker","family":"OpenSeeker","version":"OpenSeeker-v1","score":48.4},{"place":66,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":47.9},{"place":67,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":47.9},{"place":68,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":47.8},{"place":69,"model":"mirothinker-v1.0-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker-v1.0","score":47.8},{"place":70,"model":"marco-deepresearch-8b","company":"alibaba","family":"Marco","version":"Marco DeepResearch","score":47.1},{"place":71,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":46.7},{"place":72,"model":"iterresearch-30b-a3b","company":"tongyi","family":"IterResearch","version":"IterResearch","score":45.2},{"place":73,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":45},{"place":74,"model":"websailor-v2-30b-a3b","company":"tongyi","family":"WebSailor","version":"WebSailor-V2","score":44.1},{"place":75,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":43.5},{"place":76,"model":"openai-deepresearch","company":"openai","family":"DeepResearch","version":"DeepResearch","score":42.9},{"place":77,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":42.9},{"place":78,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.4},{"place":79,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.4},{"place":80,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":40.8},{"place":81,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":40.2},{"place":82,"model":"deepminer-32b-rl","company":"alibaba","family":"DeepMiner","version":"DeepMiner","score":40.1},{"place":83,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.6},{"place":84,"model":"dr-venus-4b-rl","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":37.7},{"place":85,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":37.5},{"place":86,"model":"re-trac-4b","company":"microsoft","family":"RE-TRAC","version":"RE-TRAC","score":36.1},{"place":87,"model":"dr-venus-4b-sft","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":35.7},{"place":88,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":34.6},{"place":89,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":32.2},{"place":90,"model":"webexplorer-8b","company":"hkust","family":"WebExplorer","version":"WebExplorer","score":32},{"place":91,"model":"toolmind-web-3b","company":"boss","family":"Nanbeige","version":"ToolMind-Web","score":30.8},{"place":92,"model":"mirothinker-v0.2-32b","company":"miromind","family":"MiroThinker","version":"MiroThinker v0.2","score":29.4},{"place":93,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":29.1},{"place":94,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":29.1},{"place":95,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":29.1},{"place":96,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":29},{"place":97,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":28.8},{"place":98,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":28.8},{"place":99,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":28.7},{"place":100,"model":"offseeker-8b-dpo","company":"offseeker","family":"OffSeeker","version":"OffSeeker","score":26.6},{"place":101,"model":"offseeker-8b-sft","company":"offseeker","family":"OffSeeker","version":"OffSeeker","score":24.2},{"place":102,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":22.2},{"place":103,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":21.1},{"place":104,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.2},{"place":105,"model":"webdancer-32b","company":"tongyi","family":"WebDancer","version":"WebDancer","score":18},{"place":106,"model":"deepdive-9b-sft","company":"zai","family":"DeepDive","version":"DeepDive","score":15.7},{"place":107,"model":"deepdive-9b-rl","company":"zai","family":"DeepDive","version":"DeepDive","score":15.1},{"place":108,"model":"websailor-7b","company":"tongyi","family":"WebSailor","version":"WebSailor","score":14.2},{"place":109,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":13.2},{"place":110,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":9.8},{"place":111,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":7},{"place":112,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.7},{"place":113,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.3}]},{"id":"brumo25","name":"BRuMo25","topic":"Math competition","description":"BruMo 2025 olympiad-style mathematics benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2.5 Thinking","top_percent":98.3,"top_model_id":"kimi-k2.5-thinking","top_generation":"Kimi K2.5","top_model_base":"Kimi K2.5","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":98.3},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":98.3},{"place":3,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":96.7},{"place":4,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":95.8},{"place":5,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":95},{"place":6,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":93.8},{"place":7,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":92.5},{"place":8,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":92.5},{"place":9,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":91.7},{"place":10,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":90},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90},{"place":12,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":86.7},{"place":13,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":86.7},{"place":14,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.5},{"place":15,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.3},{"place":16,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":80.8},{"place":17,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.4},{"place":18,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":79.8},{"place":19,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":78.8},{"place":20,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.7},{"place":21,"model":"questa-nemotron-1.5b","company":"amazon","family":"Nemotron","version":"QuestA Nemotron","score":69.48},{"place":22,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":69},{"place":23,"model":"deepseek-r1-distill-32b","company":"deepseek","family":"DeepSeek-R1","version":"32B","score":68},{"place":24,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":66.5},{"place":25,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":62.7},{"place":26,"model":"nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":58.23},{"place":27,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":49.2},{"place":28,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":44.06}]},{"id":"business-arena","name":"Business Arena","topic":"Business simulation","description":"Simulated business-operation arena; final profit/value in USD achieved by the agent.","url":"","leaderboard":"","github":"","paper":"","metric":"usd","stars":"","top_model":"GPT-5.6 Sol","top_percent":168867,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":168867},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":89423},{"place":3,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":79868},{"place":4,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":66292},{"place":5,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":56477},{"place":6,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":55742},{"place":7,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":44751},{"place":8,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40804},{"place":9,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":33626},{"place":10,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":13325}]},{"id":"buzzbench","name":"BuzzBench","topic":"Humor analysis","description":"A humour analysis benchmark.","url":"","leaderboard":"https://eqbench.com/buzzbench.html","github":"https://github.com/EQ-bench","paper":"https://arxiv.org/abs/2312.06281","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":71.09,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.09},{"place":2,"model":"gemini-2.5-pro-preview-03-25","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.09},{"place":3,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":69.11},{"place":4,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":69.11},{"place":5,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":68.2},{"place":6,"model":"quasar-alpha","company":"quasar","family":"Quasar","version":"Quasar","score":67.85},{"place":7,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":67.1},{"place":8,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":62.73},{"place":9,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":61.94},{"place":10,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":59.48},{"place":11,"model":"o1","company":"openai","family":"o1","version":"o1","score":59.28},{"place":12,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":54.9},{"place":13,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":54.39},{"place":14,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":53.34},{"place":15,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":51.76},{"place":16,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":51.63},{"place":17,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":47.48},{"place":18,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":46.18},{"place":19,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":45.94},{"place":20,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.89},{"place":21,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":45.7},{"place":22,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":39},{"place":23,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":38.67},{"place":24,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":32.88},{"place":25,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":32.3},{"place":26,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":31.42},{"place":27,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":26.55},{"place":28,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":9.51}]},{"id":"c-eval","name":"C-Eval","topic":"Chinese exams","description":"Chinese college-level exam benchmark.","url":"https://github.com/SJTU-LIT/ceval","leaderboard":"","github":"","paper":"","metric":"percent","stars":"1768","top_model":"Kimi-K2.5","top_percent":94,"top_model_id":"kimi-k2.5","top_generation":"Kimi K2.5","top_model_base":"Kimi K2.5","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":330,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":94},{"place":2,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":93.7},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.4},{"place":4,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":93.3},{"place":5,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.1},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93},{"place":7,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":92.9},{"place":8,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":92.8},{"place":9,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":92.5},{"place":10,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":92.2},{"place":11,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.2},{"place":12,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":92.1},{"place":13,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":92.1},{"place":14,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":92.1},{"place":15,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":92},{"place":16,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.9},{"place":17,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":91.9},{"place":18,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":91.51},{"place":19,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":91.5},{"place":20,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":91.4},{"place":21,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":91},{"place":22,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":91},{"place":23,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":91},{"place":24,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":90.91},{"place":25,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":90.74},{"place":26,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.7},{"place":27,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":90.6},{"place":28,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":90.5},{"place":29,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":90.5},{"place":30,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.5},{"place":31,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.4},{"place":32,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":90.35},{"place":33,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.2},{"place":34,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":90.1},{"place":35,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":90},{"place":36,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90},{"place":37,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":90},{"place":38,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":89.8},{"place":39,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":89.76},{"place":40,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":89.7},{"place":41,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":89.6},{"place":42,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":89.4},{"place":43,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":89.38},{"place":44,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":89.36},{"place":45,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.2},{"place":46,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":89.1},{"place":47,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":88.6},{"place":48,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":88.6},{"place":49,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":88.5},{"place":50,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.2},{"place":51,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.17},{"place":52,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.12},{"place":53,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":88.03},{"place":54,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":87.9},{"place":55,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":87.86},{"place":56,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":87.7},{"place":57,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":87.54},{"place":58,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.4},{"place":59,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.3},{"place":60,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":87.2},{"place":61,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":86.93},{"place":62,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":86.9},{"place":63,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":86.9},{"place":64,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":86.8},{"place":65,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86.75},{"place":66,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":86.71},{"place":67,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":86.55},{"place":68,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.5},{"place":69,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.1},{"place":70,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.1},{"place":71,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":86},{"place":72,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86},{"place":73,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":85.84},{"place":74,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":85.76},{"place":75,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":85.21},{"place":76,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.1},{"place":77,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":85},{"place":78,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":84.1},{"place":79,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":83.8},{"place":80,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":83.8},{"place":81,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83.7},{"place":82,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83.5},{"place":83,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":83.3},{"place":84,"model":"qwen-72b","company":"qwen","family":"Qwen","version":"Qwen","score":83.3},{"place":85,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":83.2},{"place":86,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":83.2},{"place":87,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.6},{"place":88,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.5},{"place":89,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.2},{"place":90,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.2},{"place":91,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":82.2},{"place":92,"model":"skywork-moe-base","company":"skywork","family":"Skywork","version":"Skywork-MoE","score":82.2},{"place":93,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":82.17},{"place":94,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":82},{"place":95,"model":"yi-34b-200k","company":"01ai","family":"Yi","version":"Yi","score":81.9},{"place":96,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":81.8},{"place":97,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":81.8},{"place":98,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":81.7},{"place":99,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.52},{"place":100,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":81.4},{"place":101,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":81.4},{"place":102,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":81.36},{"place":103,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":80.9},{"place":104,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":80.9},{"place":105,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.6},{"place":106,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":80.59},{"place":107,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":80.5},{"place":108,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.4},{"place":109,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.2},{"place":110,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":80.2},{"place":111,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":80.16},{"place":112,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":80.1},{"place":113,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":79.7},{"place":114,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":79.5},{"place":115,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":79.5},{"place":116,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":79.4},{"place":117,"model":"qwen1.5-moe-a2.7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":79.2},{"place":118,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":79},{"place":119,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":78.97},{"place":120,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":78.7},{"place":121,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":78.6},{"place":122,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":78.59},{"place":123,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":78.53},{"place":124,"model":"openpangu-embedded-7b-v1.1","company":"huawei","family":"openPangu-Embedded","version":"openPangu-Embedded-V1.1","score":78.5},{"place":125,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":78.5},{"place":126,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":78.48},{"place":127,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":78.4},{"place":128,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.12},{"place":129,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":78},{"place":130,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":77.9},{"place":131,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":77.9},{"place":132,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":77.6},{"place":133,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":77.5},{"place":134,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":77.3},{"place":135,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":77.27},{"place":136,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":77.2},{"place":137,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":77.1},{"place":138,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":76.7},{"place":139,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":76.7},{"place":140,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.67},{"place":141,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.5},{"place":142,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":76.2},{"place":143,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":76.1},{"place":144,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":76},{"place":145,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":75.89},{"place":146,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":75.6},{"place":147,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":75.4},{"place":148,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.16},{"place":149,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":75},{"place":150,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.22},{"place":151,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.2},{"place":152,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.1},{"place":153,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":73.9},{"place":154,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":73.85},{"place":155,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":73.6},{"place":156,"model":"yi-6b-200k","company":"01ai","family":"Yi","version":"Yi","score":73.5},{"place":157,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":73.4},{"place":158,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.2},{"place":159,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":73.03},{"place":160,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":72.9},{"place":161,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":72.8},{"place":162,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":72.72},{"place":163,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":72.7},{"place":164,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":72.5},{"place":165,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":72.4},{"place":166,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":72.3},{"place":167,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":72.29},{"place":168,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":72.1},{"place":169,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":72},{"place":170,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":71.9},{"place":171,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":71.8},{"place":172,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":71.7},{"place":173,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":71.7},{"place":174,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":71.5},{"place":175,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":71.4},{"place":176,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":71.4},{"place":177,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":70.88},{"place":178,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":70.81},{"place":179,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":70.6},{"place":180,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":70.5},{"place":181,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":70.1},{"place":182,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":70.06},{"place":183,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":69.9},{"place":184,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":69.8},{"place":185,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":69.1},{"place":186,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":69},{"place":187,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":69},{"place":188,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.9},{"place":189,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":68.9},{"place":190,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":68.8},{"place":191,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":68.7},{"place":192,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":68.6},{"place":193,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":68.5},{"place":194,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":68.4},{"place":195,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":68.1},{"place":196,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":68},{"place":197,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":67.9},{"place":198,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":67.75},{"place":199,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.7},{"place":200,"model":"qwen1.5-4b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":67.6},{"place":201,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":67.5},{"place":202,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":67.5},{"place":203,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":67.3},{"place":204,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":67.2},{"place":205,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":66.76},{"place":206,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":66.6},{"place":207,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":66.54},{"place":208,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":66.54},{"place":209,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.2},{"place":210,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":66.11},{"place":211,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":66.1},{"place":212,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":65.96},{"place":213,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":65.8},{"place":214,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":65.56},{"place":215,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":65.2},{"place":216,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":65.2},{"place":217,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":64.6},{"place":218,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":63.8},{"place":219,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":63.7},{"place":220,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":63.5},{"place":221,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":63.5},{"place":222,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.2},{"place":223,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":63.1},{"place":224,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":63.1},{"place":225,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":63.1},{"place":226,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":63.07},{"place":227,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":63.07},{"place":228,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":63},{"place":229,"model":"kwaiyii-13b-base","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":62.6},{"place":230,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":62.1},{"place":231,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":62},{"place":232,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":61.8},{"place":233,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":61.6},{"place":234,"model":"chatglm2-12b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":61.6},{"place":235,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":61.6},{"place":236,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":61.5},{"place":237,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":61.4},{"place":238,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":61},{"place":239,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":60.9},{"place":240,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":60.8},{"place":241,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":60.8},{"place":242,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":60.74},{"place":243,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":60.7},{"place":244,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":60.6},{"place":245,"model":"skywork-13b","company":"skywork","family":"Skywork","version":"Skywork","score":60.6},{"place":246,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":60.5},{"place":247,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":60.4},{"place":248,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":60.4},{"place":249,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":60.3},{"place":250,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":60.1},{"place":251,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":60.1},{"place":252,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":60},{"place":253,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":59.8},{"place":254,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":59.7},{"place":255,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":59.7},{"place":256,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":59.7},{"place":257,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":59.6},{"place":258,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":59.6},{"place":259,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":59.4},{"place":260,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":59.3},{"place":261,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":59.2},{"place":262,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":59.18},{"place":263,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":59.1},{"place":264,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":59.1},{"place":265,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":59.01},{"place":266,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":59},{"place":267,"model":"kwaiyii-13b-chat","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":59},{"place":268,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":58.96},{"place":269,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":58.8},{"place":270,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":58.74},{"place":271,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.7},{"place":272,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":58.57},{"place":273,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":58.2},{"place":274,"model":"minicpm-moe-8x2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":58.11},{"place":275,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":58.1},{"place":276,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":57.98},{"place":277,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":57.8},{"place":278,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":57.68},{"place":279,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":57.5},{"place":280,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":57.1},{"place":281,"model":"chatglm2-12b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":57},{"place":282,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":56.97},{"place":283,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":56.8},{"place":284,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":56.74},{"place":285,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":56.7},{"place":286,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":56.7},{"place":287,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":56.7},{"place":288,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":56.7},{"place":289,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":56.3},{"place":290,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":56.3},{"place":291,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":56.2},{"place":292,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":56.2},{"place":293,"model":"baichuan2-13b-chat-4bits","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":56.05},{"place":294,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":55.6},{"place":295,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":55.6},{"place":296,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":55.42},{"place":297,"model":"xverse-7b-chat","company":"xverse","family":"XVERSE","version":"XVERSE","score":55.4},{"place":298,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":55.4},{"place":299,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":55.3},{"place":300,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":55.2},{"place":301,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":55},{"place":302,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":54.8},{"place":303,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":54.75},{"place":304,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":54.7},{"place":305,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":54.7},{"place":306,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":54.6},{"place":307,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":54.4},{"place":308,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":54.4},{"place":309,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":54.35},{"place":310,"model":"hy-1.8b","company":"tencent","family":"HY","version":"HY","score":54.27},{"place":311,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":54.2},{"place":312,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":54.2},{"place":313,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":54.1},{"place":314,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54},{"place":315,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":54},{"place":316,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":53.9},{"place":317,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":53.9},{"place":318,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":53.8},{"place":319,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":53.7},{"place":320,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":53.7},{"place":321,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":53.6},{"place":322,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":53.6},{"place":323,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":53.6},{"place":324,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":53.57},{"place":325,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":53.4},{"place":326,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":53.3},{"place":327,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":53.28},{"place":328,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":53.2},{"place":329,"model":"baichuan2-7b-chat-4bits","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":53.04},{"place":330,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":52.8},{"place":331,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":52.8},{"place":332,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":52.8},{"place":333,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":52.6},{"place":334,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":52.5},{"place":335,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":52.5},{"place":336,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":52.4},{"place":337,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":52.4},{"place":338,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":52.28},{"place":339,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":52.2},{"place":340,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":52.1},{"place":341,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":52.05},{"place":342,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":51.7},{"place":343,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":51.7},{"place":344,"model":"baichuan-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan","score":51.5},{"place":345,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":51.4},{"place":346,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":51.4},{"place":347,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":51.3},{"place":348,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":51.2},{"place":349,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":51.13},{"place":350,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":51.1},{"place":351,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":51.1},{"place":352,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":51.1},{"place":353,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":50.9},{"place":354,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":50.8},{"place":355,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":50.76},{"place":356,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":50.7},{"place":357,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":50.7},{"place":358,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":50.6},{"place":359,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.5},{"place":360,"model":"qwen1.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":50.5},{"place":361,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":50.3},{"place":362,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":50.3},{"place":363,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":50.13},{"place":364,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":50.1},{"place":365,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":50.1},{"place":366,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":50},{"place":367,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":49.9},{"place":368,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":49.83},{"place":369,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":49.81},{"place":370,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":49.5},{"place":371,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":49.14},{"place":372,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":48.89},{"place":373,"model":"hy-1.8b-int4gptq","company":"tencent","family":"HY","version":"HY","score":48.67},{"place":374,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":48.64},{"place":375,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":48.62},{"place":376,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":48.6},{"place":377,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":48.6},{"place":378,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":48.46},{"place":379,"model":"hy-1.8b-2bit","company":"tencent","family":"HY","version":"HY","score":47.6},{"place":380,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":47.54},{"place":381,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":47.5},{"place":382,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":47.4},{"place":383,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":47},{"place":384,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":46.95},{"place":385,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":46.12},{"place":386,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":46.1},{"place":387,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":45.9},{"place":388,"model":"claude-instant-1.0","company":"anthropic","family":"Claude","version":"Claude 1","score":45.9},{"place":389,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":45.2},{"place":390,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":45.1},{"place":391,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":45},{"place":392,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":44.9},{"place":393,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":44.7},{"place":394,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":44.3},{"place":395,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":44.17},{"place":396,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":43.72},{"place":397,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":43.6},{"place":398,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":42.82},{"place":399,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":42.8},{"place":400,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":42.7},{"place":401,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":42.57},{"place":402,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":42.55},{"place":403,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":42.4},{"place":404,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":41.4},{"place":405,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":41.31},{"place":406,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":41.3},{"place":407,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":40.6},{"place":408,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":40.4},{"place":409,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":40.36},{"place":410,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":40.29},{"place":411,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":40.1},{"place":412,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":40},{"place":413,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":39.4},{"place":414,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":39.22},{"place":415,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":38.9},{"place":416,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":38.8},{"place":417,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":38.8},{"place":418,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":38.67},{"place":419,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":38.06},{"place":420,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":37.5},{"place":421,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":37.47},{"place":422,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":37.32},{"place":423,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.2},{"place":424,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":36.5},{"place":425,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":36.2},{"place":426,"model":"hy-0.5b","company":"tencent","family":"HY","version":"HY","score":35.98},{"place":427,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":35.9},{"place":428,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":35.88},{"place":429,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":35.8},{"place":430,"model":"bloomz-7b1","company":"bigscience","family":"BLOOM","version":"BLOOMZ","score":35.7},{"place":431,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":35.67},{"place":432,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":35.6},{"place":433,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":35.5},{"place":434,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":35.21},{"place":435,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":35.18},{"place":436,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":35},{"place":437,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":34.9},{"place":438,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":34.54},{"place":439,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":34.5},{"place":440,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":33.9},{"place":441,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":32.8},{"place":442,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":32.5},{"place":443,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":32.42},{"place":444,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":32.4},{"place":445,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":32.37},{"place":446,"model":"chinese-llama-plus-13b","company":"hfl","family":"LLaMA","version":"Chinese-LLaMA-Alpaca","score":32.1},{"place":447,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":31.9},{"place":448,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":31.83},{"place":449,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":31.8},{"place":450,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":31.2},{"place":451,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":30.34},{"place":452,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":30.3},{"place":453,"model":"ziya-llama-13b-pretrain","company":"idea-ccnl","family":"Ziya","version":"Ziya-LLaMA","score":30.2},{"place":454,"model":"ziya-llama-13b-pretrain","company":"idea-ccnl","family":"Ziya","version":"Ziya-LLaMA","score":30},{"place":455,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":29.34},{"place":456,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":29.26},{"place":457,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":28.9},{"place":458,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":28.9},{"place":459,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":28.8},{"place":460,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":28.5},{"place":461,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":28},{"place":462,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":27.8},{"place":463,"model":"moss-moon-003-base","company":"fudan","family":"MOSS","version":"MOSS","score":27.4},{"place":464,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":27.39},{"place":465,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":27.3},{"place":466,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":27.3},{"place":467,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":27.15},{"place":468,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":27.1},{"place":469,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":27.1},{"place":470,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":27},{"place":471,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":26.29},{"place":472,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":25.8},{"place":473,"model":"tigerbot-7b-base","company":"tigerbot","family":"TigerBot","version":"TigerBot","score":25.7},{"place":474,"model":"aquila-7b","company":"baai","family":"Aquila","version":"Aquila","score":25.5},{"place":475,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":25.02},{"place":476,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":25},{"place":477,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":24.82},{"place":478,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":24.64},{"place":479,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":24.23},{"place":480,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":24.2},{"place":481,"model":"open-llama-7b-v2","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA v2","score":24},{"place":482,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":23.82},{"place":483,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":23.7},{"place":484,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":23.5},{"place":485,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":23.4},{"place":486,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":23.37},{"place":487,"model":"vicuna-7b-v1.5","company":"lmsys","family":"Vicuna","version":"Vicuna","score":22.9},{"place":488,"model":"bloom-7b1","company":"bigscience","family":"BLOOM","version":"BLOOM","score":22.8}]},{"id":"c3","name":"C3","topic":"Chinese reading comprehension","description":"Multiple-choice Chinese machine reading comprehension (CLUE C3).","url":"https://dataset.org/c3/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1904.09679","metric":"percent","stars":"","top_model":"InternVL2.5-26B","top_percent":95.8,"top_model_id":"internvl2.5-26b","top_generation":"InternVL 2.5","top_model_base":"InternVL2.5 26B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":60,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":95.8},{"place":2,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":94.7},{"place":3,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":94.2},{"place":4,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":94},{"place":5,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":93.5},{"place":6,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":93.5},{"place":7,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":93.2},{"place":8,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":92.2},{"place":9,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":91.7},{"place":10,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":91.5},{"place":11,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":91.5},{"place":12,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":90.8},{"place":13,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":88.1},{"place":14,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":84.4},{"place":15,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":84.4},{"place":16,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":82.3},{"place":17,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":82.1},{"place":18,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":80.6},{"place":19,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":80.2},{"place":20,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":79.7},{"place":21,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":79.3},{"place":22,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":79.1},{"place":23,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":78.9},{"place":24,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":78.6},{"place":25,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":78.5},{"place":26,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":78.2},{"place":27,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":78},{"place":28,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":77.4},{"place":29,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":77.37},{"place":30,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":77.2},{"place":31,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":77},{"place":32,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":76.9},{"place":33,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.7},{"place":34,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":75.8},{"place":35,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":75.34},{"place":36,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":75.3},{"place":37,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":74.1},{"place":38,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":74},{"place":39,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":73.9},{"place":40,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":73.7},{"place":41,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":71.4},{"place":42,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":71.4},{"place":43,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":69.42},{"place":44,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":67.6},{"place":45,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":67.01},{"place":46,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":66.9},{"place":47,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":66.4},{"place":48,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":65.6},{"place":49,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":65.4},{"place":50,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":64.9},{"place":51,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":64.6},{"place":52,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":61.9},{"place":53,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":61.7},{"place":54,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":61.4},{"place":55,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":60.16},{"place":56,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":59.1},{"place":57,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":58.6},{"place":58,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":56.9},{"place":59,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54.85},{"place":60,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":54.6},{"place":61,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":51.7},{"place":62,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":51.01},{"place":63,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":47.51},{"place":64,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":47.5},{"place":65,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":47.4},{"place":66,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":46.1},{"place":67,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":43.8},{"place":68,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":35.1}]},{"id":"c3-bench","name":"C3-Bench","topic":"Reasoning (Chinese)","description":"Comprehensive Chinese reasoning capability benchmark.","url":"https://github.com/Tencent-Hunyuan/C3-Benchmark","leaderboard":"","github":"","paper":"","metric":"percent","stars":"35","top_model":"GLM-4.5 Base","top_percent":83.1,"top_model_id":"glm-4.5-base","top_generation":"GLM 4.5","top_model_base":"GLM 4.5","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":83.1},{"place":2,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":78.6},{"place":3,"model":"hunyuan-7b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":68.5}]},{"id":"caselaw-v2","name":"CaseLaw v2","topic":"Legal reasoning","description":"U.S. case law benchmark evaluating legal reasoning and judgment over court opinions.","url":"https://www.vals.ai/benchmarks/case_law_v2-09-20-2025","leaderboard":"https://www.vals.ai/benchmarks/case_law_v2-09-20-2025","github":"","paper":"","metric":"percent","stars":"","top_model":"Grok 4.3","top_percent":79.31,"top_model_id":"grok-4.3","top_generation":"Grok 4.3","top_model_base":"Grok 4.3","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":false,"bench_models":78,"total_models":3854,"placements":[{"place":1,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":79.31},{"place":2,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":78.1},{"place":3,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":77.5},{"place":4,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":76.2},{"place":5,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":75.2},{"place":6,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":74.9},{"place":7,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":74.6},{"place":8,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":74},{"place":9,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":74},{"place":10,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":73.6},{"place":11,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":73.42},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.7},{"place":13,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":72.7},{"place":14,"model":"claude-4.1-opus-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":72.3},{"place":15,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":71.4},{"place":16,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":71.1},{"place":17,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70.1},{"place":18,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":70.1},{"place":19,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":69.88},{"place":20,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":69.8},{"place":21,"model":"o3","company":"openai","family":"o3","version":"o3","score":69.5},{"place":22,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":68.49},{"place":23,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":68.38},{"place":24,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.2},{"place":25,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":66.6},{"place":26,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":66.45},{"place":27,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":66.24},{"place":28,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":66.2},{"place":29,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":66.2},{"place":30,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":66.02},{"place":31,"model":"grok-3-mini-fast-low-reasoning","company":"xai","family":"Grok","version":"Grok 3","score":65.9},{"place":32,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":65.81},{"place":33,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":65.7},{"place":34,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":65.7},{"place":35,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":65.3},{"place":36,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.84},{"place":37,"model":"command-a-03-2025","company":"cohere","family":"Command","version":"Command","score":64.52},{"place":38,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":64},{"place":39,"model":"grok-3-mini-fast-high-reasoning","company":"xai","family":"Grok","version":"Grok 3","score":64},{"place":40,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":63.99},{"place":41,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.88},{"place":42,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":63.77},{"place":43,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":63.3},{"place":44,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":63.13},{"place":45,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.59},{"place":46,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.16},{"place":47,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":62.1},{"place":48,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":62.06},{"place":49,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":61.41},{"place":50,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":61.2},{"place":51,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":60.88},{"place":52,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":60.45},{"place":53,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":59.7},{"place":54,"model":"qwen3.5-plus-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.7},{"place":55,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.38},{"place":56,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":58.73},{"place":57,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":57.88},{"place":58,"model":"claude-4.5-haiku-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.48},{"place":59,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.95},{"place":60,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":55.84},{"place":61,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":55.84},{"place":62,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":55.41},{"place":63,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.98},{"place":64,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.98},{"place":65,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":54.88},{"place":66,"model":"grok-4.2-0309","company":"xai","family":"Grok","version":"Grok 4.2","score":54.45},{"place":67,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":53.91},{"place":68,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":53.48},{"place":69,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":53.4},{"place":70,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":53.16},{"place":71,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":53.05},{"place":72,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.63},{"place":73,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":52.63},{"place":74,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":52.52},{"place":75,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":51.88},{"place":76,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":51.66},{"place":77,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":51.55},{"place":78,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":51.45},{"place":79,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":51.4},{"place":80,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":48.77},{"place":81,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":47.91},{"place":82,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":47.48},{"place":83,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":44.16},{"place":84,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":43.84}]},{"id":"casereportbench","name":"CaseReportBench","topic":"Medical information extraction","description":"Clinical information extraction from medical case reports into structured fields.","url":"https://huggingface.co/datasets/cxyzhang/caseReportBench_ClinicalDenseExtraction_Benchmark","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 350M","top_percent":32.45,"top_model_id":"lfm2.5-350m","top_generation":"LFM2.5","top_model_base":"LFM2.5 350M","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":32.45},{"place":2,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":22.51},{"place":3,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.83},{"place":4,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":12.44},{"place":5,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":11.67},{"place":6,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":2.28},{"place":7,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":0.84},{"place":8,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.39}]},{"id":"cc-bench-v2-backend","name":"CC-Bench-V2 Backend","topic":"Agentic coding","description":"Z.ai CC-Bench-V2 backend development tasks in a Claude Code-style agent harness.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":26.9,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":26.9},{"place":2,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":25.3},{"place":3,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":22.8},{"place":4,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":20.5}]},{"id":"cc-bench-v2-frontend","name":"CC-Bench-V2 Frontend","topic":"Agentic coding","description":"Z.ai CC-Bench-V2 frontend development tasks in a Claude Code-style agent harness.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":75.9,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.9},{"place":2,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":69.4},{"place":3,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":68.4},{"place":4,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":62.3}]},{"id":"cc-bench-v2-repo-exploration","name":"CC-Bench-V2 Repo Exploration","topic":"Agentic coding","description":"Z.ai CC-Bench-V2 repository exploration tasks in a Claude Code-style agent harness.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":74.4,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":74.4},{"place":2,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":72.2},{"place":3,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":68.9},{"place":4,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":66.7}]},{"id":"cc-ocr","name":"CC-OCR","topic":"OCR (cross-lingual)","description":"Cross-lingual OCR benchmark evaluating character recognition across mixed-language documents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.6-Plus","top_percent":83.4,"top_model_id":"qwen3.6-plus","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":43,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.4},{"place":2,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":83.4},{"place":3,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.49},{"place":4,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":82.34},{"place":5,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":82.33},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82},{"place":7,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.9},{"place":8,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.8},{"place":9,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.5},{"place":10,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.5},{"place":11,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.2},{"place":12,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":81.14},{"place":13,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81},{"place":14,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":80.8},{"place":15,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.7},{"place":16,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.7},{"place":17,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.3},{"place":18,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.9},{"place":19,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":79.8},{"place":20,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":79.7},{"place":21,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.3},{"place":22,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":79.3},{"place":23,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":79},{"place":24,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.8},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.2},{"place":26,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.91},{"place":27,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.9},{"place":28,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.7},{"place":29,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.5},{"place":30,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.2},{"place":31,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.7},{"place":32,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.5},{"place":33,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.8},{"place":34,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.9},{"place":35,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.9},{"place":36,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.8},{"place":37,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.1},{"place":38,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":70.8},{"place":39,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":70.3},{"place":40,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":69.1},{"place":41,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":68.3},{"place":42,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.3},{"place":43,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.1},{"place":44,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":67.3},{"place":45,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.2},{"place":46,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":61.6},{"place":47,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":58.9},{"place":48,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":52.9},{"place":49,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":27.6}]},{"id":"cc-ocr-kie","name":"CC-OCR (KIE)","topic":"Key information extraction","description":"Key information extraction track of the CC-OCR benchmark.","url":"https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/Benchmarks/CC-OCR","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-VL-235B-A22B","top_percent":95.1,"top_model_id":"qwen3-vl-235b-a22b","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.1},{"place":2,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":92.8},{"place":3,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.6},{"place":4,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":88.69},{"place":5,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.43},{"place":6,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":79.53},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":72.5},{"place":8,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":68.36},{"place":9,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":66.08}]},{"id":"cc-ocr-multilingual","name":"CC-OCR (Multilingual)","topic":"OCR (multilingual)","description":"Multilingual text recognition track of the CC-OCR benchmark.","url":"https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/Benchmarks/CC-OCR","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qianfan-OCR","top_percent":76.7,"top_model_id":"qianfan-ocr","top_generation":"Qianfan-OCR","top_model_base":"Qianfan-OCR","top_model_family":"Qianfan","top_company":"baidu","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":76.7},{"place":2,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.2},{"place":3,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":32.5}]},{"id":"ccbench","name":"CCBench","topic":"Chinese culture VQA","description":"MMBench-family benchmark on Chinese culture (painting, calligraphy, cuisine, history...).","url":"https://mmbench.opencompass.org.cn/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2307.06281","metric":"percent","stars":"","top_model":"Step-1V 32K","top_percent":71.2,"top_model_id":"step-1v-32k","top_generation":"Step 1V 32K","top_model_base":"Step 1V","top_model_family":"Step","top_company":"stepfun","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":71.2},{"place":2,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":69.8},{"place":3,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":63.5},{"place":4,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":59.2},{"place":5,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":55.1},{"place":6,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":52.5},{"place":7,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":49.2},{"place":8,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":46.5},{"place":9,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":27.8},{"place":10,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":26.3},{"place":11,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":24.5}]},{"id":"ccpm","name":"CCPM","topic":"Chinese classical poetry","description":"Chinese Classical Poetry Matching: match modern Chinese to classical poetry lines.","url":"https://github.com/THUNLP-AIPoet/CCPM","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2106.01979","metric":"percent","stars":"","top_model":"DeepSeek-V2","top_percent":93.1,"top_model_id":"deepseek-v2","top_generation":"DeepSeek-V2","top_model_base":"DeepSeek V2","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":93.1},{"place":2,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":93},{"place":3,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":92},{"place":4,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":88.5},{"place":5,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.5},{"place":6,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":88.1},{"place":7,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":84.9},{"place":8,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":78.6},{"place":9,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":76.9},{"place":10,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":76.5},{"place":11,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":68.1},{"place":12,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":66.2},{"place":13,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":61},{"place":14,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":60.7}]},{"id":"cfcolor-decision","name":"cfcolor (decision)","topic":"Color perception","description":"Color-name / color judgement decisions; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://huggingface.co/spaces/multimodalart/jev-decision-index","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"pplx-decider-v1.2","top_percent":68.2,"top_model_id":"pplx-decider-v1.2","top_generation":"v1.2","top_model_base":"pplx-decider","top_model_family":"pplx-decider","top_company":"perplexity","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":68.2},{"place":2,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":66.3},{"place":3,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":66.2},{"place":4,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":66},{"place":5,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":65.8},{"place":6,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":65.6},{"place":7,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":65.2},{"place":8,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":64.7},{"place":9,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":64},{"place":10,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":63.2},{"place":11,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":63.2},{"place":12,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":63},{"place":13,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":62.9},{"place":14,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":62.9},{"place":15,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":62.7},{"place":16,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":62.2},{"place":17,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":62},{"place":18,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61.8},{"place":19,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":61.6},{"place":20,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61.1},{"place":21,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":58.7},{"place":22,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":58.5},{"place":23,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":58.5},{"place":24,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":58.4},{"place":25,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":58.2},{"place":26,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":56.7},{"place":27,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":56.7},{"place":28,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":56.4},{"place":29,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":56.3},{"place":30,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":55.8},{"place":31,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":54.3},{"place":32,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":53.7},{"place":33,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":53.4},{"place":34,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":52.3},{"place":35,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":52.1},{"place":36,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":51.7},{"place":37,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":51.2},{"place":38,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":50.7}]},{"id":"cfeval","name":"CFEval","topic":"Coding ELO / contest eval","description":"Contest-style coding evaluation with ELO-like scoring.","url":"","leaderboard":"","github":"","paper":"","metric":"ELO","stars":"","top_model":"Qwen3-235B-A22B-Thinking-2507","top_percent":2134,"top_model_id":"qwen3-235b-a22b-thinking-2507","top_generation":"Qwen3","top_model_base":"Qwen3 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":2134},{"place":2,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":2071},{"place":3,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":2044},{"place":4,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":1995},{"place":5,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":1986}]},{"id":"cgbench","name":"CGBench","topic":"Long video QA","description":"Cartoon/CG long video question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Lite (0428)","top_percent":65.5,"top_model_id":"seed2.0-lite-0428","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Lite","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":65.5},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65.5},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":65.3},{"place":4,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":65},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.6},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":64.5},{"place":7,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":62.4},{"place":8,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":59.3},{"place":9,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":57.4},{"place":10,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":42.2},{"place":11,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":41.8},{"place":12,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":41.3},{"place":13,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":40.1}]},{"id":"charades-sta","name":"Charades-STA","topic":"Video grounding","description":"Charades-STA temporal grounding (mIoU).","url":"https://huggingface.co/datasets/VLM2Vec/Charades-STA","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.5-VL-Thinking","top_percent":64,"top_model_id":"seed1.5-vl-thinking","top_generation":"Seed 1.5","top_model_base":"Seed 1.5 VL","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":64},{"place":2,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.5},{"place":3,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":61.4},{"place":4,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.2},{"place":5,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.3},{"place":6,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":59.33},{"place":7,"model":"videotemp-o3-7b","company":"kuaishou","family":"Keye-VL","version":"VideoTemp-o3","score":57.8},{"place":8,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":56.2},{"place":9,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56},{"place":10,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.5},{"place":11,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.5},{"place":12,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":50.9},{"place":13,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":50.9},{"place":14,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":50.6},{"place":15,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":50},{"place":16,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":43.6},{"place":17,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":38.5},{"place":18,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":38.5},{"place":19,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":32.8},{"place":20,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":28.9},{"place":21,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":27.11},{"place":22,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":25.4},{"place":23,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":21.9},{"place":24,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":9.5},{"place":25,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":5.5},{"place":26,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":5}]},{"id":"chartbench","name":"ChartBench","topic":"Chart understanding","description":"Chart comprehension benchmark covering annotated and unannotated chart types.","url":"https://chartbench.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qianfan-OCR","top_percent":85.9,"top_model_id":"qianfan-ocr","top_generation":"Qianfan-OCR","top_model_base":"Qianfan-OCR","top_model_family":"Qianfan","top_company":"baidu","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":85.9},{"place":2,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.9},{"place":3,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.2}]},{"id":"chartmuseum","name":"ChartMuseum","topic":"Chart understanding","description":"Large-scale curated collection of charts for evaluating parsing, grounding, and reasoning.","url":"https://chartmuseum-leaderboard.github.io/","leaderboard":"https://chartmuseum-leaderboard.github.io/","github":"https://github.com/Liyan06/ChartMuseum","paper":"https://arxiv.org/abs/2505.13444","metric":"percent","stars":"","top_model":"Claude Mythos 5","top_percent":85.9,"top_model_id":"claude-mythos-5","top_generation":"Claude 5","top_model_base":"Claude Mythos 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":50,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85.9},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.7},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":78.6},{"place":4,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":77},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75.8},{"place":6,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.1},{"place":7,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":70.6},{"place":8,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.1},{"place":9,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":63.3},{"place":10,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":63.3},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":63},{"place":12,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":62.9},{"place":13,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":61.7},{"place":14,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":61.5},{"place":15,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":60.9},{"place":16,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60.7},{"place":17,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":60.3},{"place":18,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":59.1},{"place":19,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":58.4},{"place":20,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":55.3},{"place":21,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":54.4},{"place":22,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":52.7},{"place":23,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":52.6},{"place":24,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":49.8},{"place":25,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.7},{"place":26,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":48.8},{"place":27,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":48.4},{"place":28,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.4},{"place":29,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":42.2},{"place":30,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":41.3},{"place":31,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":40.6},{"place":32,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40.2},{"place":33,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":40},{"place":34,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40},{"place":35,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":38.5},{"place":36,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":38.5},{"place":37,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":38.1},{"place":38,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":37.7},{"place":39,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.1},{"place":40,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":35.2},{"place":41,"model":"bespoke-minichart-7b","company":"bespokelabs","family":"Bespoke","version":"Bespoke-MiniChart","score":34},{"place":42,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":33.6},{"place":43,"model":"internvl3-38b","company":"opengvlab","family":"Intern","version":"InternVL3","score":32.1},{"place":44,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":31.1},{"place":45,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.1},{"place":46,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":28.2},{"place":47,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":26.8},{"place":48,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":23.9},{"place":49,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":22.7},{"place":50,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":21},{"place":51,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":16}]},{"id":"chartography","name":"Chartography","topic":"Chart understanding","description":"Surge AI benchmark for professional chart understanding (no tools).","url":"https://surgehq.ai/blog/chartography","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":71.6,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":71.6},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":71},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":66.3},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":64.4},{"place":5,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":61.6},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":53.6},{"place":7,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":46.4},{"place":8,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":46.2},{"place":9,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":42.6},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":29.6},{"place":11,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":29.1},{"place":12,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":15.6},{"place":13,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":6.4}]},{"id":"chartography-with-tools","name":"Chartography (With Tools)","topic":"Chart understanding","description":"Surge AI Chartography evaluated with tool (code execution) access.","url":"https://surgehq.ai/blog/chartography","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":91,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":91},{"place":2,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":90.2},{"place":3,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":90.2},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":89},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":88.4},{"place":6,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":86.2},{"place":7,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":86.2},{"place":8,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.4},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83},{"place":11,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":83},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":79.9},{"place":13,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":78.9},{"place":14,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":78},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75},{"place":16,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":68.1},{"place":17,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":68},{"place":18,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":65},{"place":19,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":65},{"place":20,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.3}]},{"id":"chartqa","name":"ChartQA","topic":"Chart understanding (VQA)","description":"Visual question answering over charts and plots.","url":"https://github.com/vis-nlp/ChartQA","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Keye-VL-1.5-8B","top_percent":94.1,"top_model_id":"keye-vl-1.5-8b","top_generation":"Keye-VL 1.5","top_model_base":"Keye-VL 1.5 8B","top_model_family":"Keye-VL","top_company":"kuaishou","top_open_source":1,"lower_is_better":false,"bench_models":223,"total_models":3854,"placements":[{"place":1,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":94.1},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.7},{"place":3,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":92.9},{"place":4,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":92.2},{"place":5,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":91.7},{"place":6,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":91},{"place":7,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":90.8},{"place":8,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":90.8},{"place":9,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":90.5},{"place":10,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":90.4},{"place":11,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":90.2},{"place":12,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":90},{"place":13,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":90},{"place":14,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":89.6},{"place":15,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":89.6},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.6},{"place":17,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":89.6},{"place":18,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.44},{"place":19,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":89},{"place":20,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":88.8},{"place":21,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":88.8},{"place":22,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":88.4},{"place":23,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":88.3},{"place":24,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":88.3},{"place":25,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":88.3},{"place":26,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":88.3},{"place":27,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":88.3},{"place":28,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":88.2},{"place":29,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":88.2},{"place":30,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":88.2},{"place":31,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":88.1},{"place":32,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":88.1},{"place":33,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88.1},{"place":34,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":88},{"place":35,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":87.9},{"place":36,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":87.8},{"place":37,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":87.68},{"place":38,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":87.6},{"place":39,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":87.6},{"place":40,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":87.5},{"place":41,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":87.5},{"place":42,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":87.4},{"place":43,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":87.4},{"place":44,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":87.4},{"place":45,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":87.3},{"place":46,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":87.2},{"place":47,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":87.2},{"place":48,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":87.1},{"place":49,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":87.1},{"place":50,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":87},{"place":51,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":87},{"place":52,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":87},{"place":53,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":86.88},{"place":54,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":86.8},{"place":55,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":86.8},{"place":56,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.8},{"place":57,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86.7},{"place":58,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":86.7},{"place":59,"model":"moondream-9b-a2b","company":"moondream","family":"Moondream","version":"Moondream 3","score":86.6},{"place":60,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":86.6},{"place":61,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":86.5},{"place":62,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":86.5},{"place":63,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.4},{"place":64,"model":"aria","company":"rhymes","family":"Aria","version":"Aria","score":86.4},{"place":65,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":86.24},{"place":66,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":86.2},{"place":67,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":86.2},{"place":68,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.16},{"place":69,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":86.1},{"place":70,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":86.1},{"place":71,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":86},{"place":72,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":86},{"place":73,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":86},{"place":74,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":86},{"place":75,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":85.9},{"place":76,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":85.7},{"place":77,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":85.7},{"place":78,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":85.7},{"place":79,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":85.5},{"place":80,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":85.5},{"place":81,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":85.4},{"place":82,"model":"llama-4-maverick-17b-128e-base","company":"meta","family":"Llama","version":"Llama 4","score":85.3},{"place":83,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":85.3},{"place":84,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":85.3},{"place":85,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.2},{"place":86,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":85.2},{"place":87,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":85.1},{"place":88,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":85},{"place":89,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85},{"place":90,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":85},{"place":91,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":84.9},{"place":92,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":84.9},{"place":93,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":84.9},{"place":94,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":84.88},{"place":95,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":84.8},{"place":96,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.6},{"place":97,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.6},{"place":98,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":84.5},{"place":99,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":84.3},{"place":100,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":84.3},{"place":101,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.2},{"place":102,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":84.1},{"place":103,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":84.1},{"place":104,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.08},{"place":105,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":84},{"place":106,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":84},{"place":107,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84},{"place":108,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.96},{"place":109,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":83.8},{"place":110,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":83.8},{"place":111,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":83.76},{"place":112,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":83.7},{"place":113,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.7},{"place":114,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":83.6},{"place":115,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":83.4},{"place":116,"model":"llama-4-scout-17b-16e-base","company":"meta","family":"Llama","version":"Llama 4","score":83.4},{"place":117,"model":"llama-4-scout-17b-base","company":"meta","family":"Llama","version":"Llama 4","score":83.4},{"place":118,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":83.4},{"place":119,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":83.3},{"place":120,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.3},{"place":121,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":83.3},{"place":122,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.3},{"place":123,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.2},{"place":124,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":83.2},{"place":125,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":83.1},{"place":126,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":83},{"place":127,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":83},{"place":128,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.7},{"place":129,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":82.6},{"place":130,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":82.4},{"place":131,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":82.4},{"place":132,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.4},{"place":133,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":82.4},{"place":134,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":82.2},{"place":135,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":82.2},{"place":136,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.1},{"place":137,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":82.1},{"place":138,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":81.9},{"place":139,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":81.8},{"place":140,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":81.8},{"place":141,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":81.8},{"place":142,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":81.8},{"place":143,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":81.7},{"place":144,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":81.7},{"place":145,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":81.5},{"place":146,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":81.5},{"place":147,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":81.4},{"place":148,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":81.3},{"place":149,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":81.3},{"place":150,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":81.1},{"place":151,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":81},{"place":152,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":81},{"place":153,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":81},{"place":154,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":80.8},{"place":155,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":80.8},{"place":156,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":80.8},{"place":157,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":80.7},{"place":158,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":80.4},{"place":159,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":80.4},{"place":160,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":80.2},{"place":161,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.2},{"place":162,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":80.1},{"place":163,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":80.1},{"place":164,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":80},{"place":165,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":79.8},{"place":166,"model":"llava-next-110b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":79.7},{"place":167,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":79.6},{"place":168,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.5},{"place":169,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":79.2},{"place":170,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.1},{"place":171,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":79.1},{"place":172,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":79},{"place":173,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.6},{"place":174,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":78.6},{"place":175,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":78.5},{"place":176,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":78.5},{"place":177,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.4},{"place":178,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.3},{"place":179,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.3},{"place":180,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":78.3},{"place":181,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":78.24},{"place":182,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":78.2},{"place":183,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":78.2},{"place":184,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":78.1},{"place":185,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":78.1},{"place":186,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":78.1},{"place":187,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":78},{"place":188,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":78},{"place":189,"model":"gemini-1.5-flash-8b-0827","company":"google","family":"Gemini","version":"Gemini 1.5","score":78},{"place":190,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":77.9},{"place":191,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.8},{"place":192,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.5},{"place":193,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.2},{"place":194,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":76.9},{"place":195,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.9},{"place":196,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.8},{"place":197,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":76.6},{"place":198,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":76.6},{"place":199,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":76.5},{"place":200,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.3},{"place":201,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":76.2},{"place":202,"model":"grok-1.5v","company":"xai","family":"Grok","version":"Grok 1.5","score":76.1},{"place":203,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":76},{"place":204,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":75.9},{"place":205,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":75.6},{"place":206,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":75.6},{"place":207,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":75},{"place":208,"model":"cogvlm2-llama3-chinese-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":74.7},{"place":209,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":74.3},{"place":210,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":74.2},{"place":211,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":74.1},{"place":212,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":74.1},{"place":213,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":73.9},{"place":214,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":73.7},{"place":215,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":73.5},{"place":216,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":73.5},{"place":217,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":73.3},{"place":218,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":73.3},{"place":219,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":72.9},{"place":220,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.6},{"place":221,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":72.6},{"place":222,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":72},{"place":223,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":71.1},{"place":224,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":70.5},{"place":225,"model":"docowl-1.5-chat","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Chat","score":70.2},{"place":226,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":70},{"place":227,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":70},{"place":228,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":69.6},{"place":229,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":69.5},{"place":230,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.3},{"place":231,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":68.7},{"place":232,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":68.7},{"place":233,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":68.4},{"place":234,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":68.3},{"place":235,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":68.2},{"place":236,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":68},{"place":237,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":67.6},{"place":238,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":67.2},{"place":239,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":67.2},{"place":240,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":66.9},{"place":241,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":66.9},{"place":242,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":66.3},{"place":243,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":66},{"place":244,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":65.8},{"place":245,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":65.7},{"place":246,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":64.9},{"place":247,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":61.4},{"place":248,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":60},{"place":249,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":59.9},{"place":250,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":59.8},{"place":251,"model":"ureader","company":"alibaba","family":"mPLUG","version":"UReader","score":59.3},{"place":252,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":59.1},{"place":253,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":57.7},{"place":254,"model":"mplug-docowl-7b","company":"alibaba","family":"mPLUG","version":"mPLUG-DocOwl","score":57.4},{"place":255,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":51.9},{"place":256,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":50.2},{"place":257,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":48.6},{"place":258,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.5},{"place":259,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.2},{"place":260,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.2},{"place":261,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.1},{"place":262,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.9},{"place":263,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39},{"place":264,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":34},{"place":265,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":33.7},{"place":266,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":29.2},{"place":267,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":25.8},{"place":268,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":23.5},{"place":269,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":23.4},{"place":270,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":18.2},{"place":271,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":17.8},{"place":272,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":8.3}]},{"id":"chartqa-pro","name":"ChartQA-Pro","topic":"Chart understanding (VQA)","description":"Professional-grade chart question answering with diverse chart types and complex reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Mythos 5","top_percent":71.6,"top_model_id":"claude-mythos-5","top_generation":"Claude 5","top_model_base":"Claude Mythos 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":46,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":71.6},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.18},{"place":3,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":71.12},{"place":4,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":70.9},{"place":5,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":70.9},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.2},{"place":7,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":69.65},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.5},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.4},{"place":10,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69.4},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69.23},{"place":12,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":69},{"place":13,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":68.9},{"place":14,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.61},{"place":15,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":67.77},{"place":16,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":67.6},{"place":17,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":66.8},{"place":18,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.8},{"place":19,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":65.5},{"place":20,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":65.5},{"place":21,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":64.7},{"place":22,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":64.66},{"place":23,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64.54},{"place":24,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":64},{"place":25,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":62.6},{"place":26,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":62.2},{"place":27,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.4},{"place":28,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.2},{"place":29,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":60.9},{"place":30,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":59.5},{"place":31,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.3},{"place":32,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.9},{"place":33,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":58.65},{"place":34,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":57.5},{"place":35,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":56.4},{"place":36,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":54.86},{"place":37,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.9},{"place":38,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":52.87},{"place":39,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.26},{"place":40,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":42.9},{"place":41,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":37.6},{"place":42,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.2},{"place":43,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":33.5},{"place":44,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":32.57},{"place":45,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":30.8},{"place":46,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":27.8},{"place":47,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.79},{"place":48,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":25.38},{"place":49,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":24.5},{"place":50,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":23.7},{"place":51,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":0.13}]},{"id":"chartqa-pro-with-tools","name":"ChartQA-Pro (with tools)","topic":"Chart understanding (with tools)","description":"ChartQA-Pro evaluated with tool access.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.8","top_percent":72.3,"top_model_id":"claude-opus-4.8","top_generation":"Claude 4.8","top_model_base":"Claude Opus 4.8","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":72.3},{"place":2,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":69.8}]},{"id":"charxiv-dq","name":"CharXiv (DQ)","topic":"Chart description (PDF)","description":"Scientific chart/table descriptive questions from arXiv PDFs.","url":"https://charxiv.github.io/","leaderboard":"https://charxiv.github.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":95.95,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":171,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":95.95},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":95.5},{"place":3,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":95},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":94.9},{"place":6,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":94.6},{"place":7,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":94.5},{"place":8,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":94.3},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":94.1},{"place":10,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":94},{"place":11,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":94},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":93.5},{"place":13,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":93.5},{"place":14,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":93.38},{"place":15,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":93.3},{"place":16,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":93.27},{"place":17,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":93.1},{"place":18,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.92},{"place":19,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":92.1},{"place":20,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.38},{"place":21,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":91.25},{"place":22,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":91.2},{"place":23,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.2},{"place":24,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":91.17},{"place":25,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":90.8},{"place":26,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.5},{"place":27,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.3},{"place":28,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":90.3},{"place":29,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":90},{"place":30,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":89.9},{"place":31,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":89.85},{"place":32,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.6},{"place":33,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":89.5},{"place":34,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":89.05},{"place":35,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":88.9},{"place":36,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":88.4},{"place":37,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.2},{"place":38,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":88.2},{"place":39,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":88},{"place":40,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":87.9},{"place":41,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":87.8},{"place":42,"model":"o1","company":"openai","family":"o1","version":"o1","score":87.45},{"place":43,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87.4},{"place":44,"model":"internvl3-38b","company":"opengvlab","family":"Intern","version":"InternVL3","score":87.2},{"place":45,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":87},{"place":46,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":86.8},{"place":47,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86.5},{"place":48,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.5},{"place":49,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":85.1},{"place":50,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":84.5},{"place":51,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":84.45},{"place":52,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":84.3},{"place":53,"model":"doubao-1.5-vision-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":84.3},{"place":54,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":84.3},{"place":55,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":83.9},{"place":56,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.6},{"place":57,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83},{"place":58,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":82.45},{"place":59,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":82.3},{"place":60,"model":"internvl3-14b","company":"opengvlab","family":"Intern","version":"InternVL3","score":82.2},{"place":61,"model":"command-a-vision-07-2025","company":"cohere","family":"Command","version":"Command","score":82},{"place":62,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.8},{"place":63,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":81.8},{"place":64,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":81.35},{"place":65,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":80.3},{"place":66,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":79.92},{"place":67,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":79.9},{"place":68,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":79.6},{"place":69,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":79.5},{"place":70,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":79.4},{"place":71,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":78.8},{"place":72,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":78.6},{"place":73,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":77.4},{"place":74,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":76.83},{"place":75,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":76.6},{"place":76,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.2},{"place":77,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.1},{"place":78,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":75.7},{"place":79,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":75.45},{"place":80,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":75.2},{"place":81,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":75.17},{"place":82,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.1},{"place":83,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":74.92},{"place":84,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":73.9},{"place":85,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":73.9},{"place":86,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":73.65},{"place":87,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":73.6},{"place":88,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":73.6},{"place":89,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.5},{"place":90,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":73.5},{"place":91,"model":"internvl3-9b","company":"opengvlab","family":"Intern","version":"InternVL3","score":72.5},{"place":92,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":72.2},{"place":93,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":72},{"place":94,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":71.97},{"place":95,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":71.83},{"place":96,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":71.6},{"place":97,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":71.55},{"place":98,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":71.1},{"place":99,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":70.6},{"place":100,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":69.8},{"place":101,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.7},{"place":102,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":68.6},{"place":103,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":68.42},{"place":104,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":68.4},{"place":105,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":68.35},{"place":106,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":68.18},{"place":107,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":68.15},{"place":108,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":68.12},{"place":109,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":66.4},{"place":110,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":66},{"place":111,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":65.08},{"place":112,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":65},{"place":113,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":64.4},{"place":114,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":64.4},{"place":115,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":63.92},{"place":116,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":63.8},{"place":117,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":63.7},{"place":118,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":63.5},{"place":119,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":63.4},{"place":120,"model":"ovis1.5-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.5-Gemma2","score":62.6},{"place":121,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":62.4},{"place":122,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.3},{"place":123,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":61.7},{"place":124,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":61.62},{"place":125,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":60.48},{"place":126,"model":"ovis1.5-llama3-8b","company":"alibaba","family":"Ovis","version":"Ovis1.5-Llama3","score":60.15},{"place":127,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":60.1},{"place":128,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":60},{"place":129,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":59.73},{"place":130,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":59.7},{"place":131,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.5},{"place":132,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":59.35},{"place":133,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":59.27},{"place":134,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":58.6},{"place":135,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":58.5},{"place":136,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":58},{"place":137,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":57.62},{"place":138,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":57.1},{"place":139,"model":"reka-flash","company":"reka","family":"Reka","version":"Reka","score":56.45},{"place":140,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":56.1},{"place":141,"model":"reka-core","company":"reka","family":"Reka","version":"Reka","score":55.6},{"place":142,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":55.02},{"place":143,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":55},{"place":144,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":54.7},{"place":145,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":54.65},{"place":146,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":54.37},{"place":147,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":53.3},{"place":148,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":52.98},{"place":149,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":52.73},{"place":150,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":52.68},{"place":151,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":51.6},{"place":152,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":51.05},{"place":153,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":49.7},{"place":154,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":48.73},{"place":155,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":48.2},{"place":156,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":48},{"place":157,"model":"internvl3-1b","company":"opengvlab","family":"Intern","version":"InternVL3","score":47.1},{"place":158,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":47},{"place":159,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":45.8},{"place":160,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":45.67},{"place":161,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":44.55},{"place":162,"model":"mini-gemini-hd-8b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":44.42},{"place":163,"model":"idefics2-8b-chatty","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":41.55},{"place":164,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":41.48},{"place":165,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":40.8},{"place":166,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":40.6},{"place":167,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":38.75},{"place":168,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":38.7},{"place":169,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":38.67},{"place":170,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":38.4},{"place":171,"model":"docowl-1.5-chat","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Chat","score":37.4},{"place":172,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":36.9},{"place":173,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":36.3},{"place":174,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":35.77},{"place":175,"model":"llava-1.6-mistral-7b","company":"llava","family":"LLaVA","version":"LLaVA-1.6-Mistral","score":35.4},{"place":176,"model":"reka-edge","company":"reka","family":"Reka","version":"Reka","score":33.65},{"place":177,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":32.77},{"place":178,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":32.77},{"place":179,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":30.7},{"place":180,"model":"sphinx-v2","company":"alpha-vllm","family":"SPHINX","version":"SPHINX-V2","score":30.25},{"place":181,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":28.93},{"place":182,"model":"moai","company":"kaist","family":"MoAI","version":"MoAI","score":28.7},{"place":183,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":27.8},{"place":184,"model":"docowl-1.5-omni","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Omni","score":25.7},{"place":185,"model":"chartinstruct-llama2","company":"vis-nlp","family":"ChartInstruct","version":"ChartInstruct-Llama2","score":21.4},{"place":186,"model":"chartgemma","company":"vis-nlp","family":"ChartGemma","version":"ChartGemma","score":21.3},{"place":187,"model":"unichart-chartqa","company":"vis-nlp","family":"UniChart","version":"UniChart-ChartQA","score":19.32},{"place":188,"model":"chartllama","company":"tencent","family":"ChartLlama","version":"ChartLlama","score":19.23},{"place":189,"model":"ureader","company":"alibaba","family":"mPLUG","version":"UReader","score":18.98},{"place":190,"model":"chartassistant","company":"opengvlab","family":"ChartAssistant","version":"ChartAssistant","score":16.93},{"place":191,"model":"tinychart","company":"alibaba","family":"mPLUG","version":"TinyChart","score":16.15},{"place":192,"model":"chartinstruct-flant5","company":"vis-nlp","family":"ChartInstruct","version":"ChartInstruct-FlanT5","score":15.47},{"place":193,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":12.45}]},{"id":"charxiv-rq","name":"CharXiv (RQ)","topic":"Chart reasoning (PDF)","description":"Scientific chart/table reasoning questions from arXiv PDFs.","url":"https://charxiv.github.io/","leaderboard":"https://charxiv.github.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":93.5,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":274,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":93.5},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93.5},{"place":3,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":91.4},{"place":4,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.6},{"place":5,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.2},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":89.9},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89.9},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":89.1},{"place":9,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.9},{"place":10,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":88.9},{"place":11,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.9},{"place":12,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":88.4},{"place":13,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":86.6},{"place":14,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.5},{"place":15,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":86.4},{"place":16,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":86.2},{"place":17,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":86.2},{"place":18,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":86.1},{"place":19,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":85.9},{"place":20,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":85.9},{"place":21,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":85.8},{"place":22,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":85.8},{"place":23,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":85.4},{"place":24,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":85.2},{"place":25,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":85.2},{"place":26,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":85.1},{"place":27,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.8},{"place":28,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":84.8},{"place":29,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":84.7},{"place":30,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":84.6},{"place":31,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":84.5},{"place":32,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":84.5},{"place":33,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.4},{"place":34,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":84.2},{"place":35,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":84.2},{"place":36,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":84.2},{"place":37,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.1},{"place":38,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84},{"place":39,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.7},{"place":40,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83.7},{"place":41,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.5},{"place":42,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.5},{"place":43,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":83.5},{"place":44,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.3},{"place":45,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":83.2},{"place":46,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":83.1},{"place":47,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":83.1},{"place":48,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":82.8},{"place":49,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":82.7},{"place":50,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":82.6},{"place":51,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":82.5},{"place":52,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":82.4},{"place":53,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":82.1},{"place":54,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":82.1},{"place":55,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":82.1},{"place":56,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":82.1},{"place":57,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":82.1},{"place":58,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":81.9},{"place":59,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":81.6},{"place":60,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":81.6},{"place":61,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":81.6},{"place":62,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.5},{"place":63,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.4},{"place":64,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":81.4},{"place":65,"model":"ling-3.0-flash-vl","company":"antgroup","family":"Ling","version":"Ling 3.0","score":81.3},{"place":66,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.1},{"place":67,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":81.1},{"place":68,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":81},{"place":69,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":80.82},{"place":70,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.8},{"place":71,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":80.6},{"place":72,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80.5},{"place":73,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.5},{"place":74,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.4},{"place":75,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":80.3},{"place":76,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":80.3},{"place":77,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.2},{"place":78,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":80.1},{"place":79,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":79.9},{"place":80,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":79.7},{"place":81,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.5},{"place":82,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":78.8},{"place":83,"model":"o3","company":"openai","family":"o3","version":"o3","score":78.6},{"place":84,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":78.6},{"place":85,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78.4},{"place":86,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":78.1},{"place":87,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78},{"place":88,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":77.8},{"place":89,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.7},{"place":90,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77.5},{"place":91,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77.5},{"place":92,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.5},{"place":93,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":77.4},{"place":94,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.4},{"place":95,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.2},{"place":96,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":77},{"place":97,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":76.9},{"place":98,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":75.6},{"place":99,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":75},{"place":100,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":74.6},{"place":101,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":74.5},{"place":102,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":74},{"place":103,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":73.2},{"place":104,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73},{"place":105,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":72.9},{"place":106,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":72.5},{"place":107,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":72.2},{"place":108,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":72},{"place":109,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":72},{"place":110,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":71.7},{"place":111,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":71.5},{"place":112,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":71.4},{"place":113,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":71.4},{"place":114,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":70.9},{"place":115,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.8},{"place":116,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":70.7},{"place":117,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":70.5},{"place":118,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.1},{"place":119,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":70},{"place":120,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.6},{"place":121,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":69.5},{"place":122,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.5},{"place":123,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":69.1},{"place":124,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.1},{"place":125,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69},{"place":126,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":68.6},{"place":127,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":68.6},{"place":128,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.5},{"place":129,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.5},{"place":130,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":68.5},{"place":131,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.5},{"place":132,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":68.5},{"place":133,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.3},{"place":134,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":68.1},{"place":135,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.9},{"place":136,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":67.9},{"place":137,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.8},{"place":138,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":67.7},{"place":139,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.5},{"place":140,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.2},{"place":141,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.2},{"place":142,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":67.1},{"place":143,"model":"gpt-5.1-thinking","company":"openai","family":"GPT","version":"GPT-5.1","score":67},{"place":144,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.1},{"place":145,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.1},{"place":146,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66},{"place":147,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":65.3},{"place":148,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.2},{"place":149,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.1},{"place":150,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65},{"place":151,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":64.4},{"place":152,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":64.4},{"place":153,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":64.4},{"place":154,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":64.2},{"place":155,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.7},{"place":156,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":63.6},{"place":157,"model":"nemotron-3-nano-omni-30b-a3b-reasoning","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63.6},{"place":158,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":63.4},{"place":159,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":63.2},{"place":160,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":63},{"place":161,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":63},{"place":162,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63},{"place":163,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.8},{"place":164,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.7},{"place":165,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":60.9},{"place":166,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":60.9},{"place":167,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":60.2},{"place":168,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":60.2},{"place":169,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":60.2},{"place":170,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":60.1},{"place":171,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":60},{"place":172,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":59.6},{"place":173,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.8},{"place":174,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":57.8},{"place":175,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":57.5},{"place":176,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.4},{"place":177,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":56.9},{"place":178,"model":"r-4b-base","company":"tencent","family":"R","version":"R","score":56.8},{"place":179,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":56.8},{"place":180,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":56.7},{"place":181,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.6},{"place":182,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":56.5},{"place":183,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.5},{"place":184,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.1},{"place":185,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":56},{"place":186,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55.8},{"place":187,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.5},{"place":188,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":55.4},{"place":189,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":55.3},{"place":190,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":55.1},{"place":191,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":54.4},{"place":192,"model":"doubao-1.5-vision-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":54.4},{"place":193,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":54.3},{"place":194,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":52.8},{"place":195,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":52.7},{"place":196,"model":"o1","company":"openai","family":"o1","version":"o1","score":52.6},{"place":197,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":52},{"place":198,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":50.5},{"place":199,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":50.3},{"place":200,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":50.1},{"place":201,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":50.1},{"place":202,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":49.7},{"place":203,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.9},{"place":204,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":48.9},{"place":205,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":48.8},{"place":206,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":48.5},{"place":207,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.5},{"place":208,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":48},{"place":209,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":47.7},{"place":210,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":47.5},{"place":211,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":47.1},{"place":212,"model":"command-a-vision-07-2025","company":"cohere","family":"Command","version":"Command","score":46.9},{"place":213,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.4},{"place":214,"model":"internvl3-38b","company":"opengvlab","family":"Intern","version":"InternVL3","score":46.4},{"place":215,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":46},{"place":216,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":45.8},{"place":217,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":44.7},{"place":218,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.6},{"place":219,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":44.4},{"place":220,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":43.8},{"place":221,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":43.3},{"place":222,"model":"internvl3-14b","company":"opengvlab","family":"Intern","version":"InternVL3","score":43.1},{"place":223,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":43},{"place":224,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":42.8},{"place":225,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":42.5},{"place":226,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":42.5},{"place":227,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":42.4},{"place":228,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":42.4},{"place":229,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":42.4},{"place":230,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":42.1},{"place":231,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":41.9},{"place":232,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":41.7},{"place":233,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.3},{"place":234,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":41.3},{"place":235,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.3},{"place":236,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.3},{"place":237,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":40.7},{"place":238,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":40.5},{"place":239,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":40.1},{"place":240,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":40},{"place":241,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":40},{"place":242,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":39.9},{"place":243,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":39.8},{"place":244,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":39.7},{"place":245,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":39.7},{"place":246,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":39.6},{"place":247,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":38.9},{"place":248,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.2},{"place":249,"model":"internvl3-9b","company":"opengvlab","family":"Intern","version":"InternVL3","score":38},{"place":250,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":37.6},{"place":251,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":37.6},{"place":252,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":37.5},{"place":253,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":37.1},{"place":254,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":37.1},{"place":255,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":36.8},{"place":256,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":36.5},{"place":257,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":36.4},{"place":258,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":35.9},{"place":259,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":35.8},{"place":260,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":34.6},{"place":261,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":34.1},{"place":262,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":34.1},{"place":263,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":33.9},{"place":264,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":33.5},{"place":265,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":33.4},{"place":266,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.2},{"place":267,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":33.2},{"place":268,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":32.9},{"place":269,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":32.9},{"place":270,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":32.7},{"place":271,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":32.3},{"place":272,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.3},{"place":273,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":32.2},{"place":274,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":31.8},{"place":275,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":31.7},{"place":276,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":31.7},{"place":277,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":31.6},{"place":278,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":31.6},{"place":279,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":31.6},{"place":280,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":31.3},{"place":281,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":31.2},{"place":282,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":31.2},{"place":283,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":31},{"place":284,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.6},{"place":285,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":30.2},{"place":286,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.2},{"place":287,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":29.2},{"place":288,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":29.1},{"place":289,"model":"reka-core","company":"reka","family":"Reka","version":"Reka","score":28.9},{"place":290,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.8},{"place":291,"model":"ovis1.5-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.5-Gemma2","score":28.4},{"place":292,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":28.3},{"place":293,"model":"ovis1.5-llama3-8b","company":"alibaba","family":"Ovis","version":"Ovis1.5-Llama3","score":28.2},{"place":294,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":27.3},{"place":295,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":27.1},{"place":296,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":27},{"place":297,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.8},{"place":298,"model":"reka-flash","company":"reka","family":"Reka","version":"Reka","score":26.6},{"place":299,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":26.5},{"place":300,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":26.4},{"place":301,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":25.7},{"place":302,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":25.4},{"place":303,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":25},{"place":304,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":25},{"place":305,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":24.9},{"place":306,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":24.9},{"place":307,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":24.7},{"place":308,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":24.5},{"place":309,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":24.5},{"place":310,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":24.3},{"place":311,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":24},{"place":312,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":23.6},{"place":313,"model":"reka-edge","company":"reka","family":"Reka","version":"Reka","score":23.5},{"place":314,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":23.3},{"place":315,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":22.8},{"place":316,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":22.5},{"place":317,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":21.3},{"place":318,"model":"internvl3-1b","company":"opengvlab","family":"Intern","version":"InternVL3","score":21},{"place":319,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":21},{"place":320,"model":"mini-gemini-hd-8b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":19},{"place":321,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":19},{"place":322,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":18.8},{"place":323,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":18.7},{"place":324,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":18.5},{"place":325,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":18.2},{"place":326,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":18.1},{"place":327,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":18},{"place":328,"model":"idefics2-8b-chatty","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":17.8},{"place":329,"model":"moai","company":"kaist","family":"MoAI","version":"MoAI","score":17.5},{"place":330,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":17.1},{"place":331,"model":"docowl-1.5-chat","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Chat","score":17},{"place":332,"model":"sphinx-v2","company":"alpha-vllm","family":"SPHINX","version":"SPHINX-V2","score":16.1},{"place":333,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":16},{"place":334,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":15.6},{"place":335,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":15.5},{"place":336,"model":"ureader","company":"alibaba","family":"mPLUG","version":"UReader","score":14.3},{"place":337,"model":"chartllama","company":"tencent","family":"ChartLlama","version":"ChartLlama","score":14.2},{"place":338,"model":"llava-1.6-mistral-7b","company":"llava","family":"LLaVA","version":"LLaVA-1.6-Mistral","score":13.9},{"place":339,"model":"chartgemma","company":"vis-nlp","family":"ChartGemma","version":"ChartGemma","score":12.5},{"place":340,"model":"chartassistant","company":"opengvlab","family":"ChartAssistant","version":"ChartAssistant","score":11.7},{"place":341,"model":"chartinstruct-flant5","company":"vis-nlp","family":"ChartInstruct","version":"ChartInstruct-FlanT5","score":11.7},{"place":342,"model":"docowl-1.5-omni","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Omni","score":9.1},{"place":343,"model":"chartinstruct-llama2","company":"vis-nlp","family":"ChartInstruct","version":"ChartInstruct-Llama2","score":8.8},{"place":344,"model":"tinychart","company":"alibaba","family":"mPLUG","version":"TinyChart","score":8.3},{"place":345,"model":"unichart-chartqa","company":"vis-nlp","family":"UniChart","version":"UniChart-ChartQA","score":5.7},{"place":346,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":3.9},{"place":347,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":1.5}]},{"id":"charxiv-rq-with-tools","name":"CharXiv (RQ, With Tools)","topic":"Chart understanding","description":"CharXiv reasoning questions evaluated with tool access.","url":"https://charxiv.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Mythos 5","top_percent":93.5,"top_model_id":"claude-mythos-5","top_generation":"Claude 5","top_model_base":"Claude Mythos 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":33,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":93.5},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":93.5},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.4},{"place":4,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":93.2},{"place":5,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":92.9},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":92.6},{"place":7,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":92.5},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":92.1},{"place":9,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":91.8},{"place":10,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":91.3},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":91},{"place":12,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":90},{"place":13,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":89.9},{"place":14,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89.9},{"place":15,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":89.4},{"place":16,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":89.4},{"place":17,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89.4},{"place":18,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89.3},{"place":19,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":89.1},{"place":20,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":89},{"place":21,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":88.7},{"place":22,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":88.4},{"place":23,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.3},{"place":24,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":88},{"place":25,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":87.8},{"place":26,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":87.6},{"place":27,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":86.7},{"place":28,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":84.9},{"place":29,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84.7},{"place":30,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":84},{"place":31,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.2},{"place":32,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":82},{"place":33,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":81.3},{"place":34,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.4},{"place":35,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.7},{"place":36,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":76.5},{"place":37,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":75.6},{"place":38,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":75.5}]},{"id":"chessbench-decision","name":"ChessBench (decision)","topic":"Chess","description":"Choose the best move among candidates (ChessBench); accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/google-deepmind/searchless_chess","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef","top_percent":24.7,"top_model_id":"clef","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":24.7},{"place":2,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":24.6},{"place":3,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":24},{"place":4,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":23},{"place":5,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":22.1},{"place":6,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":22},{"place":7,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":21.2},{"place":8,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":19.8},{"place":9,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":19.5},{"place":10,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":17.6},{"place":11,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":17.5},{"place":12,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":17.3},{"place":13,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":17.2},{"place":14,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":16.9},{"place":15,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":16.5},{"place":16,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":15.8},{"place":17,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":15.1},{"place":18,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":14.4},{"place":19,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":14.2},{"place":20,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":14.1},{"place":21,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":13.6},{"place":22,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":12.9},{"place":23,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":12.6},{"place":24,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":12.5},{"place":25,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":12.4},{"place":26,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":11.2},{"place":27,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":10.7},{"place":28,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":10.6},{"place":29,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":9.2},{"place":30,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":8.8},{"place":31,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":8.7},{"place":32,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":8.5},{"place":33,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":8.3},{"place":34,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":8.1},{"place":35,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":7.7},{"place":36,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":7.4},{"place":37,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":7.1},{"place":38,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":6.7}]},{"id":"chexpert","name":"CheXpert","topic":"Medical imaging","description":"Chest X-ray condition classification, macro F1 over top 5 conditions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedGemma 27B","top_percent":49.9,"top_model_id":"medgemma-27b-it","top_generation":"MedGemma 1","top_model_base":"MedGemma","top_model_family":"MedGemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":49.9},{"place":2,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":48.2},{"place":3,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":48.1},{"place":4,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":32.6}]},{"id":"chid","name":"CHID","topic":"Chinese idiom cloze","description":"Chinese IDiom cloze-test dataset (CLUE).","url":"https://github.com/chujiezheng/ChID-Dataset","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1906.01265","metric":"percent","stars":"","top_model":"DeepSeek-V2","top_percent":92.7,"top_model_id":"deepseek-v2","top_generation":"DeepSeek-V2","top_model_base":"DeepSeek V2","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":92.7},{"place":2,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":92.1},{"place":3,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":90.1},{"place":4,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":89.4},{"place":5,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":89.3},{"place":6,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":88.1},{"place":7,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":88},{"place":8,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":84.7},{"place":9,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":83.2},{"place":10,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":83.2},{"place":11,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":83.2},{"place":12,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":81.7},{"place":13,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":79.7},{"place":14,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":78.2},{"place":15,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":75.2},{"place":16,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":72.6},{"place":17,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":72.3},{"place":18,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":72.3},{"place":19,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":69.8},{"place":20,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":64.9},{"place":21,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":63.4},{"place":22,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":57.9},{"place":23,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":57},{"place":24,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":55.5},{"place":25,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":53},{"place":26,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":48},{"place":27,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":44.1},{"place":28,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":37.9}]},{"id":"chinese-simpleqa","name":"Chinese SimpleQA","topic":"QA (Chinese)","description":"Chinese variant of the SimpleQA benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ERNIE 5.0","top_percent":86.03,"top_model_id":"ernie-5.0","top_generation":"ERNIE 5.0","top_model_base":"ERNIE 5.0","top_model_family":"ERNIE","top_company":"baidu","top_open_source":0,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":86.03},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.9},{"place":3,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84.4},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":84.08},{"place":5,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.9},{"place":6,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77.7},{"place":7,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":77.6},{"place":8,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":77.1},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":76.8},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.5},{"place":11,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":76.4},{"place":12,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":76.1},{"place":13,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":75.9},{"place":14,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.8},{"place":15,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":75.7},{"place":16,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":75.1},{"place":17,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":75},{"place":18,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":74.2},{"place":19,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.2},{"place":20,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":72.37},{"place":21,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":72.1},{"place":22,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":72},{"place":23,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":71.5},{"place":24,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":66.7},{"place":25,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":66},{"place":26,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":64},{"place":27,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":63},{"place":28,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":53.5}]},{"id":"cibench","name":"CIBench","topic":"Code interpreter","description":"Evaluation of LLMs using a code interpreter for data-science tasks; EN/ZH average.","url":"https://github.com/open-compass/CIBench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2407.10499","metric":"percent","stars":"","top_model":"InternLM2-Chat-20B","top_percent":55.4,"top_model_id":"internlm2-chat-20b","top_generation":"InternLM2","top_model_base":"InternLM2 20B","top_model_family":"InternLM","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":55.4},{"place":2,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":53.8},{"place":3,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":48.9},{"place":4,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":47.8},{"place":5,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":46.4},{"place":6,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":42.8},{"place":7,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":41.5},{"place":8,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":39.9},{"place":9,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":38.5},{"place":10,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":35.8},{"place":11,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":23.2},{"place":12,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":16.1},{"place":13,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":11.4}]},{"id":"circa","name":"Circa","topic":"Indirect answers","description":"Interpreting indirect yes/no answers in dialogue.","url":"https://github.com/google-research-datasets/circa","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"pplx-decider-v1-27b","top_percent":89.2,"top_model_id":"pplx-decider-v1-27b","top_generation":"v1","top_model_base":"pplx-decider","top_model_family":"pplx-decider","top_company":"perplexity","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":89.2},{"place":2,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":84.6}]},{"id":"civil-comments","name":"Civil Comments","topic":"Toxicity classification","description":"Toxicity classification of online comments (Jigsaw Civil Comments).","url":"https://huggingface.co/datasets/google/civil_comments","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"d1-omni-600M","top_percent":95.8,"top_model_id":"d1-omni-600m","top_generation":"d1","top_model_base":"d1-omni-600M","top_model_family":"d1","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":95.8},{"place":2,"model":"mapika-decider-2b","company":"mapika","family":"Decider","version":"Decider","score":93.6},{"place":3,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":93},{"place":4,"model":"mapika-decider-4b","company":"mapika","family":"Decider","version":"Decider","score":92.8}]},{"id":"cl-bench","name":"CL-Bench","topic":"Long-context reasoning","description":"Comprehensive long-context benchmark evaluating reasoning over extended contexts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":27.8,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":27.8},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":26.7},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":25.4},{"place":4,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":25.2},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":24.8},{"place":6,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":23.9},{"place":7,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":23.8},{"place":8,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":23.5},{"place":9,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":23.1},{"place":10,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":22.9},{"place":11,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":22.8},{"place":12,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":22.6},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":21.3},{"place":14,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":21.1},{"place":15,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":21},{"place":16,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":20.8},{"place":17,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":20.5},{"place":18,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":20.4},{"place":19,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":20.1},{"place":20,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":20.1},{"place":21,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":20},{"place":22,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":19.7},{"place":23,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":19.3},{"place":24,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":18.4},{"place":25,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":18.1},{"place":26,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":18.1},{"place":27,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":17.8},{"place":28,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":17.2},{"place":29,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":16.4},{"place":30,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":16.1},{"place":31,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":15.6},{"place":32,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15.5},{"place":33,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":15.5},{"place":34,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":15.4},{"place":35,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":14.9},{"place":36,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":14.8},{"place":37,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":12.2},{"place":38,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":12}]},{"id":"cl-bench-life","name":"CL-bench Life","topic":"Context learning","description":"Tencent Hy context-learning benchmark built from real-life scenarios (companion to CL-bench); models must learn and apply rules given in long, messy contexts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":21.1,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":21.1},{"place":2,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":21},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":19.2},{"place":4,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":17},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":16.9},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":16.5},{"place":7,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":15.7},{"place":8,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":14.3},{"place":9,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":14},{"place":10,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":13.3},{"place":11,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":13},{"place":12,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":13},{"place":13,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":13},{"place":14,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":11.4},{"place":15,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":8.5}]},{"id":"cladder","name":"CLadder","topic":"Causal reasoning","description":"Causal reasoning questions across the ladder of causation; accuracy (Jev Decision Index suite, posed as typed decisions).","url":"https://github.com/causalNLP/cladder","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef-Flash","top_percent":97.7,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":97.7},{"place":2,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":97.2},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":94},{"place":4,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":90.8},{"place":5,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":88.6},{"place":6,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":85.4},{"place":7,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":81.2},{"place":8,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":77.5},{"place":9,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":75},{"place":10,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":74.7},{"place":11,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":72.8},{"place":12,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":72.7},{"place":13,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":72.6},{"place":14,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":72},{"place":15,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":71.6},{"place":16,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":70.5},{"place":17,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":67.8},{"place":18,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":66.9},{"place":19,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":66.5},{"place":20,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":66.4},{"place":21,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":65.6},{"place":22,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":63.1},{"place":23,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":62},{"place":24,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61.1},{"place":25,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":60.3},{"place":26,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":60},{"place":27,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59},{"place":28,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":56.6},{"place":29,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":54.5},{"place":30,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":54.4},{"place":31,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":54.1},{"place":32,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":53.8},{"place":33,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":52.9},{"place":34,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":51},{"place":35,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":50.5},{"place":36,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":50.5},{"place":37,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":50.1},{"place":38,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":49.7}]},{"id":"claw-eval","name":"Claw-Eval","topic":"Agentic assistant tasks","description":"Benchmark of end-to-end OpenClaw-style personal-agent tasks; overall (EN) score.","url":"https://github.com/claw-eval/claw-eval","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-5.1","top_percent":84.4,"top_model_id":"glm-5.1","top_generation":"GLM 5.1","top_model_base":"GLM-5.1","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":59,"total_models":3854,"placements":[{"place":1,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":84.4},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83.92},{"place":3,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.7},{"place":4,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":82.2},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":81.8},{"place":6,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":81.7},{"place":7,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":81.6},{"place":8,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":81.4},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":80.6},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80.2},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.7},{"place":12,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":79.4},{"place":13,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":79.3},{"place":14,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":78.8},{"place":15,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":78.2},{"place":16,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":77.7},{"place":17,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77.6},{"place":18,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":77.1},{"place":19,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.6},{"place":20,"model":"xing4.0-29b-a4b","company":"teleai","family":"Xing","version":"Xing4.0","score":76.55},{"place":21,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.5},{"place":22,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.8},{"place":23,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.4},{"place":24,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.8},{"place":25,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.54},{"place":26,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":74.2},{"place":27,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":73.4},{"place":28,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":73},{"place":29,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":72.5},{"place":30,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":72.4},{"place":31,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":71.6},{"place":32,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.49},{"place":33,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.7},{"place":34,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":70.7},{"place":35,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":70.3},{"place":36,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":69.9},{"place":37,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":69.9},{"place":38,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":69.8},{"place":39,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":69.5},{"place":40,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":68.7},{"place":41,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":67.8},{"place":42,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":66.6},{"place":43,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.53},{"place":44,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":66.5},{"place":45,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.5},{"place":46,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66.3},{"place":47,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66.3},{"place":48,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":66.2},{"place":49,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.4},{"place":50,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":65.2},{"place":51,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":64.4},{"place":52,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.3},{"place":53,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":63.5},{"place":54,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":63.1},{"place":55,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":62.85},{"place":56,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.3},{"place":57,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.28},{"place":58,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":61.5},{"place":59,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":61.2},{"place":60,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":59.6},{"place":61,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.8},{"place":62,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.3},{"place":63,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.02},{"place":64,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58},{"place":65,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":54.8},{"place":66,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.2},{"place":67,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.14},{"place":68,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.9},{"place":69,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":50},{"place":70,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.5},{"place":71,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":48.1},{"place":72,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":47.1},{"place":73,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.5}]},{"id":"claw-eval-multimodal","name":"Claw-Eval Multimodal","topic":"Multimodal agent tasks","description":"Multimodal subset of Claw-Eval OpenClaw-style agent benchmark.","url":"https://github.com/claw-eval/claw-eval","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.4","top_percent":25.7,"top_model_id":"gpt-5.4","top_generation":"GPT-5.4","top_model_base":"GPT-5.4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":25.7},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":24.8},{"place":3,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":23.8},{"place":4,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":23.8},{"place":5,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":18.8},{"place":6,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":15.8}]},{"id":"claw-gym","name":"Claw-Gym","topic":"Agentic assistant tasks","description":"OpenClaw-style personal-assistant agent environment suite measuring task success on daily tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nanbeige4.2-3B","top_percent":65,"top_model_id":"nanbeige4.2-3b","top_generation":"Nanbeige4.2","top_model_base":"Nanbeige4.2 3B","top_model_family":"Nanbeige","top_company":"boss","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":65},{"place":2,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.1},{"place":3,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53},{"place":4,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.8},{"place":5,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":16.4}]},{"id":"claweval-pass-at-3","name":"ClawEval (Pass@3)","topic":"Agent tasks (OpenClaw)","description":"ClawEval OpenClaw agent benchmark, pass@3 (any of 3 trials succeeds).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":82.9,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82.9},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82.4},{"place":3,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.9},{"place":4,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":78.4},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.9},{"place":6,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":75.4},{"place":7,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":75},{"place":8,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":73.1},{"place":9,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":72.1}]},{"id":"claweval-pass3","name":"ClawEval (Pass^3)","topic":"Agent tasks (OpenClaw)","description":"ClawEval OpenClaw agent benchmark, pass^3 (all 3 trials succeed).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Flash-0731","top_percent":78.9,"top_model_id":"deepseek-v4-flash-0731","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Flash 0731","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":73,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.9},{"place":2,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":78.3},{"place":3,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.2},{"place":4,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":74.5},{"place":5,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.5},{"place":6,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.68},{"place":7,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":73.4},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":72.1},{"place":9,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":71.6},{"place":10,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":71.4},{"place":11,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":70.8},{"place":12,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":70.4},{"place":13,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":68.9},{"place":14,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":68.5},{"place":15,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":68.3},{"place":16,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":68.3},{"place":17,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":67.8},{"place":18,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":67.1},{"place":19,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66.3},{"place":20,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":66.3},{"place":21,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":65.2},{"place":22,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":64.56},{"place":23,"model":"llada2.2-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":64.22},{"place":24,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":64},{"place":25,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":63.82},{"place":26,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":63.8},{"place":27,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":62.7},{"place":28,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":62.4},{"place":29,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":62.3},{"place":30,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":62.3},{"place":31,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":62.3},{"place":32,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":62.3},{"place":33,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":62.1},{"place":34,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.8},{"place":35,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":61.7},{"place":36,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":61.5},{"place":37,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":60.6},{"place":38,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":60.3},{"place":39,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.8},{"place":40,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.8},{"place":41,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.6},{"place":42,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":58.7},{"place":43,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":58.4},{"place":44,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":58.2},{"place":45,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":57.8},{"place":46,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":57.8},{"place":47,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.8},{"place":48,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.8},{"place":49,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":57.7},{"place":50,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":57.7},{"place":51,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":57.7},{"place":52,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":57.3},{"place":53,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":57.16},{"place":54,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56},{"place":55,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":55.6},{"place":56,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":55},{"place":57,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":54.8},{"place":58,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":52.9},{"place":59,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":52.9},{"place":60,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":52.3},{"place":61,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":52.2},{"place":62,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":51.9},{"place":63,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":51},{"place":64,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51},{"place":65,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":51},{"place":66,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":50},{"place":67,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":50},{"place":68,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":49.7},{"place":69,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":49.4},{"place":70,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":48.7},{"place":71,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.1},{"place":72,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":48.08},{"place":73,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.1},{"place":74,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.2},{"place":75,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":46.15},{"place":76,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.2},{"place":77,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":43.6},{"place":78,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":43.26},{"place":79,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":41.7},{"place":80,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":40.38},{"place":81,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":40.2},{"place":82,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":37},{"place":83,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.9},{"place":84,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":32.4},{"place":85,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":28},{"place":86,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25.5},{"place":87,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25},{"place":88,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15.9}]},{"id":"click","name":"CLIcK","topic":"Korean instruction following","description":"Korean long-form instruction-following benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Pro-Thinking (max)","top_percent":91.6,"top_model_id":"deepseek-v4-pro-thinking-max","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Pro","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.6},{"place":2,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":91.6},{"place":3,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":90.7},{"place":4,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":89.6},{"place":5,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.6},{"place":6,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.2},{"place":7,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.9},{"place":8,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":88.8},{"place":9,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":88.7},{"place":10,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.4},{"place":11,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":86.3},{"place":12,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":85.3},{"place":13,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":84.2},{"place":14,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.1},{"place":15,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":83.9},{"place":16,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":82.76},{"place":17,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.3},{"place":18,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":80.9},{"place":19,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.9},{"place":20,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":78.9},{"place":21,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":78.8},{"place":22,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":78.4},{"place":23,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":77.9},{"place":24,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":77.2},{"place":25,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":76.1},{"place":26,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":74.6},{"place":27,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.5}]},{"id":"clinc150-oos","name":"CLINC150+OOS","topic":"Intent classification","description":"CLINC150 intent detection with out-of-scope class; macro-F1 (Jev Decision Index suite, posed as typed decisions).","url":"https://github.com/clinc/oos-eval","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"Clef-Omni","top_percent":97.7,"top_model_id":"clef-omni","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":97.7},{"place":2,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":97.4},{"place":3,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":96.9},{"place":4,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":96.4},{"place":5,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":96.3},{"place":6,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":95.1},{"place":7,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":94.4},{"place":8,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":94.3},{"place":9,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":94},{"place":10,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":93.6},{"place":11,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":93.3},{"place":12,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":93},{"place":13,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":91.9},{"place":14,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":91.2},{"place":15,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":90.3},{"place":16,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":89.9},{"place":17,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":89.3},{"place":18,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":88.3},{"place":19,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":87.6},{"place":20,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":87.4},{"place":21,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":85.3},{"place":22,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":84.6},{"place":23,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":83.5},{"place":24,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":79},{"place":25,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":79},{"place":26,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":78.6},{"place":27,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":72.7},{"place":28,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":66.8},{"place":29,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":65.2},{"place":30,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":64.7},{"place":31,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":63.1},{"place":32,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":60.4},{"place":33,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":30.8},{"place":34,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":4.9},{"place":35,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":4.3},{"place":36,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":3.2}]},{"id":"cloc-count","name":"CLOC Counting","topic":"Visual counting","description":"CLOC test object counting, exact-match accuracy.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":28.3,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":28.3},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":26.9},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":23.9},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.4},{"place":5,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":22.3}]},{"id":"cloningscenarios","name":"CloningScenarios","topic":"Biosecurity refusal","description":"Safety benchmark that red-teams models with cloning-related misuse scenarios to measure compliance and refusal rates.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Grok 4","top_percent":45,"top_model_id":"grok-4","top_generation":"Grok 4","top_model_base":"Grok 4","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":45},{"place":2,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":46}]},{"id":"cluewsc","name":"CLUEWSC","topic":"Coreference reasoning (Chinese)","description":"Chinese Winograd Schema-style coreference benchmark from CLUE.","url":"https://www.cluebenchmarks.com/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek R1","top_percent":92.8,"top_model_id":"deepseek-r1","top_generation":"DeepSeek R1","top_model_base":"DeepSeek R1","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":92.8},{"place":2,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":91.4},{"place":3,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":90.9},{"place":4,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":90.4},{"place":5,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":90.1},{"place":6,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":89.9},{"place":7,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":88.6},{"place":8,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":87.9},{"place":9,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":85.93},{"place":10,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":85.9},{"place":11,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":85.6},{"place":12,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":85.4},{"place":13,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":85.4},{"place":14,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.2},{"place":15,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":85},{"place":16,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84.7},{"place":17,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":84.7},{"place":18,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":83.6},{"place":19,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":83.5},{"place":20,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.5},{"place":21,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":83},{"place":22,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":82.7},{"place":23,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.5},{"place":24,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.2},{"place":25,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":82.2},{"place":26,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":82},{"place":27,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":81},{"place":28,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":80.5},{"place":29,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":80},{"place":30,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":78.6},{"place":31,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":78.5},{"place":32,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":78.3},{"place":33,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.5},{"place":34,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":76.5},{"place":35,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":76.5},{"place":36,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":75.8},{"place":37,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":75.6},{"place":38,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":74.3},{"place":39,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":73.1},{"place":40,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":72.1},{"place":41,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":71.9},{"place":42,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":68.2},{"place":43,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":66.2},{"place":44,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":64},{"place":45,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":63.8},{"place":46,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":63.3},{"place":47,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":60},{"place":48,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":59.8},{"place":49,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":59.1},{"place":50,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":53.9},{"place":51,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":52.8},{"place":52,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":52.2},{"place":53,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":50.3},{"place":54,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":50.3},{"place":55,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":49.2}]},{"id":"cmath","name":"CMath","topic":"Math (Chinese)","description":"Chinese mathematics benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LLaDA2.0 Flash","top_percent":96.9,"top_model_id":"llada2.0-flash","top_generation":"LLaDA 2.0","top_model_base":"LLaDA 2.0 Flash","top_model_family":"LLaDA","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":93,"total_models":3854,"placements":[{"place":1,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":96.9},{"place":2,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":96.7},{"place":3,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":96.63},{"place":4,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":96.58},{"place":5,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":96.54},{"place":6,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":96.52},{"place":7,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":96.4},{"place":8,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":95.72},{"place":9,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.7},{"place":10,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":95.63},{"place":11,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":95.42},{"place":12,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":94.99},{"place":13,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":94.8},{"place":14,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":94.72},{"place":15,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":94.3},{"place":16,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":93.62},{"place":17,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.6},{"place":18,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":93.53},{"place":19,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":93.35},{"place":20,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":92.8},{"place":21,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":92.8},{"place":22,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":92.6},{"place":23,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":92.5},{"place":24,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":92.2},{"place":25,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":91.8},{"place":26,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":91.3},{"place":27,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":91.17},{"place":28,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.9},{"place":29,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":90.83},{"place":30,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":90.7},{"place":31,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":90},{"place":32,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":89.8},{"place":33,"model":"qwen2.5-math-72b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":89.7},{"place":34,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":89.7},{"place":35,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":89.33},{"place":36,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":88.8},{"place":37,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":87.3},{"place":38,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":86.7},{"place":39,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":86.7},{"place":40,"model":"qwen2-math-72b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":86.4},{"place":41,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":86},{"place":42,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":85.5},{"place":43,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":85.5},{"place":44,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":85.4},{"place":45,"model":"qwen2.5-math-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":85},{"place":46,"model":"deepseek-math-7b-instruct","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":84.6},{"place":47,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.5},{"place":48,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":84.2},{"place":49,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":83.5},{"place":50,"model":"qwen2-math-7b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":83.2},{"place":51,"model":"qwen2.5-math-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":83},{"place":52,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":82.8},{"place":53,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":82.7},{"place":54,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":82},{"place":55,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":81.9},{"place":56,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":81.3},{"place":57,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":80.3},{"place":58,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":79.6},{"place":59,"model":"qwen2-math-1.5b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":79.6},{"place":60,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":79.2},{"place":61,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":78.7},{"place":62,"model":"numinamath-7b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":78.2},{"place":63,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":77.8},{"place":64,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":77.8},{"place":65,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":77.3},{"place":66,"model":"skywork-13b-math","company":"skywork","family":"Skywork","version":"Skywork","score":77.27},{"place":67,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":76.7},{"place":68,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":76.7},{"place":69,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":75.5},{"place":70,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":75.1},{"place":71,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":73.9},{"place":72,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":73.8},{"place":73,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":72.3},{"place":74,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":71.7},{"place":75,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":71.7},{"place":76,"model":"metamath-70b","company":"meta-math","family":"MetaMath","version":"MetaMath","score":70.9},{"place":77,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":68.4},{"place":78,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":67.9},{"place":79,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":66.4},{"place":80,"model":"internlm2-math-base-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":65.9},{"place":81,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":65.5},{"place":82,"model":"wizardmath-70b-v1.0","company":"microsoft","family":"WizardMath","version":"WizardMath V1.0","score":65.4},{"place":83,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":64.8},{"place":84,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":63},{"place":85,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":58.4},{"place":86,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":56.1},{"place":87,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":55.6},{"place":88,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":53.9},{"place":89,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":51.5},{"place":90,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":51.33},{"place":91,"model":"wizardmath-13b-v1.0","company":"microsoft","family":"WizardMath","version":"WizardMath V1.0","score":50.83},{"place":92,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":44.9},{"place":93,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":43.4},{"place":94,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":40.4},{"place":95,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":34.5},{"place":96,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":25.1}]},{"id":"cmmlu","name":"CMMLU","topic":"Chinese multi-domain","description":"Chinese counterpart to MMLU.","url":"https://github.com/haonan-li/CMMLU","leaderboard":"","github":"","paper":"","metric":"percent","stars":"781","top_model":"Qwen2.5 Max","top_percent":91.9,"top_model_id":"qwen2.5-max","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":281,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":91.9},{"place":2,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":90.9},{"place":3,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.8},{"place":4,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":90.72},{"place":5,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.4},{"place":6,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":90.4},{"place":7,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":90.21},{"place":8,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":90.2},{"place":9,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":90.2},{"place":10,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":90.2},{"place":11,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":90.18},{"place":12,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":90.1},{"place":13,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":89.94},{"place":14,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.9},{"place":15,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":89.61},{"place":16,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.52},{"place":17,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.5},{"place":18,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.34},{"place":19,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.9},{"place":20,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.9},{"place":21,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":88.9},{"place":22,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.9},{"place":23,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":88.8},{"place":24,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":88.8},{"place":25,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":88.8},{"place":26,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":88.5},{"place":27,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":88.3},{"place":28,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":88.2},{"place":29,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":88.2},{"place":30,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.9},{"place":31,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":87.66},{"place":32,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":87.64},{"place":33,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.5},{"place":34,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":87.47},{"place":35,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":87.4},{"place":36,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":87.03},{"place":37,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":86.9},{"place":38,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":86.59},{"place":39,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":86.5},{"place":40,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":86.46},{"place":41,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.36},{"place":42,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.88},{"place":43,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":85.76},{"place":44,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":85.13},{"place":45,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":84.8},{"place":46,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":84.72},{"place":47,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":84.6},{"place":48,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":84.3},{"place":49,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":84.25},{"place":50,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":84.2},{"place":51,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":84},{"place":52,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":83.9},{"place":53,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":83.7},{"place":54,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":83.6},{"place":55,"model":"yi-34b-200k","company":"01ai","family":"Yi","version":"Yi","score":83.6},{"place":56,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83.5},{"place":57,"model":"joyai-llm-flash-base","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":83.09},{"place":58,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83},{"place":59,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":82.9},{"place":60,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":82.6},{"place":61,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":82.48},{"place":62,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":82.4},{"place":63,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":82.3},{"place":64,"model":"internlm2.5-20b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":82.22},{"place":65,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":82.13},{"place":66,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":81.9},{"place":67,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":81.7},{"place":68,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.68},{"place":69,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":81.6},{"place":70,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":81.55},{"place":71,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":81.34},{"place":72,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":81.3},{"place":73,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":81.23},{"place":74,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":81.2},{"place":75,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":80.9},{"place":76,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":80.9},{"place":77,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":80.62},{"place":78,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":80.5},{"place":79,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.76},{"place":80,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":79.7},{"place":81,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":79.5},{"place":82,"model":"skywork-moe-base","company":"skywork","family":"Skywork","version":"Skywork-MoE","score":79.5},{"place":83,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":79.4},{"place":84,"model":"qwen1.5-moe-a2.7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":79.2},{"place":85,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":79.2},{"place":86,"model":"internlm2.5-7b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":79.1},{"place":87,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":78.92},{"place":88,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":78.7},{"place":89,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":78.7},{"place":90,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.6},{"place":91,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":78.3},{"place":92,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":78.2},{"place":93,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":78.1},{"place":94,"model":"baichuan-3","company":"baichuan","family":"Baichuan","version":"Baichuan 3","score":78.1},{"place":95,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":78},{"place":96,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":77.6},{"place":97,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":77.27},{"place":98,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":76.53},{"place":99,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":76.43},{"place":100,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":76.26},{"place":101,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":75.85},{"place":102,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":75.7},{"place":103,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":75.5},{"place":104,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":75.3},{"place":105,"model":"yi-6b-200k","company":"01ai","family":"Yi","version":"Yi","score":75.3},{"place":106,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":75.1},{"place":107,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":75.1},{"place":108,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.8},{"place":109,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.71},{"place":110,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.7},{"place":111,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":74.7},{"place":112,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":74.69},{"place":113,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.5},{"place":114,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":74.5},{"place":115,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":74.2},{"place":116,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":74.2},{"place":117,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.1},{"place":118,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":73.7},{"place":119,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":73.4},{"place":120,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":73.3},{"place":121,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":73.3},{"place":122,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":73.29},{"place":123,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":73.2},{"place":124,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":73.1},{"place":125,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":73.1},{"place":126,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":73},{"place":127,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":72.6},{"place":128,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":72.2},{"place":129,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.06},{"place":130,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":71.74},{"place":131,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":71.5},{"place":132,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":71.4},{"place":133,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":71.36},{"place":134,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":71.2},{"place":135,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":71.11},{"place":136,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":71},{"place":137,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":71},{"place":138,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":70.95},{"place":139,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":70.8},{"place":140,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":70.8},{"place":141,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":70.7},{"place":142,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":70.6},{"place":143,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":70.6},{"place":144,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":70.58},{"place":145,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":70.57},{"place":146,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":70.5},{"place":147,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":70.33},{"place":148,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":70.3},{"place":149,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":70.2},{"place":150,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":70.1},{"place":151,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":70.02},{"place":152,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":70},{"place":153,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":70},{"place":154,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":69.9},{"place":155,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":69.3},{"place":156,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":69.01},{"place":157,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":68.9},{"place":158,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":68.7},{"place":159,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":68.29},{"place":160,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":68.1},{"place":161,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":68.1},{"place":162,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":68},{"place":163,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":67.8},{"place":164,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":67.53},{"place":165,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":67.53},{"place":166,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":67.5},{"place":167,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":67.42},{"place":168,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":67.4},{"place":169,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":67.2},{"place":170,"model":"qwen1.5-4b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.7},{"place":171,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":66.6},{"place":172,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":66.5},{"place":173,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":66.3},{"place":174,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":66.2},{"place":175,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":66.2},{"place":176,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":65.65},{"place":177,"model":"internlm2.5-1.8b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":65.44},{"place":178,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":65.4},{"place":179,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":65.3},{"place":180,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":65.22},{"place":181,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":65.2},{"place":182,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":65.1},{"place":183,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":64.7},{"place":184,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":64.5},{"place":185,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":64.3},{"place":186,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":64.3},{"place":187,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":64.2},{"place":188,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":63.9},{"place":189,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":63.55},{"place":190,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.3},{"place":191,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":63.3},{"place":192,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":63.2},{"place":193,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":63},{"place":194,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":63},{"place":195,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":62.7},{"place":196,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":62.7},{"place":197,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":62.5},{"place":198,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":62.5},{"place":199,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":62.4},{"place":200,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":62.2},{"place":201,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":62.2},{"place":202,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":62},{"place":203,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":62},{"place":204,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":61.97},{"place":205,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":61.8},{"place":206,"model":"qwen-72b","company":"qwen","family":"Qwen","version":"Qwen","score":61.8},{"place":207,"model":"skywork-13b","company":"skywork","family":"Skywork","version":"Skywork","score":61.8},{"place":208,"model":"kwaiyii-13b-base","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":61.73},{"place":209,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":61.59},{"place":210,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":61.4},{"place":211,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":61.3},{"place":212,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":61.3},{"place":213,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":61.3},{"place":214,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":61},{"place":215,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":60.87},{"place":216,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":60.8},{"place":217,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":60.49},{"place":218,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.4},{"place":219,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":60.4},{"place":220,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":60.35},{"place":221,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":60.3},{"place":222,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":60},{"place":223,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":60},{"place":224,"model":"kwaiyii-13b-chat","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":59.97},{"place":225,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":59.9},{"place":226,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":59.68},{"place":227,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":59.67},{"place":228,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":59.6},{"place":229,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":59.5},{"place":230,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":59.5},{"place":231,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":59.5},{"place":232,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":59.47},{"place":233,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":59.1},{"place":234,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":59},{"place":235,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":59},{"place":236,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":58.82},{"place":237,"model":"baichuan2-13b-chat-4bits","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":58.82},{"place":238,"model":"minicpm-moe-8x2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":58.8},{"place":239,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":58.75},{"place":240,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":58.66},{"place":241,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":58.44},{"place":242,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":58.4},{"place":243,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":58},{"place":244,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":57.9},{"place":245,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":57.8},{"place":246,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":57.8},{"place":247,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":57.23},{"place":248,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":57.2},{"place":249,"model":"milm-6b","company":"xiaomi","family":"MiLM","version":"MiLM","score":57.17},{"place":250,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":57.1},{"place":251,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":57.07},{"place":252,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":57.07},{"place":253,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":57},{"place":254,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":57},{"place":255,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":56.7},{"place":256,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":55.82},{"place":257,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":55.8},{"place":258,"model":"baichuan-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan","score":55.8},{"place":259,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":55.51},{"place":260,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":55.5},{"place":261,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":55.3},{"place":262,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":55.27},{"place":263,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":55.1},{"place":264,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":55.1},{"place":265,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":55.1},{"place":266,"model":"hy-1.8b","company":"tencent","family":"HY","version":"HY","score":55.07},{"place":267,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":55.01},{"place":268,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":54.99},{"place":269,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":54.8},{"place":270,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":54.5},{"place":271,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":54.06},{"place":272,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":54},{"place":273,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":54},{"place":274,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":53.9},{"place":275,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":53.9},{"place":276,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":53.8},{"place":277,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":53.75},{"place":278,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":53.6},{"place":279,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":53.5},{"place":280,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":53.4},{"place":281,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":53.4},{"place":282,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":53.3},{"place":283,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":53.3},{"place":284,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":53.3},{"place":285,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":53.1},{"place":286,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":53},{"place":287,"model":"baichuan2-7b-chat-4bits","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":52.84},{"place":288,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":52.7},{"place":289,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":52.6},{"place":290,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":52.2},{"place":291,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":51.8},{"place":292,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":51.8},{"place":293,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":51.8},{"place":294,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":51.7},{"place":295,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":51.7},{"place":296,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":51.68},{"place":297,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":51.2},{"place":298,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":51.1},{"place":299,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":51.07},{"place":300,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":51},{"place":301,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":50.9},{"place":302,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":50.85},{"place":303,"model":"hy-1.8b-int4gptq","company":"tencent","family":"HY","version":"HY","score":50.8},{"place":304,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":50.8},{"place":305,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":50.72},{"place":306,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":50.6},{"place":307,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":50.6},{"place":308,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":50.5},{"place":309,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":50},{"place":310,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":49.72},{"place":311,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":49.7},{"place":312,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":49.5},{"place":313,"model":"hy-1.8b-2bit","company":"tencent","family":"HY","version":"HY","score":49.32},{"place":314,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":49.3},{"place":315,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":49.3},{"place":316,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":49.3},{"place":317,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":49.21},{"place":318,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":48.9},{"place":319,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":48.8},{"place":320,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":48.8},{"place":321,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":48.6},{"place":322,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":48.4},{"place":323,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":48.37},{"place":324,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":47.8},{"place":325,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":47.7},{"place":326,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":47.2},{"place":327,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":47.1},{"place":328,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":46.9},{"place":329,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":46.81},{"place":330,"model":"qwen1.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":46.6},{"place":331,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":46.6},{"place":332,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":46.1},{"place":333,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":45.32},{"place":334,"model":"internlm2-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":45.27},{"place":335,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":44.9},{"place":336,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":44.7},{"place":337,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":44.63},{"place":338,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":44.6},{"place":339,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":44.5},{"place":340,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":44.45},{"place":341,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":44.4},{"place":342,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":44.2},{"place":343,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":44.02},{"place":344,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":44},{"place":345,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":42.96},{"place":346,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":42.67},{"place":347,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":42.5},{"place":348,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":42.1},{"place":349,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":42},{"place":350,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":41.92},{"place":351,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":41.57},{"place":352,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":41},{"place":353,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":40.99},{"place":354,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":40.6},{"place":355,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":39.2},{"place":356,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":38.8},{"place":357,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":38.7},{"place":358,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":38.4},{"place":359,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":37.99},{"place":360,"model":"hy-0.5b","company":"tencent","family":"HY","version":"HY","score":37.08},{"place":361,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":37.06},{"place":362,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":36.96},{"place":363,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":36.74},{"place":364,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":36.6},{"place":365,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":36.3},{"place":366,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":36.28},{"place":367,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":36},{"place":368,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":35.55},{"place":369,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":35.1},{"place":370,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":35.08},{"place":371,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":33.9},{"place":372,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":33.8},{"place":373,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":33.43},{"place":374,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":33.4},{"place":375,"model":"chinese-llama-plus-13b","company":"hfl","family":"LLaMA","version":"Chinese-LLaMA-Alpaca","score":33},{"place":376,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":32.64},{"place":377,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":32.6},{"place":378,"model":"ziya-llama-13b-pretrain","company":"idea-ccnl","family":"Ziya","version":"Ziya-LLaMA","score":32.1},{"place":379,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":32.09},{"place":380,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":31.9},{"place":381,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":31.85},{"place":382,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":31.8},{"place":383,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":31.5},{"place":384,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":31.5},{"place":385,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":31.38},{"place":386,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":31.2},{"place":387,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":31.15},{"place":388,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":31.11},{"place":389,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":30.9},{"place":390,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":30.89},{"place":391,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":30.7},{"place":392,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":30.09},{"place":393,"model":"moss-moon-003-base","company":"fudan","family":"MOSS","version":"MOSS","score":29.6},{"place":394,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":28.56},{"place":395,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":26.8},{"place":396,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":26.75},{"place":397,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":26.7},{"place":398,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":26},{"place":399,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":25.9},{"place":400,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":25.77},{"place":401,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":25.66},{"place":402,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":25.6},{"place":403,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":25.53},{"place":404,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":25.34},{"place":405,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":25.3},{"place":406,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":24.88},{"place":407,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":24.2},{"place":408,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":24.18},{"place":409,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":24.03},{"place":410,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":24}]},{"id":"cmmmu","name":"CMMMU","topic":"Chinese multimodal understanding","description":"Chinese Massive Multi-discipline Multimodal Understanding benchmark.","url":"https://cmmmu-benchmark.github.io/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2401.11944","metric":"percent","stars":"","top_model":"GPT-4V(ision)","top_percent":42.5,"top_model_id":"gpt-4v","top_generation":"GPT-4V","top_model_base":"GPT-4V","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":42.5},{"place":2,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":39.5},{"place":3,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":37.9},{"place":4,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":35.8},{"place":5,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":32.1},{"place":6,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":30.7},{"place":7,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":27.4},{"place":8,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":24.8},{"place":9,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":23.8}]},{"id":"cmrc2018","name":"CMRC 2018","topic":"Chinese reading comprehension","description":"Span-extraction Chinese machine reading comprehension (CMRC 2018).","url":"https://github.com/ymcui/cmrc2018","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1810.07366","metric":"percent","stars":"","top_model":"TigerBot-70B-Base","top_percent":85.93,"top_model_id":"tigerbot-70b-base","top_generation":"TigerBot","top_model_base":"TigerBot 70B","top_model_family":"TigerBot","top_company":"tigerresearch","top_open_source":1,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":85.93},{"place":2,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":85.37},{"place":3,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":80.06},{"place":4,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":77.5},{"place":5,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":77.4},{"place":6,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":76.73},{"place":7,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":76.3},{"place":8,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":76.17},{"place":9,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":76},{"place":10,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.8},{"place":11,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":74.62},{"place":12,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":73.4},{"place":13,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":73.3},{"place":14,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":73.1},{"place":15,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":68.97},{"place":16,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.6},{"place":17,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":66.57}]},{"id":"cmt-benchmark","name":"CMT-Benchmark","topic":"Physics reasoning (condensed matter)","description":"Condensed Matter Theory benchmark of expert-written research-level theoretical physics problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Sage-A1.5","top_percent":80,"top_model_id":"sage-a1.5","top_generation":"A1.5","top_model_base":"Sage-A1.5","top_model_family":"Agents","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":80},{"place":2,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":72},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":50},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":47},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":43.8},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":43.6},{"place":7,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":40},{"place":8,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":40},{"place":9,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":37.8},{"place":10,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35},{"place":11,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":34.1},{"place":12,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":34},{"place":13,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":31},{"place":14,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":26.8},{"place":15,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":26},{"place":16,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":25.3},{"place":17,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":19.4}]},{"id":"cnmo-2024","name":"CNMO 2024","topic":"Math (competition)","description":"China National Mathematical Olympiad 2024 evaluation set.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"openPangu-R-72B-2512 Slow Thinking","top_percent":82.8,"top_model_id":"openpangu-r-72b-2512-slow-thinking","top_generation":"openPangu-R","top_model_base":"openPangu-R 72B","top_model_family":"openPangu-R","top_company":"freedomintelligence","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":82.8},{"place":2,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":78.5},{"place":3,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":77.8},{"place":4,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75},{"place":5,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":74.7},{"place":6,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":74.3},{"place":7,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":67},{"place":8,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":60.4},{"place":9,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":57.6},{"place":10,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":56.6},{"place":11,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.6},{"place":12,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":43.2},{"place":13,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":15.9},{"place":14,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":13.1},{"place":15,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":10.8},{"place":16,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":10.8},{"place":17,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":6.8},{"place":18,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":2.8}]},{"id":"coco-caption","name":"COCO Captions","topic":"Image captioning","description":"COCO image captioning benchmark (Karpathy test split), CIDEr score.","url":"https://cocodataset.org/","leaderboard":"","github":"","paper":"","metric":"cider","stars":"","top_model":"T5Gemma 2 4B-4B","top_percent":105.4,"top_model_id":"t5gemma-2-4b-4b","top_generation":"T5Gemma 2","top_model_base":"T5Gemma 2 4B-4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":105.4},{"place":2,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":86},{"place":3,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":69.6}]},{"id":"coco-det-f1","name":"COCO Detection (F1)","topic":"Object detection","description":"COCO object detection with an MLLM; F1 averaged over IoU 0.5:0.95.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":57.1,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":57.1},{"place":2,"model":"groundingdino-t","company":"idea-research","family":"GroundingDINO","version":"GroundingDINO","score":56.6},{"place":3,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":55.2},{"place":4,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":54.7},{"place":5,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":52.9},{"place":6,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.5},{"place":7,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.8}]},{"id":"coco-pointing","name":"COCO Pointing","topic":"Object pointing","description":"COCO object pointing accuracy.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-2B","top_percent":85.8,"top_model_id":"wevisone-vl-2b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-2B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":85.8},{"place":2,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":85.4},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":83.9},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":80.5},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.5}]},{"id":"codeforces","name":"Codeforces","topic":"Competitive programming","description":"Competitive programming performance on Codeforces problems (ELO).","url":"https://codeforces.com/","leaderboard":"https://llmdb.com/benchmarks/codeforces","github":"","paper":"","metric":"ELO","stars":"","top_model":"DeepSeek V4.1-Flash","top_percent":3471,"top_model_id":"deepseek-v4.1-flash","top_generation":"DeepSeek V4.1","top_model_base":"DeepSeek V4.1 Flash","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":78,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":3471},{"place":2,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":3455},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":3362},{"place":4,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":3348},{"place":5,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":3329},{"place":6,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":3289},{"place":7,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":3206},{"place":8,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":3206},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":3188},{"place":10,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":3168},{"place":11,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":3148},{"place":12,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":3056},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":3052},{"place":14,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":3052},{"place":15,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":3052},{"place":16,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":3020},{"place":17,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":2919},{"place":18,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":2851},{"place":19,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":2816},{"place":20,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":2758},{"place":21,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":2727},{"place":22,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":2726},{"place":23,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":2719},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":2708},{"place":25,"model":"o3","company":"openai","family":"o3","version":"o3","score":2706},{"place":26,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":2701},{"place":27,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":2622},{"place":28,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":2537},{"place":29,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":2516},{"place":30,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":2386},{"place":31,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":2233},{"place":32,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":2160},{"place":33,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":2157},{"place":34,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":2150},{"place":35,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":2146},{"place":36,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":2121},{"place":37,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2100},{"place":38,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":2092},{"place":39,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":2091},{"place":40,"model":"ring-1t","company":"antgroup","family":"Ring","version":"Ring","score":2088},{"place":41,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":2073},{"place":42,"model":"qwen-3","company":"qwen","family":"Qwen","version":"Qwen3","score":2056},{"place":43,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":2056},{"place":44,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":2055},{"place":45,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":2046},{"place":46,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":2036},{"place":47,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":2029},{"place":48,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2028},{"place":49,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":2001},{"place":50,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":1985},{"place":51,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":1977},{"place":52,"model":"gpt-5-thinking-high","company":"openai","family":"GPT","version":"GPT-5","score":1918},{"place":53,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":1901},{"place":54,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1899},{"place":55,"model":"o1","company":"openai","family":"o1","version":"o1","score":1891},{"place":56,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":1891},{"place":57,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1837},{"place":58,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1718},{"place":59,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":1701.4},{"place":60,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1701},{"place":61,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1675},{"place":62,"model":"o1","company":"openai","family":"o1","version":"o1","score":1673},{"place":63,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1659},{"place":64,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":1650},{"place":65,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":1644},{"place":66,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":1600},{"place":67,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1582},{"place":68,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1574},{"place":69,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1485},{"place":70,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1480},{"place":71,"model":"deepseek-r1-lite-preview","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1450},{"place":72,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":1429},{"place":73,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":1428},{"place":74,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":1411.6},{"place":75,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":1258},{"place":76,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":1120},{"place":77,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":1044.5},{"place":78,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":940},{"place":79,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":882},{"place":80,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":774.4},{"place":81,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":759},{"place":82,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":732},{"place":83,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":717},{"place":84,"model":"hunyuan-80b-a13b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":683},{"place":85,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":678},{"place":86,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":633},{"place":87,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":605},{"place":88,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":110}]},{"id":"codeforces-percentile","name":"Codeforces (Percentile)","topic":"Competitive programming","description":"Competitive programming performance on Codeforces problems, reported as the percentile of human competitors outperformed.","url":"https://codeforces.com/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ring-1T-preview","top_percent":94.69,"top_model_id":"ring-1t-preview","top_generation":"Ring","top_model_base":"Ring-1T-preview","top_model_family":"Ring","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":27,"total_models":3854,"placements":[{"place":1,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":94.69},{"place":2,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":93.86},{"place":3,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.01},{"place":4,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":90.23},{"place":5,"model":"ring-flash-linear-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":89.9},{"place":6,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":89.77},{"place":7,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":89.67},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.84},{"place":9,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86.84},{"place":10,"model":"ring-mini-sparse-2.0-exp","company":"antgroup","family":"Ring","version":"Ring 2.0","score":85.77},{"place":11,"model":"ring-mini-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":84.8},{"place":12,"model":"qwen3-32b-thinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":84.25},{"place":13,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":83.78},{"place":14,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":82.25},{"place":15,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.59},{"place":16,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.31},{"place":17,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":59.5},{"place":18,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":55.4},{"place":19,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":51.6},{"place":20,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":35.6},{"place":21,"model":"qwen3-8b-nothinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":28.2},{"place":22,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":25.3},{"place":23,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.8},{"place":24,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":23.6},{"place":25,"model":"ernie-4.5-21b-a3b-pt","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":21.7},{"place":26,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":20.3},{"place":27,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":17.5}]},{"id":"codeif-bench","name":"CodeIF-Bench","topic":"Code instruction following","description":"Code-focused instruction following benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-8B Non-Thinking","top_percent":50,"top_model_id":"qwen3-8b-non-thinking","top_generation":"Qwen3","top_model_base":"Qwen3 8B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":50},{"place":2,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":48},{"place":3,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":46},{"place":4,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":46},{"place":5,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":42}]},{"id":"collegemath","name":"CollegeMath","topic":"College-level math","description":"College-level mathematics problems (MathScale) covering algebra, calculus, linear algebra, probability, etc.","url":"https://github.com/microsoft/unilm/tree/master/mathscale","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2403.02884","metric":"percent","stars":"","top_model":"Qwen2.5-Math-72B-Instruct","top_percent":49.5,"top_model_id":"qwen2.5-math-72b-instruct","top_generation":"Qwen2.5-Math","top_model_base":"Qwen2.5-Math 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":49.5},{"place":2,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":48.5},{"place":3,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":47.9},{"place":4,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.7},{"place":5,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":47.7},{"place":6,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.3},{"place":7,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":46.8},{"place":8,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":45.9},{"place":9,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":45.9},{"place":10,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":44.2},{"place":11,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.5},{"place":12,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":43.2},{"place":13,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":42.5},{"place":14,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":39.8},{"place":15,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":39.7},{"place":16,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":39.7},{"place":17,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":37.5},{"place":18,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":37.5},{"place":19,"model":"numinamath-7b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":36.9},{"place":20,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":36.2},{"place":21,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":33.8},{"place":22,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":33.7},{"place":23,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":24.5},{"place":24,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":10.4}]},{"id":"collie","name":"COLLIE","topic":"Instruction following","description":"Comprehensive instruction-following evaluation suite.","url":"https://collie-benchmark.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"55","top_model":"GPT-5","top_percent":99,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":99},{"place":2,"model":"o3","company":"openai","family":"o3","version":"o3","score":98.4},{"place":3,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":97.4},{"place":4,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":96.9},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":96.5},{"place":6,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":95.8},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":95},{"place":8,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":94},{"place":9,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":93.9},{"place":10,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":91.2},{"place":11,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.5},{"place":12,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.9},{"place":13,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.8},{"place":14,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":86.4},{"place":15,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.8},{"place":16,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.3},{"place":17,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":67.7},{"place":18,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":62.9},{"place":19,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":61.3},{"place":20,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":61},{"place":21,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":60.3},{"place":22,"model":"jamba2-mini","company":"ai21","family":"Jamba","version":"Jamba2","score":33},{"place":23,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":30},{"place":24,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":28},{"place":25,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":26}]},{"id":"collie-hard","name":"Collie-Hard","topic":"Instruction following","description":"Hard subset of Collie instruction-following tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":99,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":99},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":95.5},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.6},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":72.6},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.5}]},{"id":"commerceagentbench","name":"CommerceAgentBench","topic":"E-commerce agents","description":"Agentic benchmark of B2B/e-commerce sourcing and commerce workflows (Accio-Lab).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":49.5,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":49.5},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":46.3},{"place":3,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":43.3},{"place":4,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":39.3},{"place":5,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":37.4},{"place":6,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":37.38},{"place":7,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":30.8},{"place":8,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":19.6},{"place":9,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":16.8},{"place":10,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":9.3}]},{"id":"commonsenseqa","name":"CommonsenseQA","topic":"Commonsense QA","description":"Multiple-choice QA requiring commonsense knowledge.","url":"https://www.tau-nlp.org/csqa","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Hunyuan-Large","top_percent":92.9,"top_model_id":"hunyuan-large","top_generation":"Hunyuan-Large","top_model_base":"Hunyuan-Large","top_model_family":"Hunyuan","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":114,"total_models":3854,"placements":[{"place":1,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":92.9},{"place":2,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":90.99},{"place":3,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":90.7},{"place":4,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":89.93},{"place":5,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":89.76},{"place":6,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":88.62},{"place":7,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.5},{"place":8,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":88.3},{"place":9,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":87.71},{"place":10,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":87.55},{"place":11,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":87.31},{"place":12,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":86.98},{"place":13,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":86.5},{"place":14,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.24},{"place":15,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.8},{"place":16,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.8},{"place":17,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":85.26},{"place":18,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85},{"place":19,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":84.6},{"place":20,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":84.1},{"place":21,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":84.1},{"place":22,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":83.8},{"place":23,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.62},{"place":24,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.6},{"place":25,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":83.46},{"place":26,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":82.8},{"place":27,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":82.4},{"place":28,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":82.4},{"place":29,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":82.3},{"place":30,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":82.3},{"place":31,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":81.16},{"place":32,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":81.1},{"place":33,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":80.2},{"place":34,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.18},{"place":35,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":79.8},{"place":36,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":79.6},{"place":37,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":78.6},{"place":38,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":78.5},{"place":39,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":78.4},{"place":40,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":77.7},{"place":41,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":76.1},{"place":42,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":76.1},{"place":43,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":75.84},{"place":44,"model":"marin-32b-base","company":"marin","family":"Marin","version":"Marin 32B","score":75.5},{"place":45,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":75.3},{"place":46,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.3},{"place":47,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":75.3},{"place":48,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":75.2},{"place":49,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":75},{"place":50,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":74.9},{"place":51,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":74.1},{"place":52,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":74},{"place":53,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":74},{"place":54,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":74},{"place":55,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":73.55},{"place":56,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":73.4},{"place":57,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":73.3},{"place":58,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":72.9},{"place":59,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":72.6},{"place":60,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":72.6},{"place":61,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":72.5},{"place":62,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":72.1},{"place":63,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":72},{"place":64,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":71.3},{"place":65,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":71.1},{"place":66,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":70.6},{"place":67,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":70.4},{"place":68,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":70.35},{"place":69,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":70.3},{"place":70,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":70.3},{"place":71,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":70.11},{"place":72,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":70.1},{"place":73,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":70},{"place":74,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":69.94},{"place":75,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":69.7},{"place":76,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":69.5},{"place":77,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":69.04},{"place":78,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":68.8},{"place":79,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":68.7},{"place":80,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":68.39},{"place":81,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":68},{"place":82,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":67.57},{"place":83,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":67.4},{"place":84,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":67.3},{"place":85,"model":"apertus-v1.5-70b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":66.8},{"place":86,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":66.8},{"place":87,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":66.7},{"place":88,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":66.7},{"place":89,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":66.5},{"place":90,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":65.7},{"place":91,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":65.6},{"place":92,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":65.4},{"place":93,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":65.4},{"place":94,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":65.3},{"place":95,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":65},{"place":96,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":64.9},{"place":97,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":64.6},{"place":98,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":64.1},{"place":99,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":63.47},{"place":100,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":63},{"place":101,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":62.7},{"place":102,"model":"apertus-v1.5-8b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":62.3},{"place":103,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":62.3},{"place":104,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":62.2},{"place":105,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":62},{"place":106,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":61.8},{"place":107,"model":"glm-130b","company":"zai","family":"GLM","version":"GLM-130B","score":61.6},{"place":108,"model":"eurollm-22b-base","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":60.5},{"place":109,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":60.44},{"place":110,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":60.28},{"place":111,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":60.1},{"place":112,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":60},{"place":113,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":59.8},{"place":114,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":59.5},{"place":115,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":58.8},{"place":116,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":58.7},{"place":117,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":57.2},{"place":118,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":57},{"place":119,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":56.4},{"place":120,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":55.45},{"place":121,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":54.8},{"place":122,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":54.79},{"place":123,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":53.8},{"place":124,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":43.6},{"place":125,"model":"bloom-176b","company":"bigscience","family":"BLOOM","version":"176B","score":42.8},{"place":126,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":41.2},{"place":127,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":38},{"place":128,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.1},{"place":129,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":33.9},{"place":130,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":33.9},{"place":131,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":20.8},{"place":132,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":20.5}]},{"id":"complex-workflow","name":"Complex Workflow","topic":"Complex workflows","description":"Complex workflow benchmark for economically valuable tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":58.2,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":58.2},{"place":2,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.4},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":54.6},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.4},{"place":5,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":53}]},{"id":"complexfuncbench","name":"ComplexFuncBench","topic":"Code reasoning","description":"Complex function reasoning and synthesis benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-4o","top_percent":66.5,"top_model_id":"gpt-4o","top_generation":"GPT-4o","top_model_base":"GPT-4o","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":66.5},{"place":2,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":37.5},{"place":3,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":33.2},{"place":4,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":26.3},{"place":5,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":24.6},{"place":6,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":24.6},{"place":7,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":24.2},{"place":8,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":19},{"place":9,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":18.9}]},{"id":"complexfuncbench-audio","name":"ComplexFuncBench (Audio)","topic":"Spoken function calling","description":"ComplexFuncBench multi-step, constrained function calling with spoken user requests (%).","url":"https://github.com/THUDM/ComplexFuncBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Flash Live (high)","top_percent":90.8,"top_model_id":"gemini-3.1-flash-live-high","top_generation":"Gemini 3.1","top_model_base":"Gemini","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":90.8},{"place":2,"model":"gemini-2.5-flash-native-audio-preview-12-2025-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.5},{"place":3,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":66.5},{"place":4,"model":"gemini-2.5-flash-native-audio-preview-09-2025-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":66},{"place":5,"model":"nova-2-sonic","company":"amazon","family":"Nova","version":"Nova 2","score":65.2},{"place":6,"model":"gpt-4o-realtime-preview-2025-06-03","company":"openai","family":"GPT","version":"GPT-4o","score":58.9},{"place":7,"model":"gpt-4o-realtime-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o","score":49.7},{"place":8,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":28.7},{"place":9,"model":"nova-sonic","company":"amazon","family":"Nova","version":"Nova 1","score":26.9},{"place":10,"model":"gemini-2.5-flash-live-preview","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.5}]},{"id":"contphy","name":"ContPhy","topic":"Video physical reasoning","description":"Continuum Physical Concept Learning and Reasoning from videos.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":67.4,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":67.4},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.5},{"place":3,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":63.8},{"place":4,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":63.6},{"place":5,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":62.4},{"place":6,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":62},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":61.1},{"place":8,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":61.1},{"place":9,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":56.1},{"place":10,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":55.9}]},{"id":"contract-scrub","name":"Contract Scrub","topic":"Contract review","description":"Contract-review task: identify and redact/flag clauses in legal contracts (Thomson Reuters eval).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":54.8,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.8},{"place":2,"model":"thomson-1.0-small","company":"thomsonreuters","family":"Thomson","version":"Thomson-1.0","score":44.6},{"place":3,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.6},{"place":4,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":38.5},{"place":5,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":36.5}]},{"id":"contractnli","name":"ContractNLI","topic":"Legal NLI","description":"Document-level natural language inference over contracts; macro-F1 (Jev Decision Index suite, posed as typed decisions).","url":"https://stanfordnlp.github.io/contract-nli/","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"Clef-Flash","top_percent":84.3,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":39,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":84.3},{"place":2,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":84},{"place":3,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":83.1},{"place":4,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":82.9},{"place":5,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":81.5},{"place":6,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":81.4},{"place":7,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":80.78},{"place":8,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":80.6},{"place":9,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":80.3},{"place":10,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":78.9},{"place":11,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":78.5},{"place":12,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":76.1},{"place":13,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":76.1},{"place":14,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":76},{"place":15,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":75.1},{"place":16,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":75},{"place":17,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":74.7},{"place":18,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":74.1},{"place":19,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":73.9},{"place":20,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":73},{"place":21,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":71.7},{"place":22,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":70.8},{"place":23,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":70.7},{"place":24,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":70.3},{"place":25,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":68.8},{"place":26,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":67.7},{"place":27,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":66.2},{"place":28,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":62},{"place":29,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":60.5},{"place":30,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":57.8},{"place":31,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56.5},{"place":32,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":54.2},{"place":33,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":46.1},{"place":34,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":44.8},{"place":35,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":44.5},{"place":36,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":35.4},{"place":37,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":31},{"place":38,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":29},{"place":39,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":21.8}]},{"id":"convfinqa","name":"ConvFinQA","topic":"Conversational QA","description":"Conversational numerical reasoning over financial reports (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":86.5,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86.5},{"place":2,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":83.5},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":82.3},{"place":4,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":81.9},{"place":5,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":81.5},{"place":6,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":79.8},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":75.7},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":73.1},{"place":9,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":72.3},{"place":10,"model":"o3","company":"openai","family":"o3","version":"o3","score":67.8}]},{"id":"copa","name":"COPA","topic":"Causal reasoning","description":"Choice of Plausible Alternatives.","url":"https://people.ict.usc.edu/~gordon/copa.html","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Vega v2","top_percent":99.4,"top_model_id":"vega-v2","top_generation":"Vega v2","top_model_base":"Vega v2","top_model_family":"Vega","top_company":"jd","top_open_source":0,"lower_is_better":false,"bench_models":41,"total_models":3854,"placements":[{"place":1,"model":"vega-v2","company":"jd","family":"Vega","version":"Vega v2","score":99.4},{"place":2,"model":"st-moe-32b","company":"google","family":"ST","version":"ST-MoE-32B","score":99.2},{"place":3,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":99},{"place":4,"model":"hairuo","company":"generic","family":"Hairuo","version":"Hairuo","score":98.8},{"place":5,"model":"deberta-turingnlrv4","company":"microsoft","family":"DeBERTa","version":"DeBERTa / TuringNLRv4","score":98.4},{"place":6,"model":"turing-nlr-v5","company":"microsoft","family":"Turing","version":"Turing NLR v5","score":98.2},{"place":7,"model":"t5-plus-udg-single-model-google-brain","company":"google","family":"T5","version":"T5 + UDG, Single Model (Google Brain)","score":98},{"place":8,"model":"ernie-3.0","company":"baidu","family":"ERNIE","version":"ERNIE 3.0","score":97.4},{"place":9,"model":"select-step-by-step","company":"unknown","family":"select","version":"select-step-by-step","score":96.4},{"place":10,"model":"frozen-t5-1.1-plus-spot","company":"google","family":"Frozen","version":"Frozen T5 1.1 + SPoT","score":95.6},{"place":11,"model":"t5","company":"google","family":"T5","version":"T5","score":94.8},{"place":12,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":94},{"place":13,"model":"nezha-plus","company":"huawei","family":"NEZHA","version":"NEZHA-Plus","score":93.6},{"place":14,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":93},{"place":15,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":93},{"place":16,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":93},{"place":17,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":93},{"place":18,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":92},{"place":19,"model":"pai-albert","company":"alibaba","family":"PAI","version":"PAI Albert","score":91.8},{"place":20,"model":"roberta-icets","company":"infosys","family":"RoBERTa","version":"RoBERTa-iCETS","score":91.2},{"place":21,"model":"roberta-mtl-adv","company":"zhuiyi","family":"RoBERTa","version":"RoBERTa-mtl-adv","score":91.2},{"place":22,"model":"ipet-albert-few-shot-32-examples","company":"lmu","family":"iPET","version":"iPET (ALBERT) - Few-Shot (32 Examples)","score":90.8},{"place":23,"model":"roberta-ensemble","company":"tencent","family":"RoBERTa","version":"RoBERTa (ensemble)","score":90.8},{"place":24,"model":"roberta","company":"meta","family":"RoBERTa","version":"RoBERTa","score":90.6},{"place":25,"model":"bort-alexa-ai","company":"amazon","family":"Bort","version":"Bort (Alexa AI)","score":89.6},{"place":26,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87},{"place":27,"model":"fsl-plus-plus-albert-few-shot-32-examples","company":"unknown","family":"FSL++(ALBERT)","version":"FSL++(ALBERT)-Few-Shot(32 Examples)","score":87},{"place":28,"model":"ailabs-team-transformers","company":"unknown","family":"AILabs","version":"AILabs Team, Transformers","score":86.8},{"place":29,"model":"install-albert-few-shot-32examples","company":"casia","family":"INSTALL(ALBERT)","version":"INSTALL(ALBERT)-few-shot(32examples)","score":85.6},{"place":30,"model":"adapet-albert-few-shot","company":"unc","family":"ADAPET","version":"ADAPET (ALBERT) - few-shot","score":85.4},{"place":31,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":85},{"place":32,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":83},{"place":33,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":82},{"place":34,"model":"text-to-text-petl","company":"berkeley","family":"Text","version":"Text to Text PETL","score":80.2},{"place":35,"model":"snorkel-superglue-v1.9","company":"stanford","family":"Snorkel","version":"Snorkel [SuperGLUE v1.9]","score":76.2},{"place":36,"model":"bert-plus-plus","company":"nyu","family":"BERT++","version":"BERT++","score":73.8},{"place":37,"model":"bert-mtl","company":"ibm","family":"BERT","version":"BERT-mtl","score":73.8},{"place":38,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":72},{"place":39,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":71},{"place":40,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":70},{"place":41,"model":"warp-albert-xxl-v2-few-shot-32-examples","company":"yerevann","family":"WARP","version":"WARP (ALBERT-XXL-V2) - Few-Shot (32 Examples)","score":51.6}]},{"id":"coqa","name":"CoQA","topic":"Conversational QA","description":"Conversational question answering (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":94.6,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":94.6},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":82.5},{"place":3,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":77},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":76.4},{"place":5,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":76.1},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":73.5},{"place":7,"model":"o3","company":"openai","family":"o3","version":"o3","score":69.4},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":68.8},{"place":9,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":64.8},{"place":10,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":62.5}]},{"id":"core","name":"CORE","topic":"Ontological reasoning","description":"Comprehensive Ontological Relation Evaluation for Large Language Models.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nanbeige4.1-3B","top_percent":53.47,"top_model_id":"nanbeige4.1-3b","top_generation":"Nanbeige4.1","top_model_base":"Nanbeige4.1 3B","top_model_family":"Nanbeige","top_company":"boss","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":53.47},{"place":2,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.52}]},{"id":"coronavirus-ace2-cell-entry-screen","name":"Coronavirus-ACE2 Cell-Entry Screen","topic":"Biosecurity","description":"Predict and rank held-out cell-entry measurements for spike-protein-ACE2 pairings; clipped composite score (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"GPT-6.1 Terra","top_percent":0.4741,"top_model_id":"gpt-6.1-terra","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.4741},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.463},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.45},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.43},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.423},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.42},{"place":7,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":0.36},{"place":8,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":0.349}]},{"id":"corpfin","name":"CorpFin","topic":"Corporate finance","description":"Corporate finance reasoning and numerical literacy benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Grok 4 Fast","top_percent":73.3,"top_model_id":"grok-4-fast","top_generation":"Grok 4","top_model_base":"Grok 4 Fast","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":73.3},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":71.8},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":71.6},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":68.4},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":66.7},{"place":6,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":66.1},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.4}]},{"id":"corpusqa","name":"CorpusQA","topic":"Long-context QA","description":"Question answering over large text corpora.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":81.56,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.56},{"place":2,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":81.25},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.62},{"place":4,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.38},{"place":5,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":77.5},{"place":6,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":75.31},{"place":7,"model":"qwen3-max-thinking-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":74.69},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":71.7},{"place":9,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.56},{"place":10,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":64.38},{"place":11,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62},{"place":12,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":60.5},{"place":13,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.3},{"place":14,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.5},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":53.8},{"place":16,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":50.31},{"place":17,"model":"qwenlong-l1","company":"qwen","family":"QwenLong","version":"QwenLong","score":42.5},{"place":18,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35.6},{"place":19,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":15.5}]},{"id":"cosmos-reason-bench","name":"COSMOS (Cosmos-Reason benchmark)","topic":"Embodied reasoning","description":"NVIDIA Cosmos-Reason embodied physical-reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":75.7,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":75.7},{"place":2,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":72.8},{"place":3,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":71.2},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":71},{"place":5,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":67.5},{"place":6,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":66.8},{"place":7,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":65.3},{"place":8,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":64.5},{"place":9,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":64.3},{"place":10,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.6},{"place":11,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":57.7},{"place":12,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":56.5},{"place":13,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":46.5}]},{"id":"countbench","name":"CountBench","topic":"Visual counting","description":"Object counting and numeracy benchmark for visual-language models across varied scenes.","url":"https://huggingface.co/datasets/nielsr/countbench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2302.12066","metric":"percent","stars":"","top_model":"Qwen3.5-27B","top_percent":97.8,"top_model_id":"qwen3.5-27b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 27B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":96,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97.8},{"place":2,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97.8},{"place":3,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":97.8},{"place":4,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":97.6},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":97.35},{"place":6,"model":"ling-3.0-flash-vl","company":"antgroup","family":"Ling","version":"Ling 3.0","score":97.33},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":97.3},{"place":8,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97.2},{"place":9,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97.2},{"place":10,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":97.1},{"place":11,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97},{"place":12,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":96.7},{"place":13,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":96.54},{"place":14,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":96.3},{"place":15,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":96.3},{"place":16,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":96.1},{"place":17,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":96.1},{"place":18,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":96.1},{"place":19,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":96.1},{"place":20,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":95.7},{"place":21,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":95.1},{"place":22,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":95.1},{"place":23,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":95.1},{"place":24,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94.9},{"place":25,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":94.1},{"place":26,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":93.9},{"place":27,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":93.7},{"place":28,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":93.7},{"place":29,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":93.7},{"place":30,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":93.7},{"place":31,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":93.6},{"place":32,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":93.2},{"place":33,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":93.1},{"place":34,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":92.9},{"place":35,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.67},{"place":36,"model":"r-4b-base","company":"tencent","family":"R","version":"R","score":92.6},{"place":37,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":92.4},{"place":38,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":92.4},{"place":39,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":91.99},{"place":40,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":91.9},{"place":41,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":91.8},{"place":42,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":91.8},{"place":43,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":91.8},{"place":44,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.79},{"place":45,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":91.7},{"place":46,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":91.7},{"place":47,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":91.5},{"place":48,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.4},{"place":49,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":91.2},{"place":50,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.2},{"place":51,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91},{"place":52,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":91},{"place":53,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91},{"place":54,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":91},{"place":55,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":91},{"place":56,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":90.8},{"place":57,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.8},{"place":58,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.6},{"place":59,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.6},{"place":60,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":90.4},{"place":61,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.4},{"place":62,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":90.2},{"place":63,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":90.2},{"place":64,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90},{"place":65,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90},{"place":66,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":90},{"place":67,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.8},{"place":68,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.4},{"place":69,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89},{"place":70,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":89},{"place":71,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":89},{"place":72,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":88.88},{"place":73,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":88.5},{"place":74,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.4},{"place":75,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":88.2},{"place":76,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":88},{"place":77,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":88},{"place":78,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":87.8},{"place":79,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.3},{"place":80,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":87.1},{"place":81,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":87.1},{"place":82,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":87},{"place":83,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.7},{"place":84,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86},{"place":85,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":85.8},{"place":86,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":85.7},{"place":87,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.5},{"place":88,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":84.9},{"place":89,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.8},{"place":90,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":84.2},{"place":91,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":84.1},{"place":92,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.1},{"place":93,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":83.9},{"place":94,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":83.8},{"place":95,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":82.2},{"place":96,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":82.1},{"place":97,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":81.6},{"place":98,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.5},{"place":99,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.5},{"place":100,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":80},{"place":101,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":80},{"place":102,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":79.6},{"place":103,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.2},{"place":104,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.2},{"place":105,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77},{"place":106,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":76.4},{"place":107,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":75.1},{"place":108,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":74.1},{"place":109,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":73.7},{"place":110,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":73.31},{"place":111,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":72.5},{"place":112,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":64.5},{"place":113,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":62.2},{"place":114,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":61.81},{"place":115,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.4},{"place":116,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":48.4},{"place":117,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":47.64}]},{"id":"countbenchqa","name":"CountBenchQA","topic":"Visual counting QA","description":"Visual question answering benchmark focused on counting objects across varied scenes.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"dots.mocr","top_percent":94.46,"top_model_id":"dots.mocr","top_generation":"dots","top_model_base":"dots.mocr","top_model_family":"dots","top_company":"rednote","top_open_source":1,"lower_is_better":false,"bench_models":50,"total_models":3854,"placements":[{"place":1,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":94.46},{"place":2,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.5},{"place":3,"model":"moondream-9b-a2b","company":"moondream","family":"Moondream","version":"Moondream 3","score":93.2},{"place":4,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":92.2},{"place":5,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":91.2},{"place":6,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":91.2},{"place":7,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":90.1},{"place":8,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":89.7},{"place":9,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":89.3},{"place":10,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":89},{"place":11,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":88.5},{"place":12,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.4},{"place":13,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":88.1},{"place":14,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":87.9},{"place":15,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":87.3},{"place":16,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":87.2},{"place":17,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.9},{"place":18,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.7},{"place":19,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":85.8},{"place":20,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.9},{"place":21,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.8},{"place":22,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":84.3},{"place":23,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.2},{"place":24,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.8},{"place":25,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":83.6},{"place":26,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.2},{"place":27,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":83},{"place":28,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":82.9},{"place":29,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":82.5},{"place":30,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":82.1},{"place":31,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":81.9},{"place":32,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":81.6},{"place":33,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.2},{"place":34,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":80.6},{"place":35,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.5},{"place":36,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":80.4},{"place":37,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.1},{"place":38,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":79.2},{"place":39,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":78.8},{"place":40,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":78.8},{"place":41,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":78.5},{"place":42,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.4},{"place":43,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":77.4},{"place":44,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":76.5},{"place":45,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":76.4},{"place":46,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":75.6},{"place":47,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":74.7},{"place":48,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":73.1},{"place":49,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72},{"place":50,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":70.8},{"place":51,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":70.6},{"place":52,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":70.4},{"place":53,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":70.4},{"place":54,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":69.9},{"place":55,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":64.6},{"place":56,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":57.8},{"place":57,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":47.1},{"place":58,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":40.1}]},{"id":"countdown","name":"Countdown","topic":"Planning and reasoning","description":"Countdown-style reasoning and planning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"K2-V2","top_percent":75.6,"top_model_id":"k2-v2","top_generation":"K2 V2","top_model_base":"K2 V2","top_model_family":"K2","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":75.6},{"place":2,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":23.2},{"place":3,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":6},{"place":4,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":1.3},{"place":5,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":1},{"place":6,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":0.5}]},{"id":"countix","name":"Countix","topic":"Video counting","description":"Video-based counting benchmark for multiple objects.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":31,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":31},{"place":2,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":26},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":18.7},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":18.6}]},{"id":"countqa","name":"CountQA","topic":"Visual counting","description":"Visual question answering benchmark on object counting in real-world images.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":86.42,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":41,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":86.42},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":86.42},{"place":3,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":82.66},{"place":4,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.4},{"place":5,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":82.2},{"place":6,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":81.09},{"place":7,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":77},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":72.8},{"place":9,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":71.7},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":68.6},{"place":11,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":66.88},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.1},{"place":13,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":58.4},{"place":14,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":57.1},{"place":15,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":52.81},{"place":16,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":52.4},{"place":17,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":47.9},{"place":18,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.6},{"place":19,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":41.3},{"place":20,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40.58},{"place":21,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":37.6},{"place":22,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":35.93},{"place":23,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.86},{"place":24,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":32.5},{"place":25,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":32.4},{"place":26,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":31.74},{"place":27,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":31.41},{"place":28,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":30.82},{"place":29,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.99},{"place":30,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":28.27},{"place":31,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.14},{"place":32,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":23.63},{"place":33,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":23.43},{"place":34,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":22.64},{"place":35,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":22.58},{"place":36,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":22.32},{"place":37,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":20.94},{"place":38,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":20.72},{"place":39,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":18.91},{"place":40,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":18.5},{"place":41,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":4.71}]},{"id":"covost","name":"CoVoST","topic":"Speech translation","description":"CoVoST speech-to-text translation benchmark (BLEU).","url":"https://github.com/facebookresearch/covost","leaderboard":"","github":"","paper":"","metric":"bleu","stars":"","top_model":"Gemma 4 E4B IT","top_percent":35.54,"top_model_id":"gemma-4-e4b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 E4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":35.54},{"place":2,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.47}]},{"id":"crag","name":"CRAG","topic":"Retrieval QA","description":"Complex Retrieval-Augmented Generation benchmark for grounded question answering.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Jamba Mini 1.6","top_percent":76.2,"top_model_id":"jamba-mini-1.6","top_generation":"Jamba Mini","top_model_base":"Jamba Mini 1.6","top_model_family":"Jamba","top_company":"ai21","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":76.2},{"place":2,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":60},{"place":3,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":52},{"place":4,"model":"command-r7b","company":"cohere","family":"Command","version":"Command","score":23.1}]},{"id":"creative-story-writing-v3","name":"Creative Story‑Writing Benchmark V3","topic":"Creative writing","description":"Story writing benchmark evaluating creativity, coherence, and style (v3).","url":"","leaderboard":"https://github.com/lechmazur/writing","github":"https://github.com/lechmazur/writing","paper":"","metric":"score","stars":"291","top_model":"Kimi-K2-Instruct-0905","top_percent":8.749,"top_model_id":"kimi-k2-instruct-0905","top_generation":"Kimi K2","top_model_base":"Kimi K2","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":8.749},{"place":2,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":8.729},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":8.723},{"place":4,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":8.711},{"place":5,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":8.693},{"place":6,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":8.629},{"place":7,"model":"o3-pro","company":"openai","family":"o3","version":"o3","score":8.628},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":8.602},{"place":9,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":8.538},{"place":10,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":8.517},{"place":11,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":8.507},{"place":12,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":8.495},{"place":13,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":8.114},{"place":14,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":8.11},{"place":15,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":8.068},{"place":16,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":7.803},{"place":17,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":7.726},{"place":18,"model":"command-a","company":"cohere","family":"Command","version":"Command","score":7.459},{"place":19,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":6.37}]},{"id":"creative-writing-longform","name":"Longform Creative Writing","topic":"Creative writing","description":"Longform creative writing evaluation (EQ-Bench).","url":"https://eqbench.com/creative_writing_longform.html","leaderboard":"https://eqbench.com/creative_writing_longform.html","github":"https://github.com/EQ-bench","paper":"https://arxiv.org/abs/2312.06281","metric":"percent","stars":"20","top_model":"Claude Opus 5","top_percent":86.3,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":145,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.3},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":85.3},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":84.6},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83},{"place":5,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":83},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":82.8},{"place":7,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":82.8},{"place":8,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":82.8},{"place":9,"model":"aion-3.5","company":"aionlabs","family":"Aion","version":"Aion 3.5","score":82.1},{"place":10,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":81.8},{"place":11,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":81.8},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":81.7},{"place":13,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":81.5},{"place":14,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80.8},{"place":15,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":79.9},{"place":16,"model":"ox-alpha","company":"","family":"Stealth","version":"Ox","score":79.9},{"place":17,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.8},{"place":18,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":79.6},{"place":19,"model":"deepseek-v3-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":78.9},{"place":20,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":78.5},{"place":21,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":78.3},{"place":22,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":78.3},{"place":23,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":78.2},{"place":24,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":78},{"place":25,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":77.9},{"place":26,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.7},{"place":27,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":76.8},{"place":28,"model":"deepseek-tng-r1t2-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T2","score":76.4},{"place":29,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.6},{"place":30,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":75.5},{"place":31,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":74.9},{"place":32,"model":"hemmingway-1","company":"altworld","family":"Hemmingway","version":"Hemmingway-1","score":74.2},{"place":33,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":74.1},{"place":34,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":74},{"place":35,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73.8},{"place":36,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":73.7},{"place":37,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":73.6},{"place":38,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":73.5},{"place":39,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":73.5},{"place":40,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.1},{"place":41,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":73.1},{"place":42,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":73},{"place":43,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":72.8},{"place":44,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":72.5},{"place":45,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":72.5},{"place":46,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72},{"place":47,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":71.8},{"place":48,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":71.6},{"place":49,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":71.6},{"place":50,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":71.4},{"place":51,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.4},{"place":52,"model":"horizon-alpha","company":"openai","family":"GPT","version":"Horizon","score":71.2},{"place":53,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":70.9},{"place":54,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":70.9},{"place":55,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":70.9},{"place":56,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70.7},{"place":57,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":70.6},{"place":58,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":70.5},{"place":59,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":69.5},{"place":60,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69},{"place":61,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":68.8},{"place":62,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":68.5},{"place":63,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.3},{"place":64,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":68.2},{"place":65,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":68.1},{"place":66,"model":"hermes-4-405b","company":"nousresearch","family":"Hermes","version":"Hermes 4","score":66.8},{"place":67,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":66.8},{"place":68,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":66.8},{"place":69,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":66.2},{"place":70,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":66},{"place":71,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":66},{"place":72,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":65.3},{"place":73,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65},{"place":74,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":63.8},{"place":75,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":62.8},{"place":76,"model":"o3","company":"openai","family":"o3","version":"o3","score":62.7},{"place":77,"model":"hunter-alpha","company":"","family":"Stealth","version":"Hunter","score":62.7},{"place":78,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":62.6},{"place":79,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":62.3},{"place":80,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.2},{"place":81,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60.2},{"place":82,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":60.2},{"place":83,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":60.1},{"place":84,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.5},{"place":85,"model":"deepseek-tng-r1t-chimera-20250427","company":"tng","family":"DeepSeek","version":"2025-04-27","score":59.4},{"place":86,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.1},{"place":87,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":88,"model":"gemini-2.5-pro-preview-03-25","company":"google","family":"Gemini","version":"Gemini 2.5","score":58.8},{"place":89,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":58.4},{"place":90,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":58.4},{"place":91,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":57.8},{"place":92,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":57.8},{"place":93,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":57.7},{"place":94,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.4},{"place":95,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":57.3},{"place":96,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":56.5},{"place":97,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":56.2},{"place":98,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":56.2},{"place":99,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":55.7},{"place":100,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":55.5},{"place":101,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.3},{"place":102,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":53.6},{"place":103,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":53.3},{"place":104,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":53.1},{"place":105,"model":"hermes-4-405b","company":"nousresearch","family":"Hermes","version":"Hermes 4","score":51.2},{"place":106,"model":"healer-alpha","company":"","family":"Stealth","version":"Healer","score":51},{"place":107,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":50.8},{"place":108,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.7},{"place":109,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":49},{"place":110,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":48.8},{"place":111,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.7},{"place":112,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.6},{"place":113,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":48.3},{"place":114,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":47.8},{"place":115,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":47.3},{"place":116,"model":"sherlock-dash-alpha","company":"xai","family":"Stealth","version":"Sherlock","score":47.2},{"place":117,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":47},{"place":118,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":46.4},{"place":119,"model":"bert-nebulon-alpha","company":"mistral","family":"Stealth","version":"Bert-Nebulon","score":46.4},{"place":120,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":46.2},{"place":121,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":45.7},{"place":122,"model":"gemma-3-27b-it-antislop","company":"sam-paech","family":"Gemma","version":"Gemma 3","score":45.2},{"place":123,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.5},{"place":124,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":43.2},{"place":125,"model":"sonoma-sky","company":"","family":"Sonoma","version":"Sonoma","score":42.9},{"place":126,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":41.9},{"place":127,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":41.8},{"place":128,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":41.6},{"place":129,"model":"reka-flash-3","company":"reka","family":"Reka Flash","version":"Reka Flash","score":41.2},{"place":130,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.5},{"place":131,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":40.1},{"place":132,"model":"ftpo-exp501","company":"sam-paech","family":"FTPO","version":"FTPO","score":39.7},{"place":133,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":38.8},{"place":134,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":36.9},{"place":135,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.9},{"place":136,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":35.8},{"place":137,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.6},{"place":138,"model":"longcat-flash-chat","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":35.1},{"place":139,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":35},{"place":140,"model":"minimax-m2-her","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":34.8},{"place":141,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":34.4},{"place":142,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":32.9},{"place":143,"model":"mistral-small-creative","company":"mistral","family":"Mistral","version":"Mistral Small","score":32.6},{"place":144,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":32.4},{"place":145,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":31.9},{"place":146,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":31.9},{"place":147,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":31.5},{"place":148,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":31.5},{"place":149,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":31.1},{"place":150,"model":"aurora-alpha","company":"","family":"Stealth","version":"Aurora","score":29.4},{"place":151,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":28.7},{"place":152,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":28},{"place":153,"model":"solar-pro-3","company":"upstage","family":"Solar","version":"Solar Pro 3","score":27},{"place":154,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":22.8},{"place":155,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":21.2},{"place":156,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":17}]},{"id":"creative-writing-v3","name":"Creative Writing v3","topic":"Creative writing","description":"A LLM-judged creative writing benchmark.","url":"https://eqbench.com/creative_writing.html","leaderboard":"https://eqbench.com/creative_writing.html","github":"https://github.com/EQ-bench","paper":"https://arxiv.org/abs/2312.06281","metric":"ELO","stars":"54","top_model":"GPT-6 Astra","top_percent":2173.3,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":190,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":2173.3},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":2162},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":2132.6},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":2124.7},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":2082.3},{"place":6,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":2075},{"place":7,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":2050.1},{"place":8,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":2006.7},{"place":9,"model":"ox-alpha","company":"","family":"Stealth","version":"Ox","score":1971.7},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":1971.6},{"place":11,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":1943.1},{"place":12,"model":"aion-3.5","company":"aionlabs","family":"Aion","version":"Aion 3.5","score":1929.3},{"place":13,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":1927.1},{"place":14,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1914.3},{"place":15,"model":"hemmingway-1","company":"altworld","family":"Hemmingway","version":"Hemmingway-1","score":1906.4},{"place":16,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1905.9},{"place":17,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":1854.9},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1843.9},{"place":19,"model":"qwen3.8-2.4t-a95b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1842.5},{"place":20,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":1840.4},{"place":21,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1839.8},{"place":22,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":1839.7},{"place":23,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":1828.7},{"place":24,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1810.4},{"place":25,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1809.1},{"place":26,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":1798.3},{"place":27,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":1794},{"place":28,"model":"space-bunny-alpha","company":"","family":"Stealth","version":"Space Bunny","score":1784.3},{"place":29,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":1756.5},{"place":30,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":1747.9},{"place":31,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":1724.5},{"place":32,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":1723.2},{"place":33,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":1702.9},{"place":34,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1692.4},{"place":35,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":1689.9},{"place":36,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1686.7},{"place":37,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1677.6},{"place":38,"model":"o3","company":"openai","family":"o3","version":"o3","score":1675.6},{"place":39,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1671.3},{"place":40,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1665.7},{"place":41,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":1665},{"place":42,"model":"o3","company":"openai","family":"o3","version":"o3","score":1661},{"place":43,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1648.4},{"place":44,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1631},{"place":45,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1630.9},{"place":46,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":1628.3},{"place":47,"model":"horizon-beta","company":"openai","family":"GPT","version":"Horizon","score":1627.3},{"place":48,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":1626.6},{"place":49,"model":"horizon-alpha","company":"openai","family":"GPT","version":"Horizon","score":1622.7},{"place":50,"model":"pony-alpha","company":"","family":"Stealth","version":"Pony","score":1616.7},{"place":51,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1610.8},{"place":52,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":1603.5},{"place":53,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":1600.6},{"place":54,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":1592.2},{"place":55,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1579.7},{"place":56,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":1578.8},{"place":57,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1578.6},{"place":58,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":1573.6},{"place":59,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1559.1},{"place":60,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":1559.1},{"place":61,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1553.2},{"place":62,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1540.1},{"place":63,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":1524.5},{"place":64,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1515},{"place":65,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":1501.2},{"place":66,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1500},{"place":67,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1499.9},{"place":68,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1493.4},{"place":69,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1491.4},{"place":70,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1491.3},{"place":71,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1489},{"place":72,"model":"hunter-alpha","company":"","family":"Stealth","version":"Hunter","score":1483.9},{"place":73,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1482.8},{"place":74,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":1480.2},{"place":75,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1478.2},{"place":76,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1477.9},{"place":77,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1475.7},{"place":78,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1472.3},{"place":79,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1450.8},{"place":80,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1444.3},{"place":81,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1441.1},{"place":82,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1435.9},{"place":83,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":1421.2},{"place":84,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1421.1},{"place":85,"model":"hermes-4-405b","company":"nousresearch","family":"Hermes","version":"Hermes 4","score":1420.8},{"place":86,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":1419.7},{"place":87,"model":"optimus-alpha","company":"openbmb","family":"Optimus","version":"Optimus","score":1417.4},{"place":88,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":1413.3},{"place":89,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1412.2},{"place":90,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1411.7},{"place":91,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":1411.1},{"place":92,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":1396.1},{"place":93,"model":"mistral-small-creative","company":"mistral","family":"Mistral","version":"Mistral Small","score":1369.4},{"place":94,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1368.2},{"place":95,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":1365.8},{"place":96,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":1361},{"place":97,"model":"quasar-alpha","company":"quasar","family":"Quasar","version":"Quasar","score":1351},{"place":98,"model":"chatgpt-4o-latest-20250129","company":"openai","family":"GPT","version":"GPT-4o","score":1346.4},{"place":99,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1343.3},{"place":100,"model":"sherlock-dash-alpha","company":"xai","family":"Stealth","version":"Sherlock","score":1332.7},{"place":101,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":1327.4},{"place":102,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":1313},{"place":103,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1304.6},{"place":104,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1288.9},{"place":105,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1280.3},{"place":106,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1276.3},{"place":107,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1265.7},{"place":108,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":1258},{"place":109,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":1257.2},{"place":110,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":1255.4},{"place":111,"model":"reka-flash-3","company":"reka","family":"Reka Flash","version":"Reka Flash","score":1227.8},{"place":112,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":1185.8},{"place":113,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":1147},{"place":114,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1145.7},{"place":115,"model":"command-a","company":"cohere","family":"Command","version":"Command","score":1145.1},{"place":116,"model":"gemini-2.5-flash-preview-04-17","company":"google","family":"Gemini","version":"Gemini 2.5","score":1136.9},{"place":117,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":1127.5},{"place":118,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1125.5},{"place":119,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":1124.7},{"place":120,"model":"gemma-3-glitter-12b","company":"allura-org","family":"Gemma","version":"Gemma 3","score":1118.4},{"place":121,"model":"darkest-muse-v1","company":"sam-paech","family":"Gemma","version":"Gemma 2","score":1104.2},{"place":122,"model":"glm-4-32b","company":"zai","family":"GLM","version":"GLM 4","score":1068.1},{"place":123,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1068},{"place":124,"model":"gemma-2-ifable-9b","company":"ifable","family":"Gemma","version":"Gemma 2","score":1002.4},{"place":125,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":987.7},{"place":126,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":984.9},{"place":127,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":961},{"place":128,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":945.8},{"place":129,"model":"gemma-3-starshine-12b","company":"toastypigeon","family":"Gemma","version":"Gemma 3","score":885.6},{"place":130,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":880.9},{"place":131,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":872.8},{"place":132,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":870.1},{"place":133,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":860.1},{"place":134,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":841.4},{"place":135,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":841.2},{"place":136,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":783.6},{"place":137,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":783.1},{"place":138,"model":"cypher-alpha","company":"","family":"Stealth","version":"Cypher","score":776.9},{"place":139,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":760.9},{"place":140,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":752.2},{"place":141,"model":"lfm-7b","company":"liquid","family":"LFM","version":"LFM","score":751.7},{"place":142,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":717.3},{"place":143,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":713},{"place":144,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":706.5},{"place":145,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":704.9},{"place":146,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":665.6},{"place":147,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":595.3},{"place":148,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":450.9},{"place":149,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":200},{"place":150,"model":"gpt-5-thinking-high","company":"openai","family":"GPT","version":"GPT-5","score":89.69},{"place":151,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.5},{"place":152,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":86},{"place":153,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86},{"place":154,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.7},{"place":155,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":85.5},{"place":156,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.49},{"place":157,"model":"ring-1t","company":"antgroup","family":"Ring","version":"Ring","score":85.4},{"place":158,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":85.3},{"place":159,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":85.24},{"place":160,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":85.17},{"place":161,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":85},{"place":162,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":84.9},{"place":163,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.6},{"place":164,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.6},{"place":165,"model":"ring-flash-linear-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":84.51},{"place":166,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84.4},{"place":167,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":84.33},{"place":168,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83.6},{"place":169,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":83.58},{"place":170,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.54},{"place":171,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":83.46},{"place":172,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":82.5},{"place":173,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.5},{"place":174,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":82.17},{"place":175,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":82.1},{"place":176,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":81.8},{"place":177,"model":"qwen3-32b-thinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":81},{"place":178,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":81},{"place":179,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":80.77},{"place":180,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":80.6},{"place":181,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.4},{"place":182,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":80.3},{"place":183,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.1},{"place":184,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":79.09},{"place":185,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":77.57},{"place":186,"model":"jan-v1-2509","company":"menlo","family":"Jan","version":"Jan v1","score":75.73},{"place":187,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":72.57},{"place":188,"model":"jan-v1","company":"menlo","family":"Jan","version":"Jan v1","score":72.08},{"place":189,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":68.56},{"place":190,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.74},{"place":191,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.71},{"place":192,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":46.96},{"place":193,"model":"jan-v1-edge","company":"menlo","family":"Jan","version":"Jan v1","score":45.31},{"place":194,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":44.22},{"place":195,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":41.67},{"place":196,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":38.84},{"place":197,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":38.79},{"place":198,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.49},{"place":199,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":36.44},{"place":200,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":32.6},{"place":201,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":31.56},{"place":202,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":31.43},{"place":203,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":22.18}]},{"id":"critpt","name":"Complex Research using Integrated Thinking – Physics Test","topic":"Reasoning","description":"CritPt (Complex Research using Integrated Thinking – Physics Test) benchmark.","url":"https://critpt.com/","leaderboard":"https://critpt.com/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":32.3,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":95,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":32.3},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":29.1},{"place":3,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":28.6},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":28.6},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":27.1},{"place":6,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":23.4},{"place":7,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":22.9},{"place":8,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":21},{"place":9,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":20.9},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":20.9},{"place":11,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":20.6},{"place":12,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":20},{"place":13,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":20},{"place":14,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":19.1},{"place":15,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":18},{"place":16,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":17.7},{"place":17,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":16.9},{"place":18,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":16.9},{"place":19,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":16.3},{"place":20,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":16.29},{"place":21,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":15.4},{"place":22,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":14.3},{"place":23,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":14},{"place":24,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":13.4},{"place":25,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":12.9},{"place":26,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":12.9},{"place":27,"model":"gpt-5-high-code-web","company":"openai","family":"GPT","version":"GPT-5","score":12.6},{"place":28,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":12.6},{"place":29,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":12.6},{"place":30,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":11.6},{"place":31,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":11.6},{"place":32,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":11.4},{"place":33,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":10.86},{"place":34,"model":"gpt-5-high-code","company":"openai","family":"GPT","version":"GPT-5","score":10.6},{"place":35,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":10.6},{"place":36,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":9.1},{"place":37,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":9.1},{"place":38,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":9.1},{"place":39,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":8.6},{"place":40,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":8.6},{"place":41,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":8.3},{"place":42,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":8},{"place":43,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":7.1},{"place":44,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":6.6},{"place":45,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":6},{"place":46,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":5.7},{"place":47,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":5.4},{"place":48,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":5.4},{"place":49,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":4.9},{"place":50,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":4.9},{"place":51,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":4.6},{"place":52,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":4.6},{"place":53,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.3},{"place":54,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":4.3},{"place":55,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":4.3},{"place":56,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":3.7},{"place":57,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":3.7},{"place":58,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":3.7},{"place":59,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.1},{"place":60,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.1},{"place":61,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":2.9},{"place":62,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":2.9},{"place":63,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":2.9},{"place":64,"model":"k2-horizon-32b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":2.9},{"place":65,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":2.9},{"place":66,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":2.6},{"place":67,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":2.6},{"place":68,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.4},{"place":69,"model":"k2-horizon-mova-36b-a4b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":2.1},{"place":70,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":2},{"place":71,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":2},{"place":72,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":1.7},{"place":73,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1.7},{"place":74,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":1.4},{"place":75,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":1.4},{"place":76,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1.4},{"place":77,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1.1},{"place":78,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1.1},{"place":79,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1.1},{"place":80,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1.1},{"place":81,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1.1},{"place":82,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1.1},{"place":83,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":0.9},{"place":84,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":0.6},{"place":85,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":0.6},{"place":86,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":0.3},{"place":87,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":0.3},{"place":88,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":0.3},{"place":89,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":0.3},{"place":90,"model":"g9v3-39a5b","company":"ai9stars","family":"G9","version":"G9v3","score":0.3},{"place":91,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":92,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":0},{"place":93,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0},{"place":94,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":0},{"place":95,"model":"nova-pro","company":"amazon","family":"Nova","version":"Nova","score":0},{"place":96,"model":"nova-lite","company":"amazon","family":"Nova","version":"Nova","score":0},{"place":97,"model":"kat-coder-pro-v1","company":"kuaishou","family":"KAT","version":"KAT-Coder Pro v1","score":0},{"place":98,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":0},{"place":99,"model":"qwen3-235b-a22b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":100,"model":"midm-k-2.5-pro","company":"kt","family":"Mi:dm","version":"Mi:dm K 2.5","score":0},{"place":101,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":0},{"place":102,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":0}]},{"id":"crosstabbench-relation-f1","name":"CrossTabBench Relation F1","topic":"Cross-page tables","description":"CrossTabBench: F1 for detecting cross-page table continuation relations.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OvisOCR3","top_percent":97.07,"top_model_id":"ovisocr3","top_generation":"OvisOCR3","top_model_base":"OvisOCR3","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":97.07},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.47},{"place":3,"model":"mineru2.5-pro","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":59.14},{"place":4,"model":"mineru2.5-pro-popo","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":54.76},{"place":5,"model":"logics-parsing-v3","company":"alibaba","family":"Logics-Parsing","version":"Logics-Parsing-V3","score":44.55},{"place":6,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":42.61}]},{"id":"crosstabbench-teds","name":"CrossTabBench Reconstruction TEDS","topic":"Cross-page tables","description":"CrossTabBench: TEDS of reconstructed cross-page tables.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":91.71,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.71},{"place":2,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":89.66},{"place":3,"model":"mineru2.5-pro","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":41.02},{"place":4,"model":"mineru2.5-pro-popo","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":36.42},{"place":5,"model":"logics-parsing-v3","company":"alibaba","family":"Logics-Parsing","version":"Logics-Parsing-V3","score":26.1},{"place":6,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":24.24}]},{"id":"crossvid","name":"CrossVid","topic":"Multi-video reasoning","description":"Benchmark for cross-video (multi-video) understanding and reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":65,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":65},{"place":2,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.7},{"place":3,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":63.2},{"place":4,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":61},{"place":5,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":58.6},{"place":6,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":58.6},{"place":7,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":57.7},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":53},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":48.8},{"place":10,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":48.7}]},{"id":"crpe","name":"CRPE","topic":"Relation hallucination","description":"Circular-based Relation Probing Evaluation (relation split) for object-relation hallucination.","url":"https://github.com/OpenGVLab/all-seeing","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2402.19474","metric":"percent","stars":"","top_model":"InternVL2.5-26B","top_percent":79.1,"top_model_id":"internvl2.5-26b","top_generation":"InternVL 2.5","top_model_base":"InternVL2.5 26B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":79.1},{"place":2,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":78.8},{"place":3,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":78.4},{"place":4,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":78.3},{"place":5,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":77.6},{"place":6,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":77.6},{"place":7,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":76.6},{"place":8,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":75.8},{"place":9,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":75.6},{"place":10,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":75.5},{"place":11,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":75.4},{"place":12,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":75.2},{"place":13,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":74.4},{"place":14,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":71.1},{"place":15,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":70.2},{"place":16,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":66.3},{"place":17,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":60.9},{"place":18,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":57.5}]},{"id":"crux-i","name":"CRUX-I","topic":"Code reasoning","description":"Code Reasoning and Understanding eXam – Interactive.","url":"","leaderboard":"https://crux-eval.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro Preview","top_percent":98.8,"top_model_id":"gemini-3-pro-preview","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro Preview","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":132,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":98.8},{"place":2,"model":"iquest-coder-v1-40b-loop-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":98.5},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.4},{"place":4,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":97.9},{"place":5,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":96.5},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":96.2},{"place":7,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":93.5},{"place":8,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":92.2},{"place":9,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":91.6},{"place":10,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":91.1},{"place":11,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":87.1},{"place":12,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":86.8},{"place":13,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":86.5},{"place":14,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":84.4},{"place":15,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":82.1},{"place":16,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":78.8},{"place":17,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":78.6},{"place":18,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":77.4},{"place":19,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":76.9},{"place":20,"model":"gpt-4-turbo-2024-04-09-cot","company":"openai","family":"GPT","version":"GPT-4","score":75.7},{"place":21,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":75.7},{"place":22,"model":"gpt-4o-cot","company":"openai","family":"GPT","version":"GPT-4o","score":75.6},{"place":23,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.6},{"place":24,"model":"gpt-4-0613-cot","company":"openai","family":"GPT","version":"GPT-3","score":75.5},{"place":25,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":75.5},{"place":26,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":75.5},{"place":27,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.2},{"place":28,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":74},{"place":29,"model":"claude-opus-4-cot","company":"anthropic","family":"Claude","version":"Claude 4","score":73.4},{"place":30,"model":"claude-3-opus-cot","company":"anthropic","family":"Claude","version":"Claude 3","score":73.4},{"place":31,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":73.4},{"place":32,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":71.4},{"place":33,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":71.19},{"place":34,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":70.8},{"place":35,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":70},{"place":36,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":69.8},{"place":37,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.5},{"place":38,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":68.51},{"place":39,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":68.5},{"place":40,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":68.01},{"place":41,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":67.79},{"place":42,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":67.5},{"place":43,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":67.5},{"place":44,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":67.3},{"place":45,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":67},{"place":46,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.9},{"place":47,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.8},{"place":48,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":65.6},{"place":49,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":65.1},{"place":50,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":64.2},{"place":51,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":64.2},{"place":52,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":63.9},{"place":53,"model":"semcoder-s-6.7b-cot","company":"semcoder","family":"SemCoder","version":"SemCoder","score":63.1},{"place":54,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":62.7},{"place":55,"model":"semcoder-6.7b-cot","company":"semcoder","family":"SemCoder","version":"SemCoder","score":62.5},{"place":56,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":62.5},{"place":57,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":62.1},{"place":58,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":62},{"place":59,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":62},{"place":60,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":61.5},{"place":61,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":61.3},{"place":62,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":61.1},{"place":63,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":61},{"place":64,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":60.6},{"place":65,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":59.5},{"place":66,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":59.4},{"place":67,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.1},{"place":68,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":58.5},{"place":69,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":57.1},{"place":70,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":56.5},{"place":71,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":56.5},{"place":72,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":53.4},{"place":73,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":53.2},{"place":74,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":53},{"place":75,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":52.8},{"place":76,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":52.5},{"place":77,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":52.4},{"place":78,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":51.4},{"place":79,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":50.6},{"place":80,"model":"gpt-3.5-turbo-0613-cot","company":"openai","family":"GPT","version":"GPT-3.5","score":50.3},{"place":81,"model":"codellama-34b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":50.1},{"place":82,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":49.4},{"place":83,"model":"codetulu-2-34b","company":"codetulu","family":"CodeTulu","version":"CodeTulu","score":49.3},{"place":84,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":49.1},{"place":85,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":49},{"place":86,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":48.5},{"place":87,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":48.1},{"place":88,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":48},{"place":89,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":47.5},{"place":90,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":47.5},{"place":91,"model":"codellama-13b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":47.4},{"place":92,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":47.3},{"place":93,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":47.2},{"place":94,"model":"phind-base","company":"phind","family":"Phind","version":"Phind","score":47.2},{"place":95,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":47.2},{"place":96,"model":"deepseek-base-33b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":46.5},{"place":97,"model":"deepseek-instruct-33b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":46.5},{"place":98,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":46.5},{"place":99,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":46.1},{"place":100,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":45.9},{"place":101,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":45.5},{"place":102,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.4},{"place":103,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":44.8},{"place":104,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":44.3},{"place":105,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":44},{"place":106,"model":"codellama-python-34b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":43.9},{"place":107,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":43.8},{"place":108,"model":"wizard-34b","company":"wizardlm","family":"WizardLM","version":"WizardLM","score":42.7},{"place":109,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":42.6},{"place":110,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":42.5},{"place":111,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":42.5},{"place":112,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":42.5},{"place":113,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":42.1},{"place":114,"model":"deepseek-base-6.7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":41.9},{"place":115,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":41.7},{"place":116,"model":"codellama-7b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":40.4},{"place":117,"model":"codellama-python-13b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":39.7},{"place":118,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":39.5},{"place":119,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":39.3},{"place":120,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39},{"place":121,"model":"deepseek-instruct-6.7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":37.4},{"place":122,"model":"codellama-python-7b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":37.3},{"place":123,"model":"wizardlm-13b","company":"wizardlm","family":"WizardLM","version":"WizardLM-13B","score":36.5},{"place":124,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":36.1},{"place":125,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":35.9},{"place":126,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":35.2},{"place":127,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":35},{"place":128,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":34.6},{"place":129,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":33.9},{"place":130,"model":"stablecode-3b","company":"stability","family":"StableCode","version":"StableCode","score":33.5},{"place":131,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":33},{"place":132,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":32.7},{"place":133,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":32.1},{"place":134,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":31.6},{"place":135,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":31.3},{"place":136,"model":"starcoderbase-7b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":29.7},{"place":137,"model":"deepseek-base-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":27.8},{"place":138,"model":"deepseek-instruct-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":27.2},{"place":139,"model":"phi-1.5","company":"microsoft","family":"Phi","version":"Phi","score":23.2},{"place":140,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":19.9},{"place":141,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":15.2},{"place":142,"model":"phi-1","company":"microsoft","family":"Phi","version":"Phi","score":13.1},{"place":143,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":12.9}]},{"id":"crux-o","name":"CRUX-O","topic":"Code reasoning","description":"Code Reasoning and Understanding eXam – Offline.","url":"","leaderboard":"https://crux-eval.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"IQuest-Coder-V1-40B-Loop-Thinking","top_percent":99.4,"top_model_id":"iquest-coder-v1-40b-loop-thinking","top_generation":"IQuest Coder V1","top_model_base":"IQuest Coder V1 40B","top_model_family":"IQuest Coder","top_company":"iquest","top_open_source":1,"lower_is_better":false,"bench_models":166,"total_models":3854,"placements":[{"place":1,"model":"iquest-coder-v1-40b-loop-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":99.4},{"place":2,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":99.1},{"place":3,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":98.9},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98},{"place":5,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":97.6},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":96.2},{"place":7,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":96.2},{"place":8,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":94.2},{"place":9,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":90.4},{"place":10,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.5},{"place":11,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.5},{"place":12,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":89.2},{"place":13,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":88.7},{"place":14,"model":"gpt-4-0613-cot","company":"openai","family":"GPT","version":"GPT-3","score":88.2},{"place":15,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":87.5},{"place":16,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":87.2},{"place":17,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":87},{"place":18,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.75},{"place":19,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":86.2},{"place":20,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":85.5},{"place":21,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":85.25},{"place":22,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":85.12},{"place":23,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84},{"place":24,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":83.5},{"place":25,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.4},{"place":26,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":82.75},{"place":27,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":82},{"place":28,"model":"gpt-4-turbo-2024-04-09-cot","company":"openai","family":"GPT","version":"GPT-4","score":82},{"place":29,"model":"claude-opus-4-cot","company":"anthropic","family":"Claude","version":"Claude 4","score":82},{"place":30,"model":"claude-3-opus-cot","company":"anthropic","family":"Claude","version":"Claude 3","score":82},{"place":31,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":82},{"place":32,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":82},{"place":33,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81.8},{"place":34,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":81.4},{"place":35,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":81.2},{"place":36,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":81.1},{"place":37,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":80.5},{"place":38,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.5},{"place":39,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.2},{"place":40,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.1},{"place":41,"model":"semcoder-6.7b-cot","company":"semcoder","family":"SemCoder","version":"SemCoder","score":79.1},{"place":42,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":79.1},{"place":43,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":78.4},{"place":44,"model":"semcoder-s-6.7b-cot","company":"semcoder","family":"SemCoder","version":"SemCoder","score":78.3},{"place":45,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":77.5},{"place":46,"model":"gpt-4-0613-cot","company":"openai","family":"GPT","version":"GPT-3","score":77.1},{"place":47,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":77.1},{"place":48,"model":"gpt-3.5-turbo-0613-cot","company":"openai","family":"GPT","version":"GPT-3.5","score":76.7},{"place":49,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":76.4},{"place":50,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":76.12},{"place":51,"model":"gpt-4o-cot","company":"openai","family":"GPT","version":"GPT-4o","score":76},{"place":52,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":75.1},{"place":53,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":74.9},{"place":54,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":74.06},{"place":55,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":73.75},{"place":56,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":73},{"place":57,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.5},{"place":58,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":71.62},{"place":59,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":71.1},{"place":60,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":71},{"place":61,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":70.62},{"place":62,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":70},{"place":63,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":69.8},{"place":64,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":69.8},{"place":65,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.62},{"place":66,"model":"codellama-34b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":69.4},{"place":67,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":69.4},{"place":68,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":68.7},{"place":69,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.6},{"place":70,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":68.38},{"place":71,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":67.75},{"place":72,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":67.7},{"place":73,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":67.4},{"place":74,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.2},{"place":75,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":67},{"place":76,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.6},{"place":77,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":66.6},{"place":78,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":66.4},{"place":79,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66},{"place":80,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.9},{"place":81,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":65.8},{"place":82,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":65.8},{"place":83,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":65.1},{"place":84,"model":"semcoder-6.7b-cot","company":"semcoder","family":"SemCoder","version":"SemCoder","score":64.4},{"place":85,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":64.3},{"place":86,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":64.2},{"place":87,"model":"semcoder-s-6.7b-cot","company":"semcoder","family":"SemCoder","version":"SemCoder","score":64.1},{"place":88,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":63.6},{"place":89,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":63.6},{"place":90,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":63.5},{"place":91,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":63.1},{"place":92,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":63},{"place":93,"model":"deepseek-instruct-33b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":61.8},{"place":94,"model":"codellama-13b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":61.8},{"place":95,"model":"deepseek-base-33b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":61.6},{"place":96,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":60.7},{"place":97,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":60.6},{"place":98,"model":"stable-diffcoder-8b-base","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":60},{"place":99,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":59.9},{"place":100,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.9},{"place":101,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":59.5},{"place":102,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":59.3},{"place":103,"model":"gpt-3.5-turbo-0613-cot","company":"openai","family":"GPT","version":"GPT-3.5","score":59},{"place":104,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":59},{"place":105,"model":"codetulu-2-34b","company":"codetulu","family":"CodeTulu","version":"CodeTulu","score":58.9},{"place":106,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":57.8},{"place":107,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":57.5},{"place":108,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":56.5},{"place":109,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":56.2},{"place":110,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":56},{"place":111,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":56},{"place":112,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":55.9},{"place":113,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":55.75},{"place":114,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":55.6},{"place":115,"model":"codellama-7b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":55.4},{"place":116,"model":"deepseek-base-6.7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":54.8},{"place":117,"model":"seed-coder-8b-base","company":"bytedance","family":"Seed","version":"Seed Coder","score":54.8},{"place":118,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":54.3},{"place":119,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":54},{"place":120,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":53.9},{"place":121,"model":"wizard-34b","company":"wizardlm","family":"WizardLM","version":"WizardLM","score":53.8},{"place":122,"model":"codellama-python-34b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":52.9},{"place":123,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":52.9},{"place":124,"model":"deepseek-instruct-6.7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":52.8},{"place":125,"model":"phind-base","company":"phind","family":"Phind","version":"Phind","score":52.8},{"place":126,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":52.8},{"place":127,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":52.8},{"place":128,"model":"codellama-python-13b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":52.5},{"place":129,"model":"wizardlm-13b","company":"wizardlm","family":"WizardLM","version":"WizardLM-13B","score":52.4},{"place":130,"model":"yi-coder-9b","company":"01ai","family":"Yi","version":"Yi-Coder","score":52.3},{"place":131,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":52},{"place":132,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":51.8},{"place":133,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":51.3},{"place":134,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":50.9},{"place":135,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":50.9},{"place":136,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":50.6},{"place":137,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":50.25},{"place":138,"model":"deepseek-instruct-33b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":49.9},{"place":139,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":49.9},{"place":140,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":49.8},{"place":141,"model":"deepseek-coder-33b","company":"deepseek","family":"DeepSeek Coder","version":"DeepSeek Coder","score":49.5},{"place":142,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":49.4},{"place":143,"model":"codellama-python-7b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":48.8},{"place":144,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":48.8},{"place":145,"model":"deepseek-base-33b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":48.6},{"place":146,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":48.6},{"place":147,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":48.6},{"place":148,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":48.4},{"place":149,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":48.4},{"place":150,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":47.63},{"place":151,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":47.6},{"place":152,"model":"codellama-70b","company":"meta","family":"CodeLlama","version":"CodeLlama","score":47.3},{"place":153,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":47.1},{"place":154,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":47.1},{"place":155,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":47.1},{"place":156,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":47.1},{"place":157,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":46.9},{"place":158,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":46.6},{"place":159,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":46.6},{"place":160,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":46.1},{"place":161,"model":"codetulu-2-34b","company":"codetulu","family":"CodeTulu","version":"CodeTulu","score":45.8},{"place":162,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":45.5},{"place":163,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":45.1},{"place":164,"model":"starcoderbase-7b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":44.9},{"place":165,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":44.4},{"place":166,"model":"opencoder-8b-base","company":"map","family":"OpenCoder","version":"OpenCoder","score":43.9},{"place":167,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":43.8},{"place":168,"model":"codellama-34b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":43.6},{"place":169,"model":"deepseek-base-6.7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":43.5},{"place":170,"model":"stablecode-3b","company":"stability","family":"StableCode","version":"StableCode","score":43.5},{"place":171,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":43.5},{"place":172,"model":"wizard-34b","company":"wizardlm","family":"WizardLM","version":"WizardLM","score":43.4},{"place":173,"model":"deepseek-base-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":43.4},{"place":174,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":43},{"place":175,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":42.4},{"place":176,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":42.3},{"place":177,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":41.5},{"place":178,"model":"codellama-python-34b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":41.4},{"place":179,"model":"wizardlm-13b","company":"wizardlm","family":"WizardLM","version":"WizardLM-13B","score":41.3},{"place":180,"model":"deepseek-instruct-6.7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":41.2},{"place":181,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":41.2},{"place":182,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":41.1},{"place":183,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":41},{"place":184,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":41},{"place":185,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":40.75},{"place":186,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":40.5},{"place":187,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":40.1},{"place":188,"model":"deepseek-instruct-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":40},{"place":189,"model":"codellama-python-13b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":39.8},{"place":190,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":39.7},{"place":191,"model":"phind-base","company":"phind","family":"Phind","version":"Phind","score":39.7},{"place":192,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":39.7},{"place":193,"model":"phi-1.5","company":"microsoft","family":"Phi","version":"Phi","score":39.1},{"place":194,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":38.8},{"place":195,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37.5},{"place":196,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":37.1},{"place":197,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":36.2},{"place":198,"model":"codellama-13b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":36},{"place":199,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":36},{"place":200,"model":"codellama-python-7b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":35.9},{"place":201,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":35.1},{"place":202,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":34.6},{"place":203,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":34.3},{"place":204,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":34.2},{"place":205,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":34.2},{"place":206,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":34.2},{"place":207,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":33.5},{"place":208,"model":"starcoderbase-7b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":32.2},{"place":209,"model":"phi-1","company":"microsoft","family":"Phi","version":"Phi","score":32},{"place":210,"model":"yi-coder-1.5b","company":"01ai","family":"Yi","version":"Yi-Coder","score":31.5},{"place":211,"model":"deepseek-base-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":31},{"place":212,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":31},{"place":213,"model":"codellama-7b-cot","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":29.9},{"place":214,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":29.7},{"place":215,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":29.2},{"place":216,"model":"deepseek-instruct-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":28.7},{"place":217,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.7},{"place":218,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.2},{"place":219,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.1},{"place":220,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":27.8},{"place":221,"model":"phi-1.5","company":"microsoft","family":"Phi","version":"Phi","score":27.5},{"place":222,"model":"stablecode-3b","company":"stability","family":"StableCode","version":"StableCode","score":26.7},{"place":223,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":26},{"place":224,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":24.9},{"place":225,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":23},{"place":226,"model":"phi-1","company":"microsoft","family":"Phi","version":"Phi","score":21.7}]},{"id":"cruxeval","name":"CruxEval","topic":"Code reasoning","description":"Mathematical coding challenge set from the CruxEval benchmark.","url":"https://github.com/crux-eval/cruxeval","leaderboard":"","github":"https://github.com/crux-eval/cruxeval","paper":"","metric":"percent","stars":"","top_model":"Qwen3-32B Thinking","top_percent":95,"top_model_id":"qwen3-32b-thinking","top_generation":"Qwen3","top_model_base":"Qwen3 32B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":56,"total_models":3854,"placements":[{"place":1,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":95},{"place":2,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":89.7},{"place":3,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.75},{"place":4,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":85.12},{"place":5,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":82.94},{"place":6,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":82.75},{"place":7,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":78.5},{"place":8,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.45},{"place":9,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":76.5},{"place":10,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":75.9},{"place":11,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.63},{"place":12,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":74.82},{"place":13,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.1},{"place":14,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.5},{"place":15,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":73.07},{"place":16,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.7},{"place":17,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.44},{"place":18,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":71.69},{"place":19,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":70.06},{"place":20,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.63},{"place":21,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":69.53},{"place":22,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":68.32},{"place":23,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.12},{"place":24,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":67.67},{"place":25,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":67.44},{"place":26,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":66.51},{"place":27,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.31},{"place":28,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":63.19},{"place":29,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":61.88},{"place":30,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":59.57},{"place":31,"model":"codestral-mamba","company":"mistral","family":"Codestral","version":"Codestral","score":57.8},{"place":32,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.9},{"place":33,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":56.25},{"place":34,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":55.5},{"place":35,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":55.2},{"place":36,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":55},{"place":37,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":52.32},{"place":38,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":52.13},{"place":39,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":51.3},{"place":40,"model":"codegemma-1.1-7b","company":"google","family":"CodeGemma","version":"CodeGemma","score":50.4},{"place":41,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":50.1},{"place":42,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":49.9},{"place":43,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":47.1},{"place":44,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":44.38},{"place":45,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.26},{"place":46,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":39.57},{"place":47,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.76},{"place":48,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":25.75},{"place":49,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.63},{"place":50,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":21.57},{"place":51,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":18.88},{"place":52,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":17.75},{"place":53,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":15.58},{"place":54,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":14.88},{"place":55,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":12.7},{"place":56,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":0.06}]},{"id":"cruxeval-decision","name":"CRUXEval (decision)","topic":"Code reasoning","description":"CRUXEval output prediction posed as choices among candidate outputs; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/crux-eval/cruxeval","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef-Omni","top_percent":88.8,"top_model_id":"clef-omni","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":88.8},{"place":2,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":88.1},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":86.7},{"place":4,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":86.1},{"place":5,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":86},{"place":6,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":82.5},{"place":7,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":74.7},{"place":8,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":73.7},{"place":9,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":73.2},{"place":10,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":73},{"place":11,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":71.4},{"place":12,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":71},{"place":13,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":67.2},{"place":14,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":64.7},{"place":15,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":64.7},{"place":16,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":64.6},{"place":17,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":62.6},{"place":18,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59},{"place":19,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":56.3},{"place":20,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":53.3},{"place":21,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":51.2},{"place":22,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":51.2},{"place":23,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":50.2},{"place":24,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":45.1},{"place":25,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":43.2},{"place":26,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":41.8},{"place":27,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":40.9},{"place":28,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":40.7},{"place":29,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":40.2},{"place":30,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":40.2},{"place":31,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":38.1},{"place":32,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":37.4},{"place":33,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":33.9},{"place":34,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":33.7},{"place":35,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":33.3},{"place":36,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":33.2},{"place":37,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":32.8},{"place":38,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":31.1}]},{"id":"csimpleqa","name":"CSimpleQA","topic":"QA","description":"Chinese SimpleQA benchmark variant (short factual questions).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ling 2.5 1T","top_percent":78.97,"top_model_id":"ling-2.5-1t","top_generation":"Ling 2.5","top_model_base":"Ling 2.5 1T","top_model_family":"Ling","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":78.97},{"place":2,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":77.6},{"place":3,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":76.83},{"place":4,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":76.8},{"place":5,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":76.53},{"place":6,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":74.58},{"place":7,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":71.97},{"place":8,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":70.9},{"place":9,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":70.9},{"place":10,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":70.57},{"place":11,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":70.1},{"place":12,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":69.73},{"place":13,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":68.72},{"place":14,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":68.49},{"place":15,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":68.37},{"place":16,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":68},{"place":17,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":68},{"place":18,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":67.77},{"place":19,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":64.8},{"place":20,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":64.6},{"place":21,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":64.53},{"place":22,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":63.53},{"place":23,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":63.2},{"place":24,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":61.5},{"place":25,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":60.23},{"place":26,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":59.73},{"place":27,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":59.3},{"place":28,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":58.1},{"place":29,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":54.1},{"place":30,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":53.5},{"place":31,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.3},{"place":32,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":50.4},{"place":33,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":49.43},{"place":34,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":48.5},{"place":35,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.4},{"place":36,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":47.03},{"place":37,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":43.47},{"place":38,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":34.7}]},{"id":"cultcat","name":"CultCat","topic":"Cultural knowledge","description":"Yandex 4-shot benchmark of (Russian) cultural facts.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":86.5,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":86.5},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.7},{"place":3,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":66.3},{"place":4,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.2},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":59.1}]},{"id":"cursorbench-3.0","name":"CursorBench 3.0","topic":"Software engineering","description":"Cursor's coding-agent benchmark on ambiguous multi-file tasks from real Cursor sessions (v3.0, used in the Composer 2 technical report as CursorBench-3).","url":"https://cursor.com/cursorbench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2603.24477","metric":"percent","stars":"","top_model":"GPT-5.4","top_percent":63.9,"top_model_id":"gpt-5.4","top_generation":"GPT-5.4","top_model_base":"GPT-5.4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":63.9},{"place":2,"model":"composer-2","company":"cursor","family":"Composer","version":"Composer 2","score":61.3},{"place":3,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":59.1},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":58.2},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":56.5},{"place":6,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":48.4},{"place":7,"model":"composer-1.5","company":"cursor","family":"Composer","version":"Composer 1.5","score":44.2},{"place":8,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":42.7},{"place":9,"model":"composer-1","company":"cursor","family":"Composer","version":"Composer 1","score":38},{"place":10,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":36}]},{"id":"cursorbench-3.2","name":"CursorBench 3.2","topic":"Software engineering","description":"Cursor's coding-agent benchmark on ambiguous multi-file tasks from real Cursor sessions (v3.2).","url":"https://cursor.com/cursorbench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5.1","top_percent":73.4,"top_model_id":"claude-fable-5.1","top_generation":"Claude 5.1","top_model_base":"Claude Fable 5.1","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":73.4},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.5},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70},{"place":4,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":69.9},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":67.2},{"place":6,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":66.7}]},{"id":"cursorbench-4.0","name":"CursorBench 4.0","topic":"Software engineering","description":"Cursor's coding-agent benchmark on ambiguous multi-file tasks from real Cursor sessions (v4.0).","url":"https://cursor.com/cursorbench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":57.8,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":57.8},{"place":2,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":55.5},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":51.8},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":46.6},{"place":5,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":46.3},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":41.7},{"place":7,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":40.4},{"place":8,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":34.1},{"place":9,"model":"composer-2.5","company":"cursor","family":"Composer","version":"Composer 2.5","score":27.7}]},{"id":"customer-support-qa","name":"Customer Support Q&A","topic":"Customer support QA","description":"Customer support question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":69,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":69},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65.5},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.6},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":63.4},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.4}]},{"id":"cute","name":"CUTE","topic":"English characters","description":"CUTE aggregate capability score.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Bolmo 7B","top_percent":78.6,"top_model_id":"bolmo-7b","top_generation":"Bolmo 7B","top_model_base":"Bolmo 7B","top_model_family":"Bolmo","top_company":"allenai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"bolmo-7b","company":"allenai","family":"Bolmo","version":"Bolmo 7B","score":78.6},{"place":2,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":56.9},{"place":3,"model":"tfree-hat-pretrained-7b-base","company":"alephalpha","family":"TFree","version":"TFree Hat","score":54.2},{"place":4,"model":"blt-7b","company":"meta","family":"BLT","version":"BLT 7B","score":52.3},{"place":5,"model":"evabyte-6.5b","company":"hku","family":"EvaByte","version":"EvaByte 6.5B","score":50.8}]},{"id":"cv-bench","name":"CV-Bench","topic":"Computer vision QA","description":"Diverse CV tasks for VLMs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":92,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":72,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":92},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.07},{"place":3,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":90},{"place":4,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":90},{"place":5,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":89.7},{"place":6,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.68},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":89.57},{"place":8,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":89.4},{"place":9,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":89.3},{"place":10,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":89.2},{"place":11,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":89.18},{"place":12,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":88.8},{"place":13,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":88.6},{"place":14,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":88.3},{"place":15,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":88.1},{"place":16,"model":"cosmos-reason2-32b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":88.01},{"place":17,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":88},{"place":18,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":88},{"place":19,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":87.9},{"place":20,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":87.8},{"place":21,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87.8},{"place":22,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":87.79},{"place":23,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":87.6},{"place":24,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":87.59},{"place":25,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.57},{"place":26,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":87.4},{"place":27,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":87.3},{"place":28,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":87.19},{"place":29,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.19},{"place":30,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":86.9},{"place":31,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":86.9},{"place":32,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.84},{"place":33,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":86.82},{"place":34,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.74},{"place":35,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.72},{"place":36,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86.1},{"place":37,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.9},{"place":38,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":85.9},{"place":39,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.8},{"place":40,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.8},{"place":41,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.7},{"place":42,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":85.65},{"place":43,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":85.6},{"place":44,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.6},{"place":45,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.44},{"place":46,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.37},{"place":47,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.36},{"place":48,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.17},{"place":49,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":85},{"place":50,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":85},{"place":51,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":85},{"place":52,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":84.99},{"place":53,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.95},{"place":54,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":84.9},{"place":55,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":84.9},{"place":56,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.87},{"place":57,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.8},{"place":58,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.6},{"place":59,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":84.31},{"place":60,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":84.3},{"place":61,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":84.22},{"place":62,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":84.15},{"place":63,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":83.8},{"place":64,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":83.6},{"place":65,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":83.49},{"place":66,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":82.3},{"place":67,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":82.1},{"place":68,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":81.8},{"place":69,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":81.31},{"place":70,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":81},{"place":71,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":80.9},{"place":72,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":80.9},{"place":73,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":80.5},{"place":74,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":80.25},{"place":75,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80},{"place":76,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":79.83},{"place":77,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":79.3},{"place":78,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":79.1},{"place":79,"model":"cosmos-reason2-2b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":78.74},{"place":80,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.67},{"place":81,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":77.9},{"place":82,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":76},{"place":83,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":75.4},{"place":84,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":75.4},{"place":85,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":75.34},{"place":86,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":74.6},{"place":87,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":70.4},{"place":88,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":70.3},{"place":89,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.1},{"place":90,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":64.4},{"place":91,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":57.09}]},{"id":"cvtg-2k-clipscore","name":"CVTG-2K CLIPScore","topic":"Text rendering","description":"CVTG-2K CLIPScore for text rendering in image generation.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Seedream 4.5","top_percent":0.8069,"top_model_id":"seedream-4.5","top_generation":"Seedream","top_model_base":"Seedream 4.5","top_model_family":"Seedream","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":0.8069},{"place":2,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":0.8048},{"place":3,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.8017},{"place":4,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":0.7982},{"place":5,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":0.7975},{"place":6,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":0.7969},{"place":7,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":0.7877},{"place":8,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.7819},{"place":9,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":0.7372}]},{"id":"cvtg-2k-ned","name":"CVTG-2K NED","topic":"Text rendering","description":"CVTG-2K normalized edit distance (NED) for text rendering.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"GLM-Image","top_percent":0.9557,"top_model_id":"glm-image","top_generation":"GLM-Image","top_model_base":"GLM-Image","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":0.9557},{"place":2,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":0.9483},{"place":3,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":0.9478},{"place":4,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":0.9367},{"place":5,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.929},{"place":6,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":0.9281},{"place":7,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":0.9224},{"place":8,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.9116},{"place":9,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":0.8754}]},{"id":"cvtg-2k-word-accuracy","name":"CVTG-2K Word Accuracy","topic":"Text rendering","description":"CVTG-2K word accuracy for text rendering in images.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"GLM-Image","top_percent":0.9116,"top_model_id":"glm-image","top_generation":"GLM-Image","top_model_base":"GLM-Image","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":0.9116},{"place":2,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":0.899},{"place":3,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":0.8671},{"place":4,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.8604},{"place":5,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":0.8585},{"place":6,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":0.8569},{"place":7,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":0.8451},{"place":8,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.8288},{"place":9,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":0.7788}]},{"id":"cwe-bench","name":"CWE-Bench","topic":"Cybersecurity","description":"CWE-Bench v1 vulnerability detection benchmark (cwe-bench.com, Collinear AI); pass@1.","url":"https://cwe-bench.com/","leaderboard":"https://cwe-bench.com/","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":68,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":68},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":68},{"place":3,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":68},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":67},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":58},{"place":6,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":57},{"place":7,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":55},{"place":8,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":55},{"place":9,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":53},{"place":10,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":52},{"place":11,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":37}]},{"id":"cxr14","name":"ChestX-ray14","topic":"Medical imaging","description":"NIH ChestX-ray14 classification, macro F1.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedGemma 4B","top_percent":50.1,"top_model_id":"medgemma-4b-it","top_generation":"MedGemma 1","top_model_base":"MedGemma","top_model_family":"MedGemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":50.1},{"place":2,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":48.4},{"place":3,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":45.3},{"place":4,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":32}]},{"id":"cybench","name":"CyBench","topic":"Cybersecurity CTF","description":"Framework with 40 professional-level CTF tasks evaluating LLMs' practical cybersecurity capabilities.","url":"https://cybench.github.io/","leaderboard":"https://cybench.github.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 3 70B","top_percent":5,"top_model_id":"llama-3-70b","top_generation":"Llama 3","top_model_base":"Llama 3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":true,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":5},{"place":2,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":7.5},{"place":3,"model":"mixtral-8x22b-instruct","company":"mistral","family":"Mixtral","version":"Mixtral","score":7.5},{"place":4,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":7.5},{"place":5,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":10},{"place":6,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":10},{"place":7,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":10},{"place":8,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":12.5},{"place":9,"model":"gpt-4.5-preview","company":"openai","family":"GPT","version":"GPT-4.5","score":17.5},{"place":10,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":17.5},{"place":11,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":20},{"place":12,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":22.5},{"place":13,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":30},{"place":14,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":35},{"place":15,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":38},{"place":16,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":39},{"place":17,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":42},{"place":18,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":43},{"place":19,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60},{"place":20,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":65.4},{"place":21,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82},{"place":22,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":93},{"place":23,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":96},{"place":24,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":100}]},{"id":"cybergym","name":"CyberGym","topic":"Cybersecurity tasks","description":"Benchmark for cybersecurity-related coding and reasoning tasks.","url":"","leaderboard":"https://www.cybergym.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"MiMo V2.6 Flash RL","top_percent":95.1,"top_model_id":"mimo-v2.6-flash-rl","top_generation":"MiMo V2.6","top_model_base":"MiMo V2.6 Flash","top_model_family":"MiMo","top_company":"xiaomi","top_open_source":1,"lower_is_better":false,"bench_models":47,"total_models":3854,"placements":[{"place":1,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":95.1},{"place":2,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":94},{"place":3,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":88.1},{"place":4,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":87.9},{"place":5,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":86.8},{"place":6,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":86.5},{"place":7,"model":"gemini-3.8-flash-cyber","company":"google","family":"Gemini","version":"Gemini 3.8","score":86.2},{"place":8,"model":"gpt-5.5-cyber","company":"openai","family":"GPT","version":"GPT-5.5","score":85.6},{"place":9,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":84.5},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":84.5},{"place":11,"model":"iquest-q1","company":"iquest","family":"IQuest","version":"IQuest Q1","score":84.5},{"place":12,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.8},{"place":13,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.8},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.6},{"place":15,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.3},{"place":16,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":83.1},{"place":17,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":83.1},{"place":18,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.1},{"place":19,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":82},{"place":20,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.8},{"place":21,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80},{"place":22,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":80},{"place":23,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":79},{"place":24,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":78.8},{"place":25,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":78.7},{"place":26,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":78.5},{"place":27,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":78.4},{"place":28,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":78.3},{"place":29,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":78.1},{"place":30,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":78},{"place":31,"model":"gemini-3.5-flash-cyber","company":"google","family":"Gemini","version":"Gemini 3.5","score":77.5},{"place":32,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":77.2},{"place":33,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.7},{"place":34,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.3},{"place":35,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.8},{"place":36,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.8},{"place":37,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":73.1},{"place":38,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":70.2},{"place":39,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":68.7},{"place":40,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":67},{"place":41,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66.6},{"place":42,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":66.3},{"place":43,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":59},{"place":44,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":55},{"place":45,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":52.7},{"place":46,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.7},{"place":47,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":51.8},{"place":48,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.6},{"place":49,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":48.3},{"place":50,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":41.3},{"place":51,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":40},{"place":52,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":39.9},{"place":53,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":38.8},{"place":54,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.7},{"place":55,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":34},{"place":56,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":17.3}]},{"id":"cybersecurity-capture-the-flag-challenges","name":"Cybersecurity Capture The Flag Challenges","topic":"Cybersecurity CTF","description":"Capture-the-flag challenge benchmark evaluating cybersecurity problem-solving skills.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":96.7,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":96.7},{"place":2,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":91.8},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":88.1},{"place":4,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":85.2},{"place":5,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":83.7},{"place":6,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":77.6},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":67.7},{"place":8,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":67.4}]},{"id":"cybersecurity-ctf","name":"Cybersecurity CTF","topic":"Cybersecurity CTF","description":"Cybersecurity Capture The Flag challenges benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.3 Codex","top_percent":77.6,"top_model_id":"gpt-5.3-codex","top_generation":"GPT-5.3 Codex","top_model_base":"GPT-5.3 Codex","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":77.6},{"place":2,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":67.7},{"place":3,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":67.4}]},{"id":"d4la","name":"D4LA","topic":"Layout analysis","description":"Diverse and detailed dataset for document layout analysis (12 document types, 27 categories).","url":"https://arxiv.org/abs/2308.14978","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Infinity-Parser2-Pro","top_percent":52.41,"top_model_id":"infinity-parser2-pro","top_generation":"Infinity-Parser2","top_model_base":"Infinity-Parser2 Pro","top_model_family":"Infinity-Parser","top_company":"infly","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":52.41},{"place":2,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":51.62},{"place":3,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":50.21},{"place":4,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":46.05},{"place":5,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":33.03}]},{"id":"da-2k","name":"DA-2K","topic":"Spatial reasoning","description":"2D/3D spatial reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"HY-Embodied-0.5 MoT-2B","top_percent":92.3,"top_model_id":"hy-embodied-0.5-mot-2b","top_generation":"HY-Embodied 0.5","top_model_base":"HY-Embodied 0.5 MoT-2B","top_model_family":"HY-Embodied","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":92.3},{"place":2,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":85.3},{"place":3,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":83.2},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":82.1},{"place":5,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.4},{"place":6,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":79.4},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.6},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.5},{"place":9,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.5},{"place":10,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":72.2},{"place":11,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.5},{"place":12,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":68.2},{"place":13,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":25.8}]},{"id":"daily-omni","name":"Daily-Omni","topic":"Audio-visual QA","description":"Daily-Omni: audio-visual question answering on everyday videos with temporal alignment.","url":"https://arxiv.org/abs/2505.17862","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":84.2,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":84.2},{"place":2,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":83.5},{"place":3,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":80.5},{"place":4,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":80.2},{"place":5,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.3},{"place":6,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":70.7}]},{"id":"deep-planning","name":"Deep Planning","topic":"Planning and reasoning","description":"Benchmark evaluating deep planning and multi-step reasoning capabilities.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nanbeige4.3-33B","top_percent":63.3,"top_model_id":"nanbeige4.3-33b","top_generation":"Nanbeige4.3","top_model_base":"Nanbeige4.3 33B","top_model_family":"Nanbeige","top_company":"boss","top_open_source":1,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":63.3},{"place":2,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":62.3},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":58.9},{"place":4,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":49.2},{"place":5,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":44.6},{"place":6,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":44.6},{"place":7,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.6},{"place":8,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":42.3},{"place":9,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":41.5},{"place":10,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":40.9},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.6},{"place":12,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.3},{"place":13,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":34.1},{"place":14,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33.9},{"place":15,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":28.7},{"place":16,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":25.9},{"place":17,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.1},{"place":18,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":24},{"place":19,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":23.3},{"place":20,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.8},{"place":21,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.6},{"place":22,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":21.6},{"place":23,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":21.4},{"place":24,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":19.4},{"place":25,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18},{"place":26,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":17.9},{"place":27,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":17.6},{"place":28,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":17.1},{"place":29,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":16.2},{"place":30,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":14.6},{"place":31,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":14.5},{"place":32,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":14.4},{"place":33,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":4.9},{"place":34,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":0.4}]},{"id":"deepcodebench","name":"DeepCodeBench","topic":"Code QA","description":"Qodo's question-answering benchmark over real-world code repositories, requiring retrieval and reasoning across large codebases.","url":"https://huggingface.co/datasets/Qodo/deep_code_bench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"openPangu-2.0-Flash Thinking","top_percent":76.5,"top_model_id":"openpangu-2.0-flash-thinking","top_generation":"openPangu-2.0","top_model_base":"openPangu-2.0-Flash","top_model_family":"openPangu","top_company":"huawei","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":76.5},{"place":2,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":74.2},{"place":3,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":72.6},{"place":4,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":70.9}]},{"id":"deepconsult","name":"DeepConsult","topic":"Agentic writing","description":"Agentic consulting and writing benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":57.2,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":57.2},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":48},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":41},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.3},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.8}]},{"id":"deepmind-math","name":"DeepMind Mathematics","topic":"Math reasoning","description":"Synthetic math problem sets from DeepMind covering arithmetic, algebra, calculus, and more.","url":"https://github.com/deepmind/mathematics_dataset","leaderboard":"","github":"https://github.com/deepmind/mathematics_dataset","paper":"https://arxiv.org/abs/1904.01557","metric":"percent","stars":"","top_model":"Granite-4.1-30B","top_percent":81.93,"top_model_id":"granite-4.1-30b","top_generation":"Granite 4.1","top_model_base":"Granite 4.1 30B","top_model_family":"Granite","top_company":"IBM","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":81.93},{"place":2,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":80.07},{"place":3,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":64.64},{"place":4,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":59.33},{"place":5,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":47.7},{"place":6,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":46.44},{"place":7,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":46},{"place":8,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":44.56},{"place":9,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.8},{"place":10,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":32.2},{"place":11,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":25.4},{"place":12,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":24.1},{"place":13,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":23.7},{"place":14,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":23.4},{"place":15,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":23},{"place":16,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":20.2},{"place":17,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":17.1},{"place":18,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":16.3}]},{"id":"deepresearch-bench-ii","name":"DeepResearch Bench II","topic":"Deep research reports","description":"Second-generation DeepResearch Bench evaluating long-form deep-research reports with fine-grained rubrics.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Xing4.0-29B-A4B","top_percent":60.8,"top_model_id":"xing4.0-29b-a4b","top_generation":"Xing4.0","top_model_base":"Xing4.0 29B A4B","top_model_family":"Xing","top_company":"teleai","top_open_source":1,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"xing4.0-29b-a4b","company":"teleai","family":"Xing","version":"Xing4.0","score":60.8},{"place":2,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":59.7},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.1},{"place":4,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":52.7},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":51.3},{"place":6,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":51.2},{"place":7,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":51.1},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":50.7},{"place":9,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":49.2},{"place":10,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46.6},{"place":11,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.3},{"place":12,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":33.4},{"place":13,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.3},{"place":14,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26}]},{"id":"deepresearchbench","name":"DeepResearchBench","topic":"Agentic research writing","description":"Research-oriented agentic writing and planning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AgentCPM-Report","top_percent":50.11,"top_model_id":"agentcpm-report","top_generation":"AgentCPM","top_model_base":"AgentCPM-Report 8B","top_model_family":"AgentCPM","top_company":"openbmb","top_open_source":1,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"agentcpm-report","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":50.11},{"place":2,"model":"gemini-deepresearch","company":"google","family":"Gemini","version":"Gemini DeepResearch","score":49.71},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":49.6},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":48.7},{"place":5,"model":"openai-deepresearch","company":"openai","family":"DeepResearch","version":"DeepResearch","score":46.45},{"place":6,"model":"claude-research","company":"anthropic","family":"Claude","version":"Claude Research","score":45},{"place":7,"model":"doubao-deep-research","company":"bytedance","family":"Doubao","version":"Doubao","score":44.34},{"place":8,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":43.5},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":40},{"place":10,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":39.9},{"place":11,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":38.15},{"place":12,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":36.47},{"place":13,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":36.3},{"place":14,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":34.19},{"place":15,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":33.4},{"place":16,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":32.73}]},{"id":"deepsearchqa","name":"DeepSearchQA","topic":"Deep web search QA","description":"Multi-step web search and question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Atria-Dawn","top_percent":96.5,"top_model_id":"atria-dawn","top_generation":"Atria Dawn","top_model_base":"Atria Dawn","top_model_family":"Atria","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":75,"total_models":3854,"placements":[{"place":1,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":96.5},{"place":2,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":96},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":95.9},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95.5},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":95},{"place":6,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":94.7},{"place":7,"model":"apodex-h1","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":94.4},{"place":8,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":94.2},{"place":9,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":94.2},{"place":10,"model":"arex-2","company":"baai","family":"AREX","version":"AREX-2","score":93.8},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":93.3},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":93.2},{"place":13,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":93.1},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":93.1},{"place":15,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.1},{"place":16,"model":"iris-pro","company":"allspark","family":"Iris","version":"Iris","score":92.9},{"place":17,"model":"xyz-aquila-pro","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":92.5},{"place":18,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":92.5},{"place":19,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":92.3},{"place":20,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":92.1},{"place":21,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":91.8},{"place":22,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.3},{"place":23,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":91},{"place":24,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":90.8},{"place":25,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.6},{"place":26,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.4},{"place":27,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.4},{"place":28,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":90.4},{"place":29,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.4},{"place":30,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":90.3},{"place":31,"model":"arex-base","company":"baai","family":"AREX","version":"AREX","score":89.9},{"place":32,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":89.6},{"place":33,"model":"xyz-aquila-mini","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":89.5},{"place":34,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":89.1},{"place":35,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":89.1},{"place":36,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.7},{"place":37,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":88.5},{"place":38,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":88.4},{"place":39,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":87.8},{"place":40,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.7},{"place":41,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.7},{"place":42,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":87.2},{"place":43,"model":"iris-mini","company":"allspark","family":"Iris","version":"Iris","score":86.9},{"place":44,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":85.9},{"place":45,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":85.3},{"place":46,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":84.9},{"place":47,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":84.6},{"place":48,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":84.3},{"place":49,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":83},{"place":50,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":82.8},{"place":51,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":82.3},{"place":52,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":82.2},{"place":53,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.1},{"place":54,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":81.7},{"place":55,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":81.3},{"place":56,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":80.6},{"place":57,"model":"mirothinker-h1","company":"miromind","family":"MiroThinker","version":"MiroThinker H1","score":80.6},{"place":58,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80},{"place":59,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79.8},{"place":60,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":79},{"place":61,"model":"arex-turbo","company":"baai","family":"AREX","version":"AREX","score":78.5},{"place":62,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77.1},{"place":63,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77.1},{"place":64,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.9},{"place":65,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":76.8},{"place":66,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.1},{"place":67,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":74.8},{"place":68,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":74.6},{"place":69,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.7},{"place":70,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":73.6},{"place":71,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":73.4},{"place":72,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":72.1},{"place":73,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":71.33},{"place":74,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":71.3},{"place":75,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.3},{"place":76,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":71.1},{"place":77,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":69.7},{"place":78,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.5},{"place":79,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":67.9},{"place":80,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":65.22},{"place":81,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":63.7},{"place":82,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":63.2},{"place":83,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":62.8},{"place":84,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.7},{"place":85,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60.9},{"place":86,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60.9},{"place":87,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":60.2},{"place":88,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":60},{"place":89,"model":"toolmind-web-3b","company":"boss","family":"Nanbeige","version":"ToolMind-Web","score":45.8},{"place":90,"model":"dr-venus-4b-rl","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":39.6},{"place":91,"model":"dr-venus-4b-sft","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":37.7},{"place":92,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":36.7},{"place":93,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":32.8},{"place":94,"model":"marco-deepresearch-8b","company":"alibaba","family":"Marco","version":"Marco DeepResearch","score":29.9},{"place":95,"model":"webexplorer-8b","company":"hkust","family":"WebExplorer","version":"WebExplorer","score":17.8}]},{"id":"deepsearchqa-f1","name":"DeepSearchQA (F1)","topic":"Deep web search QA","description":"DeepSearchQA multi-step web search benchmark, F1-score metric (the existing deepsearchqa entry is used for the accuracy metric).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":95,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":95},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":94.2},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":94},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":93.1},{"place":5,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":92.8},{"place":6,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":92.5},{"place":7,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":91.7},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.3},{"place":9,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":91.2},{"place":10,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.6},{"place":11,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.2},{"place":12,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":89},{"place":13,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":86.7},{"place":14,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.7},{"place":15,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":85.5},{"place":16,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82},{"place":17,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":81.9},{"place":18,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":80.5},{"place":19,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":80.1},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":79.3},{"place":21,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":79},{"place":22,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":78.6},{"place":23,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":77.3},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.9},{"place":25,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":69}]},{"id":"deepshop","name":"DeepShop","topic":"Web agents","description":"Online shopping web-agent benchmark with complex, deep product-search queries.","url":"https://arxiv.org/abs/2506.02839","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2506.02839","metric":"percent","stars":"","top_model":"MolmoWeb-8B","top_percent":42.3,"top_model_id":"molmoweb-8b","top_generation":"MolmoWeb","top_model_base":"MolmoWeb 8B","top_model_family":"Molmo","top_company":"allenai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"molmoweb-8b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":42.3},{"place":2,"model":"molmoweb-4b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":35.6},{"place":3,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":32},{"place":4,"model":"fara-7b","company":"microsoft","family":"Fara","version":"Fara","score":26.2},{"place":5,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":11.6}]},{"id":"deepswe","name":"DeepSWE","topic":"Software engineering","description":"113 long-horizon software engineering tasks written from scratch to avoid contamination (v1.1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":74.2,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":48,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":74.2},{"place":2,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":74.2},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":72.67},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":72.6},{"place":5,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":71},{"place":6,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":70.6},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":70.6},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":70},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68.8},{"place":10,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":67.5},{"place":11,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":67.4},{"place":12,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":67.3},{"place":13,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":67.2},{"place":14,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67},{"place":15,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":66.9},{"place":16,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":65.5},{"place":17,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":64.3},{"place":18,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":63.4},{"place":19,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":59.7},{"place":20,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59},{"place":21,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":56},{"place":22,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":55.57},{"place":23,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.9},{"place":24,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.4},{"place":25,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":54},{"place":26,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.8},{"place":27,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53},{"place":28,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":49.3},{"place":29,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":46.2},{"place":30,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":42.5},{"place":31,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":42.3},{"place":32,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":32.7},{"place":33,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":28},{"place":34,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":27.4},{"place":35,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":24.7},{"place":36,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":24.65},{"place":37,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":23},{"place":38,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":22},{"place":39,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":21.2},{"place":40,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":19.5},{"place":41,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":18.2},{"place":42,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":18},{"place":43,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":18},{"place":44,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":10},{"place":45,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":8},{"place":46,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":7.1},{"place":47,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":4.4},{"place":48,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3},{"place":49,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":2.7},{"place":50,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1},{"place":51,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":0.9},{"place":52,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.4},{"place":53,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":0},{"place":54,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":0}]},{"id":"deepswe-v1.0","name":"DeepSWE 1.0","topic":"Software engineering","description":"Datacurve DeepSWE v1.0 long-horizon software-engineering tasks, run by Artificial Analysis with each provider's own harness (pass@1).","url":"https://deepswe.datacurve.ai/","leaderboard":"https://deepswe.datacurve.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":70.05,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":70.05},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":66.1},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":64.31},{"place":4,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":62},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":58.19},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":55.75},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":55.53},{"place":8,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":54.2},{"place":9,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":51.62},{"place":10,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":46.31},{"place":11,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":41.52},{"place":12,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":40.12},{"place":13,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":37.76},{"place":14,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":31.77},{"place":15,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":28.32},{"place":16,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":27.6},{"place":17,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":24.34},{"place":18,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":23.89},{"place":19,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":20.44},{"place":20,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":19.47},{"place":21,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":17.7},{"place":22,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":17.52},{"place":23,"model":"grok-build-0.1","company":"xai","family":"Grok","version":"Grok Build","score":13.08},{"place":24,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":9.73},{"place":25,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":7.52},{"place":26,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":5.14},{"place":27,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":2.65},{"place":28,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":0.22},{"place":29,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":0.22}]},{"id":"deepswe-v1.1","name":"DeepSWE v1.1","topic":"Software engineering","description":"Original long-horizon software-engineering tasks in real codebases (Datacurve).","url":"https://deepswe.datacurve.ai/","leaderboard":"https://deepswe.datacurve.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Wonder Full","top_percent":79,"top_model_id":"muse-wonder-full","top_generation":"Muse Wonder","top_model_base":"Muse Wonder Full","top_model_family":"Muse","top_company":"meta","top_open_source":0,"lower_is_better":false,"bench_models":80,"total_models":3854,"placements":[{"place":1,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":79},{"place":2,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":78.8},{"place":3,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":77.9},{"place":4,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":77},{"place":5,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":75.4},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":75.2},{"place":7,"model":"ember-1","company":"fireworks","family":"Ember","version":"Ember-1","score":75.2},{"place":8,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":74.2},{"place":9,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":74.2},{"place":10,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":74.12},{"place":11,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":74.1},{"place":12,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":74},{"place":13,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":73.83},{"place":14,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":73.8},{"place":15,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":73.7},{"place":16,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":73.7},{"place":17,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":73.7},{"place":18,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":73.65},{"place":19,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":73.6},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73},{"place":21,"model":"swe-2","company":"cognition","family":"SWE","version":"SWE-2","score":73},{"place":22,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":72.7},{"place":23,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":72.67},{"place":24,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":71.9},{"place":25,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":71},{"place":26,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":70},{"place":27,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70},{"place":28,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":70},{"place":29,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":70},{"place":30,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":69.91},{"place":31,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":69.9},{"place":32,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":69.7},{"place":33,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":69.62},{"place":34,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":69.6},{"place":35,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":69.3},{"place":36,"model":"qwen3.8-max-0902","company":"qwen","family":"Qwen","version":"Qwen3.8","score":69.3},{"place":37,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":69},{"place":38,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":69},{"place":39,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":68.96},{"place":40,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":68.8},{"place":41,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":68.51},{"place":42,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":68.5},{"place":43,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":68},{"place":44,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":67.9},{"place":45,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":67.8},{"place":46,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":67.7},{"place":47,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":67.5},{"place":48,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":67.5},{"place":49,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":67.48},{"place":50,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":67.4},{"place":51,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":67.2},{"place":52,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":67.19},{"place":53,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":67.04},{"place":54,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":67},{"place":55,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":67},{"place":56,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":67},{"place":57,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":66.9},{"place":58,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":66.6},{"place":59,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":66.4},{"place":60,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":65.9},{"place":61,"model":"nex-n2.5-max","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":65.6},{"place":62,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":65.49},{"place":63,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":65.3},{"place":64,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":65.2},{"place":65,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":65},{"place":66,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":64.8},{"place":67,"model":"iquest-q1","company":"iquest","family":"IQuest","version":"IQuest Q1","score":64.6},{"place":68,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":64.6},{"place":69,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":64.3},{"place":70,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":63.4},{"place":71,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":63.39},{"place":72,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":63},{"place":73,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":63},{"place":74,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.83},{"place":75,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.8},{"place":76,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":62.8},{"place":77,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.7},{"place":78,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.7},{"place":79,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":62.2},{"place":80,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":62},{"place":81,"model":"tinfield-1","company":"badtheorylabs","family":"Tinfield","version":"Tinfield 1","score":62},{"place":82,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":61},{"place":83,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":60},{"place":84,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.3},{"place":85,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":59.3},{"place":86,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59},{"place":87,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":58.97},{"place":88,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":58.7},{"place":89,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":58},{"place":90,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":57.8},{"place":91,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":57.46},{"place":92,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":57},{"place":93,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":56.6},{"place":94,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":56.6},{"place":95,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":55.8},{"place":96,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":55.8},{"place":97,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":55},{"place":98,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":54.9},{"place":99,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":54.87},{"place":100,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.4},{"place":101,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":54},{"place":102,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54},{"place":103,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":54},{"place":104,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.85},{"place":105,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.8},{"place":106,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":53.76},{"place":107,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53.32},{"place":108,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":53.32},{"place":109,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":53.3},{"place":110,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":53},{"place":111,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":53},{"place":112,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53},{"place":113,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":52},{"place":114,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":51.77},{"place":115,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":51},{"place":116,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":49},{"place":117,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":48.6},{"place":118,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":46.68},{"place":119,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":46.2},{"place":120,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":44.4},{"place":121,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":44},{"place":122,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":44},{"place":123,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":43.78},{"place":124,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":43.3},{"place":125,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":42.2},{"place":126,"model":"laguna-s-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":40.4},{"place":127,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":40},{"place":128,"model":"swe-1.7","company":"cognition","family":"SWE","version":"SWE-1.7","score":37.7},{"place":129,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":37},{"place":130,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":36.1},{"place":131,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":36.06},{"place":132,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":33.6},{"place":133,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":31},{"place":134,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":30.53},{"place":135,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":30},{"place":136,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":29.93},{"place":137,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":24},{"place":138,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":21.6},{"place":139,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":20},{"place":140,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":19},{"place":141,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":18},{"place":142,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":18},{"place":143,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":16.5},{"place":144,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":14.2},{"place":145,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":13.3},{"place":146,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":12.8},{"place":147,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":12},{"place":148,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":11.8},{"place":149,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":11.73},{"place":150,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":10},{"place":151,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":10},{"place":152,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":9},{"place":153,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":8},{"place":154,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":8},{"place":155,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":8},{"place":156,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":7.3},{"place":157,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":0.3}]},{"id":"defects4j","name":"Defects4J","topic":"Program repair","description":"Real Java bugs from Defects4J used for automated program repair.","url":"https://github.com/rjust/defects4j","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-4o-2024-05-13","top_percent":26.1,"top_model_id":"gpt-4o-2024-05-13","top_generation":"GPT-4o","top_model_base":"GPT-4o","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":26.1},{"place":2,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":25.5},{"place":3,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":24.3},{"place":4,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":22.8},{"place":5,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":21},{"place":6,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":18.6},{"place":7,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":17.8},{"place":8,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":16.2},{"place":9,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":11.3},{"place":10,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":9.2}]},{"id":"dense200-det-f1","name":"Dense200 Detection (F1)","topic":"Object detection","description":"Dense200 object detection with an MLLM; F1 averaged over IoU 0.5:0.95.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":71.3,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":71.3},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":61.4},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":58.7},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":58.3},{"place":5,"model":"groundingdino-t","company":"idea-research","family":"GroundingDINO","version":"GroundingDINO","score":33.1},{"place":6,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18},{"place":7,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":13.8}]},{"id":"dense200-pointing","name":"Dense200 Pointing","topic":"Object pointing","description":"Dense200 object pointing accuracy.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"LocateAnything-3B","top_percent":87.6,"top_model_id":"locateanything-3b","top_generation":"LocateAnything","top_model_base":"LocateAnything-3B","top_model_family":"LocateAnything","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":87.6},{"place":2,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":87},{"place":3,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":83.2},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":82.5},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.2}]},{"id":"der2-bench","name":"DeR2 Bench","topic":"Long-context reasoning","description":"Dense retrieval and reasoning benchmark for long-context evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2 (high)","top_percent":69,"top_model_id":"gpt-5.2-high","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":69},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":66.1},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":66},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60.4},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.9},{"place":6,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":58.2},{"place":7,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":57.3},{"place":8,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":50.3},{"place":9,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":46.6}]},{"id":"design2code","name":"Design2Code","topic":"Coding (UI)","description":"Translating UI designs into code.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-5V-Turbo","top_percent":94.8,"top_model_id":"glm-5v-turbo","top_generation":"GLM 5V","top_model_base":"GLM-5V Turbo","top_model_family":"GLM","top_company":"zai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":94.8},{"place":2,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":93.4},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":92.5},{"place":4,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":91.3},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.2},{"place":6,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":88.6},{"place":7,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":88.5},{"place":8,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":82.2},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.3},{"place":10,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":69.8},{"place":11,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":64.7},{"place":12,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":38.8},{"place":13,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":34.1},{"place":14,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":16.1}]},{"id":"designarena","name":"DesignArena","topic":"Generative design","description":"Leaderboard tracking generative design systems across layout, branding, and marketing tasks.","url":"https://designarena.ai","leaderboard":"https://designarena.ai","github":"","paper":"","metric":"elo","stars":"","top_model":"Claude Sonnet 4.5 (Thinking)","top_percent":1410,"top_model_id":"claude-4.5-sonnet-thinking","top_generation":"Claude 4.5","top_model_base":"Claude Sonnet 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":199,"total_models":3854,"placements":[{"place":1,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1410},{"place":2,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1363},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1345},{"place":4,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1341},{"place":5,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":1339},{"place":6,"model":"claude-4.1-opus-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1337},{"place":7,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1337},{"place":8,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":1334},{"place":9,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1333},{"place":10,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1332},{"place":11,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":1329},{"place":12,"model":"muse-spark-1.3-xhigh","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1329},{"place":13,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":1328},{"place":14,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":1323},{"place":15,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1318},{"place":16,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":1318},{"place":17,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1315},{"place":18,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":1309},{"place":19,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":1308},{"place":20,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1307},{"place":21,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":1307},{"place":22,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1306},{"place":23,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":1303},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1301},{"place":25,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1301},{"place":26,"model":"gpt-5.6-sol-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":1299},{"place":27,"model":"deca-2.6-ultra","company":"deca","family":"Deca","version":"Deca 2.6","score":1298},{"place":28,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":1298},{"place":29,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":1295},{"place":30,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1294},{"place":31,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":1293},{"place":32,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":1291},{"place":33,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":1291},{"place":34,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":1290},{"place":35,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1289},{"place":36,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":1289},{"place":37,"model":"deca-2.5-mini","company":"deca","family":"Deca","version":"Deca 2.5","score":1288},{"place":38,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":1288},{"place":39,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1288},{"place":40,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":1286},{"place":41,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":1286},{"place":42,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":1285},{"place":43,"model":"deca-2.6-pro","company":"deca","family":"Deca","version":"Deca 2.6","score":1282},{"place":44,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":1282},{"place":45,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1281},{"place":46,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1281},{"place":47,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1279},{"place":48,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1276},{"place":49,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1273},{"place":50,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1272},{"place":51,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1272},{"place":52,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":1272},{"place":53,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1271},{"place":54,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":1270},{"place":55,"model":"deepseek-coder-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1268},{"place":56,"model":"claude-opus-4.6-thinking","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1266},{"place":57,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1265},{"place":58,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":1265},{"place":59,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":1264},{"place":60,"model":"mistral-medium-2505","company":"mistral","family":"Mistral","version":"Mistral","score":1263},{"place":61,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":1263},{"place":62,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1262},{"place":63,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":1261},{"place":64,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1259},{"place":65,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":1259},{"place":66,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":1258},{"place":67,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":1258},{"place":68,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":1256},{"place":69,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":1256},{"place":70,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":1255},{"place":71,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":1253},{"place":72,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1253},{"place":73,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1253},{"place":74,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1253},{"place":75,"model":"deca-2.5-ultra","company":"deca","family":"Deca","version":"Deca 2.5","score":1252},{"place":76,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":1251},{"place":77,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1249},{"place":78,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1247},{"place":79,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1247},{"place":80,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1246},{"place":81,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":1246},{"place":82,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1245},{"place":83,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1243},{"place":84,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1243},{"place":85,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1240},{"place":86,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":1240},{"place":87,"model":"glm-4-32b","company":"zai","family":"GLM","version":"GLM 4","score":1237},{"place":88,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":1237},{"place":89,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":1236},{"place":90,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1233},{"place":91,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1233},{"place":92,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":1231},{"place":93,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1231},{"place":94,"model":"gpt-5.4-medium","company":"openai","family":"GPT","version":"GPT-5.4","score":1230},{"place":95,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":1230},{"place":96,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":1230},{"place":97,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1229},{"place":98,"model":"o3","company":"openai","family":"o3","version":"o3","score":1228},{"place":99,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":1228},{"place":100,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":1227},{"place":101,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":1226},{"place":102,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1224},{"place":103,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":1223},{"place":104,"model":"v0-1.5-md","company":"vercel","family":"Vercel v0","version":"Vercel v0","score":1222},{"place":105,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":1222},{"place":106,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1220},{"place":107,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":1213},{"place":108,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":1213},{"place":109,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1210},{"place":110,"model":"gemini-2.5-flash-lite-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1210},{"place":111,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":1210},{"place":112,"model":"devstral-medium","company":"mistral","family":"Devstral","version":"Devstral","score":1207},{"place":113,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":1206},{"place":114,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":1205},{"place":115,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":1204},{"place":116,"model":"kimi-k2-turbo-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1203},{"place":117,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1203},{"place":118,"model":"gpt-5.1-low","company":"openai","family":"GPT","version":"GPT-5.1","score":1201},{"place":119,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":1201},{"place":120,"model":"gpt-5.4-low","company":"openai","family":"GPT","version":"GPT-5.4","score":1199},{"place":121,"model":"gpt-5.2-none","company":"openai","family":"GPT","version":"GPT-5.2","score":1199},{"place":122,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1198},{"place":123,"model":"qwen3.5-plus","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1197},{"place":124,"model":"grok-4.2-non-reasoning","company":"xai","family":"Grok","version":"Grok 4.2","score":1195},{"place":125,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":1193},{"place":126,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1193},{"place":127,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":1192},{"place":128,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":1192},{"place":129,"model":"gpt-5.2-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":1192},{"place":130,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":1190},{"place":131,"model":"gpt-5.1-medium","company":"openai","family":"GPT","version":"GPT-5.1","score":1190},{"place":132,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":1189},{"place":133,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":1188},{"place":134,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1187},{"place":135,"model":"gpt-5.1-none","company":"openai","family":"GPT","version":"GPT-5.1","score":1186},{"place":136,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1185},{"place":137,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1184},{"place":138,"model":"gpt-5.2-low","company":"openai","family":"GPT","version":"GPT-5.2","score":1184},{"place":139,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":1182},{"place":140,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1182},{"place":141,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":1182},{"place":142,"model":"v0-1.5-lg","company":"vercel","family":"Vercel v0","version":"Vercel v0","score":1181},{"place":143,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":1181},{"place":144,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1181},{"place":145,"model":"claude-4.1-opus-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1180},{"place":146,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1179},{"place":147,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":1178},{"place":148,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1177},{"place":149,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1176},{"place":150,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1176},{"place":151,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1174},{"place":152,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":1174},{"place":153,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1171},{"place":154,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":1170},{"place":155,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1169},{"place":156,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1169},{"place":157,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1168},{"place":158,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1167},{"place":159,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1166},{"place":160,"model":"codestral-2508","company":"mistral","family":"Codestral","version":"Codestral","score":1164},{"place":161,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1164},{"place":162,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1163},{"place":163,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1160},{"place":164,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1160},{"place":165,"model":"hy3-low","company":"tencent","family":"HY","version":"Hy3","score":1160},{"place":166,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1158},{"place":167,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":1156},{"place":168,"model":"kimi-k2-turbo-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1156},{"place":169,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":1153},{"place":170,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":1152},{"place":171,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":1150},{"place":172,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1150},{"place":173,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1150},{"place":174,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":1148},{"place":175,"model":"gpt-5.1-codex","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":1147},{"place":176,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1146},{"place":177,"model":"solar-mini-4","company":"upstage","family":"Solar","version":"Solar Mini 4","score":1146},{"place":178,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":1144},{"place":179,"model":"aescoder-4b","company":"microsoft","family":"AesCoder","version":"AesCoder","score":1142},{"place":180,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":1140},{"place":181,"model":"v0-1.5-lg","company":"vercel","family":"Vercel v0","version":"Vercel v0","score":1139},{"place":182,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1138},{"place":183,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":1137},{"place":184,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":1137},{"place":185,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":1136},{"place":186,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1135},{"place":187,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":1135},{"place":188,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1134},{"place":189,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":1134},{"place":190,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":1132},{"place":191,"model":"uigen-x-32b-0707","company":"tesslate","family":"UIGen X","version":"UIGen X","score":1130},{"place":192,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1130},{"place":193,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":1130},{"place":194,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":1128},{"place":195,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":1127},{"place":196,"model":"gpt-5.1-codex-mini","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":1126},{"place":197,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":1126},{"place":198,"model":"grok-4.1-fast-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1123},{"place":199,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1120},{"place":200,"model":"agi-01-swift","company":"agi","family":"AGI-01","version":"AGI-01","score":1120},{"place":201,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":1119},{"place":202,"model":"command-a","company":"cohere","family":"Command","version":"Command","score":1119},{"place":203,"model":"webgen-small","company":"tesslate","family":"WEBGEN","version":"WEBGEN","score":1119},{"place":204,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":1118},{"place":205,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1116},{"place":206,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":1107},{"place":207,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":1104},{"place":208,"model":"v0-1.5-md","company":"vercel","family":"Vercel v0","version":"Vercel v0","score":1103},{"place":209,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":1101},{"place":210,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":1099},{"place":211,"model":"magistral-small-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":1099},{"place":212,"model":"grok-2","company":"xai","family":"Grok","version":"Grok 2","score":1098},{"place":213,"model":"gemini-2.5-flash-lite-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1098},{"place":214,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1094},{"place":215,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1094},{"place":216,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1093},{"place":217,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":1091},{"place":218,"model":"mistral-large-2.1-2411","company":"mistral","family":"Mistral","version":"Mistral 2.1","score":1088},{"place":219,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":1088},{"place":220,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1081},{"place":221,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":1080},{"place":222,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1078},{"place":223,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1076},{"place":224,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":1076},{"place":225,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":1073},{"place":226,"model":"uigen-x-4b","company":"tesslate","family":"UIGen X","version":"UIGen X","score":1065},{"place":227,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":1065},{"place":228,"model":"devstral-medium","company":"mistral","family":"Devstral","version":"Devstral","score":1063},{"place":229,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1062},{"place":230,"model":"o3","company":"openai","family":"o3","version":"o3","score":1058},{"place":231,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":1057},{"place":232,"model":"codestral-2501","company":"mistral","family":"Codestral","version":"Codestral","score":1056},{"place":233,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":1054},{"place":234,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":1051},{"place":235,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":1051},{"place":236,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":1050},{"place":237,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":1043},{"place":238,"model":"devstral-small-1.1","company":"mistral","family":"Devstral","version":"Devstral","score":1042},{"place":239,"model":"magistral-medium-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":1039},{"place":240,"model":"codestral-2508","company":"mistral","family":"Codestral","version":"Codestral","score":1039},{"place":241,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":1036},{"place":242,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1034},{"place":243,"model":"llama-4-scout","company":"meta","family":"Llama","version":"Llama 1","score":1031},{"place":244,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1023},{"place":245,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":1016},{"place":246,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1006},{"place":247,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":1004},{"place":248,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":1002},{"place":249,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":989},{"place":250,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":982},{"place":251,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":960},{"place":252,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":951},{"place":253,"model":"magistral-small-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":895},{"place":254,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":885},{"place":255,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":881},{"place":256,"model":"devstral-small-1.1","company":"mistral","family":"Devstral","version":"Devstral","score":862},{"place":257,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":859},{"place":258,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":856},{"place":259,"model":"llama-4-scout","company":"meta","family":"Llama","version":"Llama 1","score":810},{"place":260,"model":"codestral-2501","company":"mistral","family":"Codestral","version":"Codestral","score":803},{"place":261,"model":"mistral-large-2.1-2411","company":"mistral","family":"Mistral","version":"Mistral 2.1","score":794},{"place":262,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":763}]},{"id":"detailbench","name":"DetailBench","topic":"Spot small mistakes","description":"Evaluates whether LLMs can notice subtle errors and minor inconsistencies in text.","url":"https://huggingface.co/datasets/xeophon/detailbench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 4 Maverick","top_percent":8.7,"top_model_id":"llama-4-maverick","top_generation":"Llama 4","top_model_base":"Llama 4 Maverick 17B 128E","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":8.7},{"place":2,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":4.3},{"place":3,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":3.6},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.9},{"place":5,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":2.2},{"place":6,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":0.7}]},{"id":"discox","name":"DiscoX","topic":"Agentic writing","description":"DiscoX benchmark for agentic writing and reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":82,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":82},{"place":2,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.3},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.6},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.8},{"place":5,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":76.3},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":75.8},{"place":7,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":75.1},{"place":8,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":74.6},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.5},{"place":10,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":73},{"place":11,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":71.9},{"place":12,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.6},{"place":13,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.3},{"place":14,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":67.7}]},{"id":"do-anything-now","name":"Do-Anything-Now","topic":"Safety / jailbreak","description":"Resistance to Do Anything Now (DAN) style jailbreak prompts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"IQuest-Coder-V1-40B-Thinking","top_percent":97.7,"top_model_id":"iquest-coder-v1-40b-thinking","top_generation":"IQuest Coder V1","top_model_base":"IQuest Coder V1 40B","top_model_family":"IQuest Coder","top_company":"iquest","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":97.7},{"place":2,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":95.7},{"place":3,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.7},{"place":4,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":63.3},{"place":5,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":43}]},{"id":"do-not-answer","name":"Do-Not-Answer","topic":"Safety / refusal","description":"Evaluates a model's ability to refuse unsafe or disallowed requests.","url":"https://huggingface.co/datasets/LibrAI/do-not-answer","leaderboard":"","github":"https://github.com/Libr-AI/do-not-answer","paper":"https://aclanthology.org/2024.findings-eacl.61","metric":"percent","stars":"","top_model":"Llama 2 7B Chat","top_percent":99.4,"top_model_id":"llama-2-7b-chat","top_generation":"Llama 2","top_model_base":"Llama 2 7B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":99.4},{"place":2,"model":"claude","company":"anthropic","family":"Claude","version":"Claude 1","score":98.3},{"place":3,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":97.8},{"place":4,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":97.7},{"place":5,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":96.5},{"place":6,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":94.9},{"place":7,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":92.9},{"place":8,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":88},{"place":9,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69.9},{"place":10,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":58.6},{"place":11,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":53.9},{"place":12,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":53.7}]},{"id":"doc2dial","name":"Doc2Dial","topic":"Conversational QA","description":"Document-grounded dialogue QA (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":55.8,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":55.8},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":35.3},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":34.6},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":33.1},{"place":5,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":32.8},{"place":6,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":31.6},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":30.2},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":28.2},{"place":9,"model":"o3","company":"openai","family":"o3","version":"o3","score":23.1},{"place":10,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":21.5}]},{"id":"docfigcapbench-caption","name":"DocFigCapBench Caption Score","topic":"Document figure captioning","description":"DocFigCapBench: caption quality score (0-10 scale).","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Qwen3.8-Max","top_percent":7.3,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":7.3},{"place":2,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":6.93},{"place":3,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":4.74},{"place":4,"model":"mineru2.5-pro","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":4.61},{"place":5,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":4.29}]},{"id":"docfigcapbench-loc-f1","name":"DocFigCapBench Localization F1","topic":"Document figure captioning","description":"DocFigCapBench: localization F1 of document figures.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OvisOCR3","top_percent":90.97,"top_model_id":"ovisocr3","top_generation":"OvisOCR3","top_model_base":"OvisOCR3","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":90.97},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.67},{"place":3,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":85.32},{"place":4,"model":"mineru2.5-pro","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":85},{"place":5,"model":"ovisocr2","company":"alibaba","family":"Ovis","version":"OvisOCR2","score":82.18},{"place":6,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.47},{"place":7,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":48.24}]},{"id":"doclaynet","name":"DocLayNet","topic":"Layout analysis","description":"Human-annotated document layout segmentation dataset; layout analysis mIoU/mAP.","url":"https://github.com/DS4SD/DocLayNet","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"PaddleOCR-VL-1.5","top_percent":71.05,"top_model_id":"paddleocr-vl-1.5","top_generation":"PaddleOCR-VL 1.5","top_model_base":"PaddleOCR-VL-1.5","top_model_family":"PaddleOCR","top_company":"paddlepaddle","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":71.05},{"place":2,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":67.74},{"place":3,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":64.97},{"place":4,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":64.93},{"place":5,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":45.62}]},{"id":"docmath","name":"DocMath","topic":"Document math","description":"Math reasoning on document-based problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-35B-A3B","top_percent":68.87,"top_model_id":"qwen3.5-35b-a3b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 35B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":48,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.87},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":67.62},{"place":3,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":66.4},{"place":4,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":66.26},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.87},{"place":6,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.75},{"place":7,"model":"golongrl-30b-a3b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":65.3},{"place":8,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.75},{"place":9,"model":"qwenlong-l1","company":"qwen","family":"QwenLong","version":"QwenLong","score":64.75},{"place":10,"model":"qwen3-max-thinking-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":64.12},{"place":11,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":63.88},{"place":12,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":63.44},{"place":13,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":63.3},{"place":14,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":62.4},{"place":15,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.38},{"place":16,"model":"golongrl-4b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":62.3},{"place":17,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":62.26},{"place":18,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":61.9},{"place":19,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":61.8},{"place":20,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":61.25},{"place":21,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":61},{"place":22,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":59.7},{"place":23,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":59.2},{"place":24,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":58.5},{"place":25,"model":"deepseek-coder-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":57.3},{"place":26,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":54.5},{"place":27,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":54.1},{"place":28,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":52.8},{"place":29,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":52.5},{"place":30,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":52.4},{"place":31,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":52.2},{"place":32,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":50.1},{"place":33,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":47.6},{"place":34,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":41.8},{"place":35,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":39.9},{"place":36,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":38.1},{"place":37,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":36.9},{"place":38,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":35.1},{"place":39,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":34},{"place":40,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":31},{"place":41,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":30.1},{"place":42,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":29.9},{"place":43,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":21.9},{"place":44,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":21.8},{"place":45,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":20.8},{"place":46,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":11.5},{"place":47,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":9},{"place":48,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":8.4},{"place":49,"model":"deepseek-coder-33b","company":"deepseek","family":"DeepSeek Coder","version":"DeepSeek Coder","score":7.6},{"place":50,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":4.1}]},{"id":"docmatix","name":"Docmatix (multimodal RAG)","topic":"Multimodal RAG","description":"Docmatix document-VQA based multimodal retrieval-augmented QA evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":67.4,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":67.4},{"place":2,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":56.8},{"place":3,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":48.5},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":48.4},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":46.2},{"place":6,"model":"o3","company":"openai","family":"o3","version":"o3","score":45.6},{"place":7,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":36.9},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":35.3}]},{"id":"docvqa","name":"DocVQA","topic":"Document understanding (VQA)","description":"Visual question answering over scanned documents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.5-VL-Thinking","top_percent":96.9,"top_model_id":"seed1.5-vl-thinking","top_generation":"Seed 1.5","top_model_base":"Seed 1.5 VL","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":245,"total_models":3854,"placements":[{"place":1,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":96.9},{"place":2,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":96.9},{"place":3,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":96.7},{"place":4,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":96.52},{"place":5,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":96.5},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":96.5},{"place":7,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":96.5},{"place":8,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":96.5},{"place":9,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":96.5},{"place":10,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":96.43},{"place":11,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":96.4},{"place":12,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":96.4},{"place":13,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":96.3},{"place":14,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":96.23},{"place":15,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":96.2},{"place":16,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":96.2},{"place":17,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":96.1},{"place":18,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":96},{"place":19,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":95.7},{"place":20,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":95.6},{"place":21,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":95.5},{"place":22,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":95.5},{"place":23,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":95.45},{"place":24,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.44},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":95.42},{"place":26,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":95.4},{"place":27,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":95.3},{"place":28,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.3},{"place":29,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.3},{"place":30,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":95.3},{"place":31,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":95.2},{"place":32,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":95.2},{"place":33,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":95.2},{"place":34,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":95.2},{"place":35,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":95.14},{"place":36,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":95.1},{"place":37,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":95.1},{"place":38,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95},{"place":39,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":95},{"place":40,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":94.9},{"place":41,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94.9},{"place":42,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":94.9},{"place":43,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":94.9},{"place":44,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":94.86},{"place":45,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94.8},{"place":46,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":94.7},{"place":47,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":94.7},{"place":48,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94.69},{"place":49,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":94.6},{"place":50,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":94.5},{"place":51,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":94.5},{"place":52,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":94.5},{"place":53,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":94.4},{"place":54,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":94.4},{"place":55,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":94.4},{"place":56,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":94.4},{"place":57,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":94.4},{"place":58,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":94.3},{"place":59,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":94.3},{"place":60,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":94.2},{"place":61,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":94.2},{"place":62,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":94.2},{"place":63,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":94.2},{"place":64,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94.2},{"place":65,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":94.2},{"place":66,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":94.2},{"place":67,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":94.16},{"place":68,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":94.1},{"place":69,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":94.1},{"place":70,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":94.1},{"place":71,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":94.1},{"place":72,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":94.1},{"place":73,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":94.08},{"place":74,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":94},{"place":75,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":94},{"place":76,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":93.9},{"place":77,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":93.9},{"place":78,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":93.8},{"place":79,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":93.8},{"place":80,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.68},{"place":81,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":93.65},{"place":82,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":93.6},{"place":83,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":93.5},{"place":84,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":93.5},{"place":85,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":93.4},{"place":86,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":93.3},{"place":87,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":93.3},{"place":88,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":93.3},{"place":89,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":93.3},{"place":90,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":93.3},{"place":91,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":93.2},{"place":92,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":93.2},{"place":93,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":93.16},{"place":94,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":93.1},{"place":95,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":93.1},{"place":96,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":93.1},{"place":97,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":93},{"place":98,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":93},{"place":99,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":93},{"place":100,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":93},{"place":101,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":92.9},{"place":102,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":92.9},{"place":103,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":92.8},{"place":104,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":92.8},{"place":105,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":92.8},{"place":106,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.8},{"place":107,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":92.8},{"place":108,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":92.79},{"place":109,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.7},{"place":110,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.6},{"place":111,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.6},{"place":112,"model":"aria","company":"rhymes","family":"Aria","version":"Aria","score":92.6},{"place":113,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":92.6},{"place":114,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":92.5},{"place":115,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":92.5},{"place":116,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":92.4},{"place":117,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.3},{"place":118,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":92.3},{"place":119,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":92.3},{"place":120,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":92.3},{"place":121,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":92.3},{"place":122,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":92.3},{"place":123,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":92.2},{"place":124,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.2},{"place":125,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":92.1},{"place":126,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":92},{"place":127,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":91.85},{"place":128,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":91.8},{"place":129,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.8},{"place":130,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91.7},{"place":131,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":91.6},{"place":132,"model":"llama-4-maverick-17b-128e-base","company":"meta","family":"Llama","version":"Llama 4","score":91.6},{"place":133,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":91.6},{"place":134,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":91.6},{"place":135,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":91.6},{"place":136,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":91.5},{"place":137,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.5},{"place":138,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":91.5},{"place":139,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.43},{"place":140,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":91.4},{"place":141,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":91.4},{"place":142,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":91.3},{"place":143,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":91.3},{"place":144,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.2},{"place":145,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.1},{"place":146,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":91.1},{"place":147,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":91},{"place":148,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":90.9},{"place":149,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":90.9},{"place":150,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":90.9},{"place":151,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":90.8},{"place":152,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":90.8},{"place":153,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":90.7},{"place":154,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.7},{"place":155,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":90.7},{"place":156,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":90.6},{"place":157,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":90.4},{"place":158,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":90.4},{"place":159,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":90.3},{"place":160,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":90.2},{"place":161,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":90.1},{"place":162,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":90.1},{"place":163,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":90.1},{"place":164,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":90.1},{"place":165,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":90},{"place":166,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":90},{"place":167,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":89.9},{"place":168,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":89.8},{"place":169,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":89.6},{"place":170,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":89.6},{"place":171,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":89.5},{"place":172,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":89.5},{"place":173,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":89.5},{"place":174,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":89.4},{"place":175,"model":"llama-4-scout-17b-16e-base","company":"meta","family":"Llama","version":"Llama 4","score":89.4},{"place":176,"model":"llama-4-scout-17b-base","company":"meta","family":"Llama","version":"Llama 4","score":89.4},{"place":177,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":89.4},{"place":178,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":89.4},{"place":179,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":89.4},{"place":180,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":89.3},{"place":181,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":89.2},{"place":182,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":89.2},{"place":183,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":88.9},{"place":184,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":88.9},{"place":185,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":88.9},{"place":186,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":88.9},{"place":187,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":88.8},{"place":188,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":88.7},{"place":189,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":88.6},{"place":190,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":88.5},{"place":191,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.5},{"place":192,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":88.4},{"place":193,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":88.4},{"place":194,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":88.4},{"place":195,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":88.4},{"place":196,"model":"cogvlm2-llama3-chinese-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":88.4},{"place":197,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":88.3},{"place":198,"model":"moondream-9b-a2b","company":"moondream","family":"Moondream","version":"Moondream 3","score":88.3},{"place":199,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":88.1},{"place":200,"model":"x-omni","company":"tencent","family":"X-Omni","version":"X-Omni","score":88.1},{"place":201,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":88.1},{"place":202,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":88.1},{"place":203,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":88.1},{"place":204,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.9},{"place":205,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":87.9},{"place":206,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":87.8},{"place":207,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":87.8},{"place":208,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":87.7},{"place":209,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":87.7},{"place":210,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.7},{"place":211,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":87.5},{"place":212,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":87.4},{"place":213,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.4},{"place":214,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":87.2},{"place":215,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":87.2},{"place":216,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":87.2},{"place":217,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":87.2},{"place":218,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.1},{"place":219,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":86.9},{"place":220,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":86.7},{"place":221,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":86.6},{"place":222,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":86.5},{"place":223,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":86},{"place":224,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.7},{"place":225,"model":"llava-next-110b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":85.7},{"place":226,"model":"grok-1.5v","company":"xai","family":"Grok","version":"Grok 1.5","score":85.6},{"place":227,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":85.4},{"place":228,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":85},{"place":229,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":84.8},{"place":230,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":84.8},{"place":231,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":84},{"place":232,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":83.9},{"place":233,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":83.3},{"place":234,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":82.5},{"place":235,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.5},{"place":236,"model":"docowl-1.5-chat","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Chat","score":82.2},{"place":237,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":81.7},{"place":238,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":81.6},{"place":239,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":81},{"place":240,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":81},{"place":241,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":80},{"place":242,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":79.9},{"place":243,"model":"gemini-1.5-flash-8b-0827","company":"google","family":"Gemini","version":"Gemini 1.5","score":79.5},{"place":244,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":78.9},{"place":245,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":78.4},{"place":246,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":78.3},{"place":247,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":78.3},{"place":248,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":78.2},{"place":249,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":77.8},{"place":250,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":77.7},{"place":251,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":76.3},{"place":252,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":76.2},{"place":253,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":75.8},{"place":254,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":75.5},{"place":255,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":75.5},{"place":256,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.2},{"place":257,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":74.7},{"place":258,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":74.6},{"place":259,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.5},{"place":260,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":74.3},{"place":261,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":74.1},{"place":262,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":74},{"place":263,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.2},{"place":264,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":73},{"place":265,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":71.9},{"place":266,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":70},{"place":267,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":69.3},{"place":268,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":69.3},{"place":269,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":66.7},{"place":270,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":66.6},{"place":271,"model":"ureader","company":"alibaba","family":"mPLUG","version":"UReader","score":65.4},{"place":272,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":65.1},{"place":273,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":62.6},{"place":274,"model":"mplug-docowl-7b","company":"alibaba","family":"mPLUG","version":"mPLUG-DocOwl","score":62.2},{"place":275,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":61.4},{"place":276,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":57.7},{"place":277,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":57.7},{"place":278,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":54},{"place":279,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":47},{"place":280,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":43.42},{"place":281,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":43.4},{"place":282,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":41.6},{"place":283,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":40.8},{"place":284,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":38.2},{"place":285,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":37.9},{"place":286,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":35.5},{"place":287,"model":"mini-gemini-2b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini","score":34.2},{"place":288,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":33.3},{"place":289,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":31.3},{"place":290,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":30.3},{"place":291,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":28.1},{"place":292,"model":"mobilevlm-v2-3b","company":"meituan","family":"MobileVLM","version":"MobileVLM V2","score":19.4},{"place":293,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":17.1},{"place":294,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":16.9},{"place":295,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":7.2}]},{"id":"dolphin-page","name":"Dolphin-Page","topic":"Document OCR","description":"Dolphin Page benchmark measuring OCR fidelity and structured extraction on multi-layout documents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Dolphin 1.5","top_percent":7.43,"top_model_id":"dolphin-1.5","top_generation":"Dolphin","top_model_base":"Dolphin 1.5","top_model_family":"Dolphin","top_company":"bytedance","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"dolphin-1.5","company":"bytedance","family":"Dolphin","version":"Dolphin","score":7.43},{"place":2,"model":"dolphin","company":"bytedance","family":"Dolphin","version":"Dolphin","score":10.28}]},{"id":"doqa","name":"DoQA","topic":"Conversational QA","description":"Domain-specific FAQ conversational QA (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":63.4,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":63.4},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":37.3},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":35.8},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":34.2},{"place":5,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":28.8},{"place":6,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":26.1},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":25.3},{"place":8,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":24.7},{"place":9,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":20.9},{"place":10,"model":"o3","company":"openai","family":"o3","version":"o3","score":18.6}]},{"id":"dpg-bench","name":"DPG-Bench","topic":"Text rendering","description":"DPG-Bench score for text rendering in image generation.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Seedream 4.5","top_percent":88.63,"top_model_id":"seedream-4.5","top_generation":"Seedream","top_model_base":"Seedream 4.5","top_model_family":"Seedream","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":88.63},{"place":2,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":88.54},{"place":3,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":88.32},{"place":4,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":88.14},{"place":5,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":87.2},{"place":6,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":87.16},{"place":7,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":85.15},{"place":8,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":84.86},{"place":9,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":84.78},{"place":10,"model":"janus-pro","company":"bytedance","family":"Janus","version":"Janus Pro","score":84.19},{"place":11,"model":"sd3-medium","company":"stabilityai","family":"Stable Diffusion 3","version":"SD3","score":84.08},{"place":12,"model":"flux-1-dev","company":"black-forest-labs","family":"FLUX.1","version":"FLUX.1","score":83.52},{"place":13,"model":"dall-e-3","company":"openai","family":"DALL-E","version":"DALL-E 3","score":83.5},{"place":14,"model":"sd-xl","company":"stabilityai","family":"Stable Diffusion","version":"SD XL","score":74.65}]},{"id":"draco","name":"DRACO","topic":"Deep research","description":"DRACO deep-research benchmark scored with per-question rubrics.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":88.6,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.6},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87.6},{"place":3,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":85.49},{"place":4,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":83.3},{"place":5,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":82.3},{"place":6,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":79.85},{"place":7,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":78.55},{"place":8,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":78.5},{"place":9,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":78.1},{"place":10,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":77.7},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.7},{"place":12,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":77.5},{"place":13,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77.3},{"place":14,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":77.2},{"place":15,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":76.8},{"place":16,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.4},{"place":17,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.8},{"place":18,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":73.2},{"place":19,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":71.3},{"place":20,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":70.4},{"place":21,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":66.8},{"place":22,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":65.2},{"place":23,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":61.3}]},{"id":"dream-1k","name":"DREAM-1K","topic":"Video captioning","description":"DREAM-1K dense/detailed video description benchmark of 1,000 clips.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":79.05,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":79.05},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":77.93},{"place":3,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":76.04},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":72.05},{"place":5,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":70}]},{"id":"drop","name":"DROP","topic":"Reading + reasoning","description":"Discrete reasoning over paragraphs (addition, counting, comparisons).","url":"https://allenai.org/data/drop","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi K2 Instruct","top_percent":93.5,"top_model_id":"kimi-k2-instruct","top_generation":"Kimi K2","top_model_base":"Kimi K2","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":151,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":93.5},{"place":2,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":92.2},{"place":3,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":92},{"place":4,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":91.6},{"place":5,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":91.2},{"place":6,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":91.1},{"place":7,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89.7},{"place":8,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":89.2},{"place":9,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89},{"place":10,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":88.9},{"place":11,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.7},{"place":12,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.7},{"place":13,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":88.7},{"place":14,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.6},{"place":15,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":88.32},{"place":16,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":88.3},{"place":17,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.2},{"place":18,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":87.9},{"place":19,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":87.9},{"place":20,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":87.86},{"place":21,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":87.8},{"place":22,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.57},{"place":23,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":87.55},{"place":24,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":87.2},{"place":25,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":86.7},{"place":26,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":86.6},{"place":27,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.5},{"place":28,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":86.4},{"place":29,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":86.3},{"place":30,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":86.3},{"place":31,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":86},{"place":32,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":85.5},{"place":33,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":85.1},{"place":34,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85},{"place":35,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":84.8},{"place":36,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":84.7},{"place":37,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.56},{"place":38,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.3},{"place":39,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":83.7},{"place":40,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":83.7},{"place":41,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":83.6},{"place":42,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":83},{"place":43,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.9},{"place":44,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":82.9},{"place":45,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":82.7},{"place":46,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":82.5},{"place":47,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.4},{"place":48,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":82.37},{"place":49,"model":"hrm-text-1b","company":"sapient","family":"HRM","version":"HRM-Text","score":82.2},{"place":50,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":81.89},{"place":51,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.7},{"place":52,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":81.55},{"place":53,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":81.5},{"place":54,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.6},{"place":55,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":80.4},{"place":56,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":80.4},{"place":57,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":80.1},{"place":58,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":79.7},{"place":59,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":79.6},{"place":60,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":79.49},{"place":61,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":79.3},{"place":62,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":79.1},{"place":63,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":78.8},{"place":64,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":77.5},{"place":65,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":77.2},{"place":66,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":77.2},{"place":67,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":77.2},{"place":68,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":77},{"place":69,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.7},{"place":70,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":74.3},{"place":71,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":74.1},{"place":72,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":73.2},{"place":73,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":73.1},{"place":74,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":73},{"place":75,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":72.9},{"place":76,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.6},{"place":77,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.5},{"place":78,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":72.2},{"place":79,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":72.2},{"place":80,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":72},{"place":81,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":71.9},{"place":82,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":71.5},{"place":83,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":71.5},{"place":84,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":71.2},{"place":85,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":70.9},{"place":86,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":70.5},{"place":87,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.4},{"place":88,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":69.9},{"place":89,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":69.7},{"place":90,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":69.3},{"place":91,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.2},{"place":92,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":68.8},{"place":93,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":68.2},{"place":94,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.9},{"place":95,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":67.9},{"place":96,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":67.6},{"place":97,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":66.7},{"place":98,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":63.6},{"place":99,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":62.6},{"place":100,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":62.5},{"place":101,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":61.5},{"place":102,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":61.5},{"place":103,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":61.3},{"place":104,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":60.7},{"place":105,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":60.4},{"place":106,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":60.1},{"place":107,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":60.1},{"place":108,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":59.5},{"place":109,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":59.36},{"place":110,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":58.8},{"place":111,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":58.57},{"place":112,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":58.4},{"place":113,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":58.29},{"place":114,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":57.2},{"place":115,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.7},{"place":116,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":56.2},{"place":117,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":55.5},{"place":118,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.4},{"place":119,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":54.2},{"place":120,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":53.6},{"place":121,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":52.1},{"place":122,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":51.78},{"place":123,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":51.3},{"place":124,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":51.2},{"place":125,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":49.9},{"place":126,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":49.73},{"place":127,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":49.7},{"place":128,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":49.4},{"place":129,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":49.1},{"place":130,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":46.4},{"place":131,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":46.22},{"place":132,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":46},{"place":133,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":45.8},{"place":134,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":45.2},{"place":135,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":45},{"place":136,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.7},{"place":137,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":44.7},{"place":138,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":44.33},{"place":139,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":44.3},{"place":140,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":41.7},{"place":141,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":41.7},{"place":142,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":41.53},{"place":143,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":41.3},{"place":144,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":41},{"place":145,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":40.8},{"place":146,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":39.8},{"place":147,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":39.4},{"place":148,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":38.4},{"place":149,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":37.1},{"place":150,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":35.98},{"place":151,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":34.9},{"place":152,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.2},{"place":153,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":34},{"place":154,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":33.8},{"place":155,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.3},{"place":156,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":33.1},{"place":157,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":32.9},{"place":158,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":31.2},{"place":159,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.8},{"place":160,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":29.3},{"place":161,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":25.6},{"place":162,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":25.5},{"place":163,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":24.8},{"place":164,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":23.84},{"place":165,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":20.99},{"place":166,"model":"huginn-3.5b","company":"tomg-umd","family":"Huginn","version":"Huginn","score":17.8},{"place":167,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":15.2},{"place":168,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":11},{"place":169,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":4.5},{"place":170,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":3.9}]},{"id":"ds-1000","name":"DS-1000","topic":"Data-science code generation","description":"DS-1000: 1000 data-science coding problems across 7 Python libraries.","url":"https://ds1000-code-gen.github.io/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2211.11501","metric":"percent","stars":"","top_model":"DeepSeek-Coder-33B-base","top_percent":40.2,"top_model_id":"deepseek-coder-33b-base","top_generation":"DeepSeek Coder","top_model_base":"DeepSeek Coder 33B","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":40.2},{"place":2,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":34.3},{"place":3,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":30.5},{"place":4,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":26.8},{"place":5,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":24.6},{"place":6,"model":"codegeex2-6b","company":"zai","family":"CodeGeeX","version":"CodeGeeX2","score":22.9},{"place":7,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":22.1},{"place":8,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":16.2}]},{"id":"dsbench-fullstack","name":"DSBench-FullStack (internal)","topic":"Coding","description":"DeepSeek internal full-stack development test set for coding agents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":77.2,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":77.2},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":73.7},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":71.6},{"place":4,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":71.1},{"place":5,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":68.7},{"place":6,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":61.8},{"place":7,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":41.8},{"place":8,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37}]},{"id":"dsbench-hard","name":"DSBench-Hard (internal)","topic":"Coding","description":"DeepSeek internal test set of difficult coding-agent problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.8","top_percent":71.7,"top_model_id":"claude-opus-4.8","top_generation":"Claude 4.8","top_model_base":"Claude Opus 4.8","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":71.7},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68.3},{"place":3,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67.2},{"place":4,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":63.6},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":63},{"place":6,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.6},{"place":7,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":54.5},{"place":8,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":31.1},{"place":9,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":25.8}]},{"id":"dude","name":"DUDE","topic":"Multimodal long-context","description":"Long-context multimodal understanding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":84.5,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":84.5},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":83.1},{"place":3,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":82.8},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82.1},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.7},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.1},{"place":7,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":69.4},{"place":8,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":67.3},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.1},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.3},{"place":11,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":54}]},{"id":"dynamath","name":"DynaMath","topic":"Math reasoning (video)","description":"Dynamic/video-based mathematical reasoning evaluating temporal and visual understanding.","url":"https://dynamath.github.io/","leaderboard":"https://dynamath.github.io/","github":"https://github.com/DynaMath/DynaMath","paper":"https://arxiv.org/pdf/2411.00836","metric":"percent","stars":"","top_model":"Qwen3.6-Plus","top_percent":88,"top_model_id":"qwen3.6-plus","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":68,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":88},{"place":2,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.7},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.8},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.3},{"place":5,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.9},{"place":6,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.6},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85.1},{"place":8,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85},{"place":9,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.4},{"place":10,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":83.8},{"place":11,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.6},{"place":12,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.3},{"place":13,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.8},{"place":14,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":82.8},{"place":15,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":81.4},{"place":16,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.1},{"place":17,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.7},{"place":18,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.5},{"place":19,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":79.3},{"place":20,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.8},{"place":21,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":78},{"place":22,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":75.9},{"place":23,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.4},{"place":24,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.6},{"place":25,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":73.1},{"place":26,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":72.1},{"place":27,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.9},{"place":28,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":68.1},{"place":29,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.7},{"place":30,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":64.8},{"place":31,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":63.7},{"place":32,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":63.3},{"place":33,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":63.1},{"place":34,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.5},{"place":35,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":61.5},{"place":36,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":61.1},{"place":37,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":60.5},{"place":38,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":59.1},{"place":39,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.3},{"place":40,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":57.1},{"place":41,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.3},{"place":42,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":55.5},{"place":43,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":55.1},{"place":44,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":54.5},{"place":45,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":54},{"place":46,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":53.9},{"place":47,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":52.7},{"place":48,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":52.5},{"place":49,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":50.1},{"place":50,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.1},{"place":51,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.9},{"place":52,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.9},{"place":53,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.7},{"place":54,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":47.5},{"place":55,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.5},{"place":56,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":44},{"place":57,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":43.7},{"place":58,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":42.5},{"place":59,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":42.1},{"place":60,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":41.8},{"place":61,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":41},{"place":62,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":39.7},{"place":63,"model":"r-4b-base","company":"tencent","family":"R","version":"R","score":39.5},{"place":64,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":35.7},{"place":65,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":35.3},{"place":66,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":31.3},{"place":67,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":30.6},{"place":68,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":28.5},{"place":69,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":28.1},{"place":70,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":27.1},{"place":71,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":23.9},{"place":72,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":21.5},{"place":73,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":20.1},{"place":74,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":19.8},{"place":75,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":16.6}]},{"id":"economically-important-tasks","name":"Economically important tasks","topic":"Industry QA (cross-domain)","description":"Evaluation suite of real-world, economically impactful tasks across key industries and workflows.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":47.1,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":47.1},{"place":2,"model":"o3","company":"openai","family":"o3","version":"o3","score":33.5}]},{"id":"edubench-english","name":"EduBench English","topic":"Education (English)","description":"Yandex education benchmark built from Alice user queries: English language subset.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Flash Base","top_percent":82.9,"top_model_id":"deepseek-v4-flash-base","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Flash Base","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.9},{"place":2,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":76.1},{"place":3,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.7},{"place":4,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.3},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":67.2}]},{"id":"edubench-history","name":"EduBench History","topic":"Education (history)","description":"Yandex education benchmark built from Alice user queries: history subset.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":82,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":82},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.9},{"place":3,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70.2},{"place":4,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.9},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":62.8}]},{"id":"edubench-literature","name":"EduBench Literature","topic":"Education (literature)","description":"Yandex education benchmark built from Alice user queries: literature subset.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":73.8,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":73.8},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.1},{"place":3,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":55.8},{"place":4,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.8},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":51.4}]},{"id":"edubench-math","name":"EduBench Math","topic":"Education (math)","description":"Yandex education benchmark built from Alice user queries: school math subset.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-35B-A3B-Base","top_percent":80,"top_model_id":"qwen3.5-35b-a3b-base","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 35B A3B Base","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80},{"place":2,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":79.3},{"place":3,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.3},{"place":4,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":69.7},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":56.9}]},{"id":"edubench-math-university","name":"EduBench Math University","topic":"Education (university math)","description":"Yandex education benchmark built from Alice user queries: university math subset.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":70.1,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":70.1},{"place":2,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":3,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":68.6},{"place":4,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.4},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":51.4}]},{"id":"edubench-russian","name":"EduBench Russian","topic":"Education (Russian language)","description":"Yandex education benchmark built from Alice user queries: Russian language subset.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":74.2,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":74.2},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67.7},{"place":3,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":44},{"place":4,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.9},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":39}]},{"id":"education-bench","name":"Education","topic":"Economics/education","description":"Education field evaluation (economically valuable tasks).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":60.8,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":60.8},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":57},{"place":3,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":55},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.4}]},{"id":"eebench","name":"EEBench","topic":"Electrical engineering","description":"atopile's electrical-engineering agent benchmark: circuit/PCB design tasks expressed as declarative atopile code and verified automatically.","url":"https://eebench.org/","leaderboard":"https://eebench.org/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":75,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":75},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":69.3},{"place":3,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":67.2},{"place":4,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":67.1},{"place":5,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":64},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":63.6},{"place":7,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":62.7},{"place":8,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":61.6},{"place":9,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":57.1},{"place":10,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":56.4},{"place":11,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":56.3},{"place":12,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":55.4},{"place":13,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.3},{"place":14,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":53},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":51.4},{"place":16,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":50.9},{"place":17,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":49.4},{"place":18,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":46.3},{"place":19,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":40.3},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":39.4},{"place":21,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":37.4},{"place":22,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":34.3},{"place":23,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":31.1},{"place":24,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":20.4},{"place":25,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":19.5},{"place":26,"model":"grok-build-0.1","company":"xai","family":"Grok","version":"Grok Build","score":18},{"place":27,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3.5}]},{"id":"ege","name":"EGE","topic":"Russian state exam","description":"Part-A questions of the Russian Unified State Exam (EGE) across subjects.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":90.5,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":90.5},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.3},{"place":3,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.7},{"place":4,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.3},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":77.8}]},{"id":"ego3d-bench","name":"Ego3D-Bench (RMSE)","topic":"Driving spatial reasoning","description":"Ego-centric multi-view 3D spatial reasoning benchmark on outdoor driving scenes; metric = RMSE of numeric answers (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"rmse","stars":"","top_model":"Qwen-Drive-1.0-4B","top_percent":7.78,"top_model_id":"qwen-drive-1.0-4b","top_generation":"Qwen-Drive-1.0","top_model_base":"Qwen-Drive 1.0 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":true,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":7.78},{"place":2,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":9.85},{"place":3,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":12.62},{"place":4,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.17},{"place":5,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":22.41},{"place":6,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":23.01},{"place":7,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":24.97},{"place":8,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":25.31},{"place":9,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":26.71}]},{"id":"egoplan-bench2","name":"EgoPlan-Bench2","topic":"Embodied reasoning","description":"Egocentric embodied task-planning benchmark (v2).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":69.3,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":69.3},{"place":2,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":62.1},{"place":3,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":56.1},{"place":4,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":53.1},{"place":5,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":53.1},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":48.4},{"place":7,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":47.5},{"place":8,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":42.6},{"place":9,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":37.9},{"place":10,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":37},{"place":11,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":33.8},{"place":12,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":33.5},{"place":13,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":32.1}]},{"id":"egoschema","name":"EgoSchema","topic":"Egocentric video QA","description":"EgoSchema validation accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2","top_percent":81.2,"top_model_id":"gpt-5.2","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":70,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":81.2},{"place":2,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":79.3},{"place":3,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":77.9},{"place":4,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":77.2},{"place":5,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":76.2},{"place":6,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":75.6},{"place":7,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":75.6},{"place":8,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":73.3},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.1},{"place":10,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":72.2},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.2},{"place":12,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":72.2},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.2},{"place":14,"model":"nova-pro","company":"amazon","family":"Nova","version":"Nova","score":72.1},{"place":15,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":71.5},{"place":16,"model":"nova-lite","company":"amazon","family":"Nova","version":"Nova","score":71.4},{"place":17,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":70.9},{"place":18,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.7},{"place":19,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.2},{"place":20,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.2},{"place":21,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.8},{"place":22,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":69.7},{"place":23,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.7},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68.9},{"place":25,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":68.8},{"place":26,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":68.8},{"place":27,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":68.6},{"place":28,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.4},{"place":29,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":68.2},{"place":30,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":68},{"place":31,"model":"gemini-2.0-flash-lite-preview","company":"google","family":"Gemini","version":"Gemini 2.0","score":67.2},{"place":32,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.2},{"place":33,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":67},{"place":34,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":66.9},{"place":35,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":66.8},{"place":36,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":66.7},{"place":37,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":66.7},{"place":38,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":64},{"place":39,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":63.5},{"place":40,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":63.2},{"place":41,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":63},{"place":42,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":62.6},{"place":43,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":62.4},{"place":44,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":62},{"place":45,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":61.3},{"place":46,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":61.2},{"place":47,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":61},{"place":48,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":60.4},{"place":49,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":59.6},{"place":50,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":59.4},{"place":51,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":58.9},{"place":52,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":58.8},{"place":53,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":58.6},{"place":54,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":58.2},{"place":55,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":57.6},{"place":56,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":57.4},{"place":57,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":57.3},{"place":58,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":56.8},{"place":59,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":56.3},{"place":60,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":55.7},{"place":61,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.7},{"place":62,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":55.6},{"place":63,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":54.9},{"place":64,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":54.2},{"place":65,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":53.9},{"place":66,"model":"videollama2-7b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":51.7},{"place":67,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":51.3},{"place":68,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":50.5},{"place":69,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":49.6},{"place":70,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":48},{"place":71,"model":"llava-next-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":43.9},{"place":72,"model":"videochat2-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":42.1},{"place":73,"model":"video-llava-7b","company":"pku","family":"Video-LLaVA","version":"Video-LLaVA","score":38.4},{"place":74,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":34.8},{"place":75,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":34},{"place":76,"model":"anygpt","company":"fudan","family":"AnyGPT","version":"AnyGPT","score":32.1}]},{"id":"egotempo","name":"EgoTempo","topic":"Egocentric temporal reasoning","description":"Egocentric video temporal reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":71.8,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.8},{"place":2,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":68.4},{"place":3,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":67.2},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":67},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65.4},{"place":6,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":61.8},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":58.4},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":58.1},{"place":9,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":51.7}]},{"id":"ehrnoteqa","name":"EHRNoteQA","topic":"Medical records","description":"Clinical-note question answering over MIMIC-IV discharge summaries.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedGemma 27B","top_percent":90.7,"top_model_id":"medgemma-27b-it","top_generation":"MedGemma 1","top_model_base":"MedGemma","top_model_family":"MedGemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":90.7},{"place":2,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":80.4},{"place":3,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":79.4},{"place":4,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":78}]},{"id":"eifbench","name":"EIFBench","topic":"Instruction following","description":"Complex instruction-following benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":66.7,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":66.7},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":50.1},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":48.6},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.7}]},{"id":"embspatialbench","name":"EmbSpatialBench","topic":"Spatial understanding","description":"Embodied spatial understanding benchmark evaluating navigation and localization.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-Omni-Plus","top_percent":85.4,"top_model_id":"qwen3.5-omni-plus","top_generation":"Qwen3.5 Omni","top_model_base":"Qwen3.5 Omni Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":71,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":85.4},{"place":2,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":84.7},{"place":3,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.6},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.5},{"place":5,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.5},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.3},{"place":7,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.3},{"place":8,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.3},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.2},{"place":10,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.9},{"place":11,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":83.4},{"place":12,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.2},{"place":13,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.1},{"place":14,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83},{"place":15,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":82.9},{"place":16,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":82.8},{"place":17,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":82.7},{"place":18,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":82.7},{"place":19,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":82.67},{"place":20,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":82.5},{"place":21,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":82.1},{"place":22,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.9},{"place":23,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":81.9},{"place":24,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":81.8},{"place":25,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.5},{"place":26,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.5},{"place":27,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":81.3},{"place":28,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.3},{"place":29,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.1},{"place":30,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":80.7},{"place":31,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.7},{"place":32,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.7},{"place":33,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.6},{"place":34,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":80.5},{"place":35,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.9},{"place":36,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":79.8},{"place":37,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.6},{"place":38,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.1},{"place":39,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":78.9},{"place":40,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":78.85},{"place":41,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":78.8},{"place":42,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":78.8},{"place":43,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":78.6},{"place":44,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.5},{"place":45,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":78.43},{"place":46,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":78.4},{"place":47,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.2},{"place":48,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.1},{"place":49,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":78},{"place":50,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.9},{"place":51,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":77.9},{"place":52,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":77.9},{"place":53,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":77.88},{"place":54,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":77.61},{"place":55,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.5},{"place":56,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77.4},{"place":57,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":77.2},{"place":58,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":77},{"place":59,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.4},{"place":60,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":76.2},{"place":61,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.99},{"place":62,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.9},{"place":63,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.9},{"place":64,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":75.7},{"place":65,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":75.2},{"place":66,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":74.7},{"place":67,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":74.2},{"place":68,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":74.2},{"place":69,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":73.8},{"place":70,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":73.4},{"place":71,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":72.67},{"place":72,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":72.1},{"place":73,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":72.1},{"place":74,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":72},{"place":75,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.8},{"place":76,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":69.7},{"place":77,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":69.2},{"place":78,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.2},{"place":79,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":68.8},{"place":80,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.6},{"place":81,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":67.5},{"place":82,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":67},{"place":83,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.3},{"place":84,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.1},{"place":85,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":61.2},{"place":86,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":50.7},{"place":87,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":45.05},{"place":88,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":41.51},{"place":89,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":20.58}]},{"id":"emma","name":"EMMA","topic":"Multimodal reasoning","description":"EMMA benchmark for multimodal reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":79.3,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":79.3},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":79},{"place":3,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":78.4},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":72.1},{"place":5,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":68.7},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":66.5},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.7},{"place":8,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":59.5},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.4},{"place":10,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":53.5},{"place":11,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":49.5}]},{"id":"enamel","name":"Enamel","topic":"Composite capability","description":"Composite capability benchmark capturing broad model performance (Enamel score).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Rnj-1.5","top_percent":50.7,"top_model_id":"rnj-1.5","top_generation":"Rnj 1.5","top_model_base":"Rnj 1.5","top_model_family":"Rnj","top_company":"essential","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":50.7},{"place":2,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":49},{"place":3,"model":"gpt-oss-20b-moe","company":"openai","family":"GPT","version":"GPT-OSS","score":38.3},{"place":4,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":38.3},{"place":5,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.8},{"place":6,"model":"codestral-12b-instruct","company":"mistral","family":"Codestral","version":"Codestral","score":29.5},{"place":7,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28.4},{"place":8,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":17.5},{"place":9,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":11.5},{"place":10,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":9.2}]},{"id":"enconda-bench","name":"EnConda-Bench","topic":"Code editing","description":"English code editing benchmark for applying conditional modifications.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Youtu-LLM-2B","top_percent":21.5,"top_model_id":"youtu-llm-2b","top_generation":"Youtu-LLM","top_model_base":"Youtu-LLM-2B","top_model_family":"Youtu-LLM","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":21.5},{"place":2,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":16.1},{"place":3,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":10.8},{"place":4,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":3.5}]},{"id":"encyclo-k","name":"Encyclo-K","topic":"Encyclopedic knowledge","description":"Encyclopedic knowledge evaluation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":65.7,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":65.7},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":64.9},{"place":3,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.5},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.3},{"place":5,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":61},{"place":6,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":60},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58},{"place":8,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":53},{"place":9,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":52.1}]},{"id":"enigmaval","name":"EnigmaEval","topic":"Challenging puzzles","description":"Challenging puzzle benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":17.8,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":17.8},{"place":2,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":15.9},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":14.5},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":12.4},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":11.7},{"place":6,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":8.2},{"place":7,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":7.8},{"place":8,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":6},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":5.6},{"place":10,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":5.2},{"place":11,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":2.9},{"place":12,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.7},{"place":13,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.3},{"place":14,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":0.8},{"place":15,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0.8}]},{"id":"enterprise-rag","name":"Enterprise RAG","topic":"Retrieval-augmented generation","description":"Enterprise retrieval-augmented generation evaluation covering internal knowledge bases.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Apriel Nemotron 15B Thinker","top_percent":69.2,"top_model_id":"apriel-nemotron-15b-thinker","top_generation":"Apriel Nemotron","top_model_base":"Apriel Nemotron 15B Thinker","top_model_family":"Apriel","top_company":"servicenow","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":69.2},{"place":2,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":66.5},{"place":3,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":65.2},{"place":4,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":52.1},{"place":5,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":11.1}]},{"id":"enterpriseops-gym","name":"EnterpriseOps-Gym","topic":"Enterprise agent tasks","description":"Agentic benchmark of enterprise operations workflows with tool use.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nanbeige4.3-33B","top_percent":41,"top_model_id":"nanbeige4.3-33b","top_generation":"Nanbeige4.3","top_model_base":"Nanbeige4.3 33B","top_model_family":"Nanbeige","top_company":"boss","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":41},{"place":2,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":40.2},{"place":3,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":33.6},{"place":4,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":30.5},{"place":5,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":27.3},{"place":6,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.3},{"place":7,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.7},{"place":8,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":24.5},{"place":9,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.9},{"place":10,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.6}]},{"id":"eqbench","name":"EQ-Bench","topic":"Reasoning","description":"General reasoning benchmark assessing equation/logic capabilities.","url":"https://eqbench.com/eqbench-v2.html","leaderboard":"https://eqbench.com/eqbench-v2.html","github":"https://github.com/EQ-bench","paper":"https://arxiv.org/abs/2312.06281","metric":"percent","stars":"352","top_model":"Claude 3.5 Sonnet 20240620","top_percent":86.36,"top_model_id":"claude-3.5-sonnet-20240620","top_generation":"Claude 3.5","top_model_base":"Claude 3.5 Sonnet","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":186,"total_models":3854,"placements":[{"place":1,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":86.36},{"place":2,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":86.35},{"place":3,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":86.05},{"place":4,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":85.73},{"place":5,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":85.17},{"place":6,"model":"mistral-large-2407","company":"mistral","family":"Mistral","version":"Mistral","score":85.05},{"place":7,"model":"rys-xlarge-base","company":"rys","family":"RYS","version":"RYS","score":85.05},{"place":8,"model":"jan-v1-2509","company":"menlo","family":"Jan","version":"Jan v1","score":85},{"place":9,"model":"senku-70b-full","company":"shinojiresearch","family":"Senku","version":"Senku","score":84.89},{"place":10,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":84.79},{"place":11,"model":"rys-xlarge","company":"rys","family":"RYS","version":"RYS","score":84.55},{"place":12,"model":"gpt-4-0125-preview","company":"openai","family":"GPT","version":"GPT-4","score":83.87},{"place":13,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83.68},{"place":14,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":83.52},{"place":15,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":83.51},{"place":16,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":83.41},{"place":17,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":83.18},{"place":18,"model":"miiqu-f16","company":"infinimol","family":"Miqu","version":"Miqu","score":83.17},{"place":19,"model":"ece-tw3-jrgl-v1","company":"paloalma","family":"ECE","version":"ECE-TW3","score":83.07},{"place":20,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":83},{"place":21,"model":"miqu-1-70b","company":"mistral","family":"Miqu","version":"Miqu","score":82.91},{"place":22,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":82.81},{"place":23,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":82.79},{"place":24,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":82.67},{"place":25,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.61},{"place":26,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":82.58},{"place":27,"model":"mistral-medium","company":"mistral","family":"Mistral","version":"Mistral","score":82.57},{"place":28,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":82.52},{"place":29,"model":"chatgpt-4o-latest-20240903","company":"openai","family":"GPT","version":"GPT-4o","score":82.45},{"place":30,"model":"miquliz-120b-v2.0","company":"wolfram","family":"Miqu","version":"Miquliz","score":82.21},{"place":31,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":82.19},{"place":32,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":82.19},{"place":33,"model":"miquella-120b","company":"alpindale","family":"Miqu","version":"Miqu","score":82.15},{"place":34,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":82.13},{"place":35,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":82.04},{"place":36,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":81.98},{"place":37,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":81.96},{"place":38,"model":"tess-72b-v1.5b","company":"migtissera","family":"Tess","version":"Tess v1.5","score":81.78},{"place":39,"model":"rys-xlarge-base","company":"rys","family":"RYS","version":"RYS","score":81.67},{"place":40,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":81.35},{"place":41,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":81.32},{"place":42,"model":"mistral-small-instruct-2409","company":"mistral","family":"Mistral","version":"Mistral","score":80.86},{"place":43,"model":"qwen-72b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":80.7},{"place":44,"model":"rys-xlarge","company":"rys","family":"RYS","version":"RYS","score":80.69},{"place":45,"model":"smaug-llama-3-70b-instruct","company":"abacusai","family":"Smaug","version":"Smaug","score":80.69},{"place":46,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":80.55},{"place":47,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":80.51},{"place":48,"model":"hermes-4-70b","company":"nousresearch","family":"Hermes","version":"Hermes 4","score":80.5},{"place":49,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":80.46},{"place":50,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":80.45},{"place":51,"model":"mistral-small-2402","company":"mistral","family":"Mistral","version":"Mistral","score":80.36},{"place":52,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":80.32},{"place":53,"model":"megadolphin-120b","company":"cognitivecomputations","family":"Dolphin","version":"MegaDolphin","score":80.21},{"place":54,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.15},{"place":55,"model":"gemma-2-ifable-9b","company":"ifable","family":"Gemma","version":"Gemma 2","score":79.93},{"place":56,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":79.91},{"place":57,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.89},{"place":58,"model":"smaug-72b-v0.1","company":"abacusai","family":"Smaug","version":"Smaug","score":79.75},{"place":59,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":79.6},{"place":60,"model":"dolphin-2.2-70b","company":"cognitivecomputations","family":"Dolphin","version":"Dolphin 2.2","score":79.6},{"place":61,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":79.51},{"place":62,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.5},{"place":63,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.23},{"place":64,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.05},{"place":65,"model":"theprofessor-155b","company":"abacusai","family":"TheProfessor","version":"TheProfessor","score":78.82},{"place":66,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":78.79},{"place":67,"model":"westlake-7b-v2","company":"senseable","family":"WestLake","version":"WestLake v2","score":78.7},{"place":68,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":78.52},{"place":69,"model":"discolm-120b","company":"discoresearch","family":"DiscoLM","version":"DiscoLM","score":78.48},{"place":70,"model":"tess-xl-v1.0","company":"migtissera","family":"Tess","version":"Tess v1.0","score":78.46},{"place":71,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":77.91},{"place":72,"model":"wizardlm-2-8x22b","company":"microsoft","family":"WizardLM","version":"WizardLM-2","score":77.91},{"place":73,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":77.22},{"place":74,"model":"experiment26-7b","company":"yam-peleg","family":"Experiment","version":"Experiment26","score":77.21},{"place":75,"model":"quyen-pro-max-v0.1","company":"vilm","family":"Quyen","version":"Quyen v0.1","score":77.16},{"place":76,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":77.13},{"place":77,"model":"beyonder-4x7b-v3","company":"mlabonne","family":"Beyonder","version":"Beyonder v3","score":77.01},{"place":78,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":76.97},{"place":79,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":76.93},{"place":80,"model":"claude","company":"anthropic","family":"Claude","version":"Claude 1","score":76.83},{"place":81,"model":"databricks-dbrx-instruct","company":"databricks","family":"databricks/dbrx-instruct","version":"databricks/dbrx-instruct","score":76.82},{"place":82,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":76.78},{"place":83,"model":"tulu-2-dpo-70b","company":"ai2","family":"Tulu","version":"Tulu 2 DPO 70B","score":76.63},{"place":84,"model":"samantha-120b","company":"cognitivecomputations","family":"Samantha","version":"Samantha","score":76.44},{"place":85,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":76.34},{"place":86,"model":"neuralmonarch-7b","company":"mlabonne","family":"Monarch","version":"Monarch","score":76.26},{"place":87,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":76.11},{"place":88,"model":"goliath-120b","company":"alpindale","family":"Goliath","version":"Goliath","score":76.09},{"place":89,"model":"alphamonarch-7b","company":"mlabonne","family":"Monarch","version":"Monarch","score":76.08},{"place":90,"model":"midnight-miqu-70b-v1.0","company":"sophosympatheia","family":"Miqu","version":"Midnight-Miqu","score":75.9},{"place":91,"model":"monarch-7b","company":"mlabonne","family":"Monarch","version":"Monarch","score":75.8},{"place":92,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":75.59},{"place":93,"model":"dolphin-2.2-yi-34b","company":"cognitivecomputations","family":"Dolphin","version":"Dolphin 2.2","score":75.52},{"place":94,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":75.08},{"place":95,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.99},{"place":96,"model":"neuralbeagle14-7b","company":"mlabonne","family":"Beagle","version":"NeuralBeagle14","score":74.79},{"place":97,"model":"beagle14-7b","company":"mlabonne","family":"Beagle","version":"Beagle14","score":74.45},{"place":98,"model":"neuralmarcoro14-7b","company":"mlabonne","family":"Marcoro","version":"NeuralMarcoro14","score":74.15},{"place":99,"model":"gml-mistral-merged-v1","company":"zyh3826","family":"GML-Mistral","version":"GML-Mistral","score":74.01},{"place":100,"model":"claude-2.1","company":"anthropic","family":"Claude","version":"Claude 2","score":73.96},{"place":101,"model":"meow","company":"rishiraj","family":"Meow","version":"Meow","score":73.94},{"place":102,"model":"starling-lm-7b-alpha","company":"berkeley","family":"Starling","version":"Starling LM","score":73.9},{"place":103,"model":"starling-lm-7b-beta","company":"berkeley","family":"Starling","version":"Starling LM","score":73.82},{"place":104,"model":"synthia-70b-v1.5","company":"migtissera","family":"SynthIA","version":"SynthIA v1.5","score":73.71},{"place":105,"model":"lmcocktail-10.7b-v1","company":"yhyu13","family":"LMCocktail","version":"LMCocktail","score":73.67},{"place":106,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":73.59},{"place":107,"model":"sauerkrautlm-una-solar-instruct","company":"weyaxi","family":"SauerkrautLM","version":"SauerkrautLM","score":73.56},{"place":108,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":73.53},{"place":109,"model":"phi-3-small-8k-instruct","company":"microsoft","family":"Phi","version":"Phi-3","score":73.49},{"place":110,"model":"solar-10.7b-instruct-dpo","company":"macadeliccc","family":"SOLAR","version":"SOLAR","score":73.21},{"place":111,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":72.95},{"place":112,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":72.93},{"place":113,"model":"nous-hermes-2-mixtral-8x7b-sft","company":"nousresearch","family":"Hermes","version":"Hermes 2","score":72.91},{"place":114,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":72.89},{"place":115,"model":"mixtral-34bx2-moe-60b","company":"cloudyu","family":"Mixtral","version":"Mixtral merge","score":72.69},{"place":116,"model":"nous-hermes-2-yi-34b","company":"nousresearch","family":"Hermes","version":"Hermes 2","score":72.68},{"place":117,"model":"openchat-3.5-1210","company":"openchat","family":"OpenChat","version":"OpenChat 3.5","score":72.52},{"place":118,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":72.37},{"place":119,"model":"openchat-3.5","company":"openchat","family":"OpenChat","version":"OpenChat 3.5","score":72.18},{"place":120,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":71.97},{"place":121,"model":"laserxtral","company":"cognitivecomputations","family":"Laserxtral","version":"Laserxtral","score":71.96},{"place":122,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":71.74},{"place":123,"model":"marcoroni-7b-v3","company":"madatnlp","family":"Marcoroni","version":"Marcoroni v3","score":71.68},{"place":124,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":71.62},{"place":125,"model":"wizardlm-70b","company":"wizardlm","family":"WizardLM","version":"WizardLM-70B","score":71.28},{"place":126,"model":"quyen-pro-v0.1","company":"vilm","family":"Quyen","version":"Quyen v0.1","score":70.75},{"place":127,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":70.67},{"place":128,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":70.37},{"place":129,"model":"dolphin-2.2.1-mistral-7b","company":"cognitivecomputations","family":"Dolphin","version":"Dolphin","score":69.92},{"place":130,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":69.35},{"place":131,"model":"wizardlm-2-7b","company":"microsoft","family":"WizardLM","version":"WizardLM-2","score":69.31},{"place":132,"model":"beyonder-4x7b-v2","company":"mlabonne","family":"Beyonder","version":"Beyonder v2","score":69.23},{"place":133,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.18},{"place":134,"model":"claude-instant-1.2","company":"anthropic","family":"Claude","version":"Claude Instant","score":69.04},{"place":135,"model":"meta-llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":68.88},{"place":136,"model":"marcoroni-neural-chat-7b-v2","company":"toten5","family":"Marcoroni","version":"Marcoroni","score":68.54},{"place":137,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":68.18},{"place":138,"model":"llama-3.2-vision-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":67.88},{"place":139,"model":"vicuna-13b-v1.5","company":"lmsys","family":"Vicuna","version":"Vicuna v1.5","score":67.39},{"place":140,"model":"vicuna-33b-v1.3","company":"lmsys","family":"Vicuna","version":"Vicuna","score":67.07},{"place":141,"model":"openhermes-2.5-mistral-7b","company":"openhermes","family":"OpenHermes","version":"OpenHermes 2.5","score":66.89},{"place":142,"model":"exaone-3.0-7.8b-instruct","company":"lgai","family":"EXAONE","version":"EXAONE 3.0","score":66.72},{"place":143,"model":"trillama-8b","company":"senseable","family":"Llama","version":"Llama 3","score":66.63},{"place":144,"model":"mistral-7b-openorca","company":"open-orca","family":"OpenOrca","version":"OpenOrca","score":66.55},{"place":145,"model":"neuralhermes-2.5-mistral-7b","company":"mlabonne","family":"Hermes","version":"NeuralHermes 2.5","score":65.86},{"place":146,"model":"snorkel-mistral-pairrm-dpo","company":"snorkelai","family":"Snorkel","version":"Snorkel Mistral","score":65.83},{"place":147,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":65.8},{"place":148,"model":"nanbeige2-8b-chat","company":"nanbeige","family":"Nanbeige","version":"Nanbeige2","score":65.17},{"place":149,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":64.97},{"place":150,"model":"neural-chat-7b-v3-1","company":"intel","family":"Neural-Chat","version":"Neural-Chat v3","score":64.77},{"place":151,"model":"firefly-mixtral-8x7b","company":"yeungnlp","family":"Firefly","version":"Firefly","score":64.36},{"place":152,"model":"wizardlm-13b-v1.2","company":"wizardlm","family":"WizardLM","version":"WizardLM v1.2","score":63.71},{"place":153,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":63.65},{"place":154,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":63.47},{"place":155,"model":"mistral-7b-instruct-v0.3","company":"mistral","family":"Mistral","version":"Mistral 0.3","score":63.15},{"place":156,"model":"una-cybertron-7b-v2","company":"fblgit","family":"Cybertron","version":"UNA-Cybertron v2","score":62.83},{"place":157,"model":"pplx-70b-online","company":"perplexity","family":"pplx","version":"pplx online","score":62.79},{"place":158,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":62.61},{"place":159,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":61.79},{"place":160,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":61.72},{"place":161,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":61.06},{"place":162,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":60.86},{"place":163,"model":"sparsetral-16x7b-v2","company":"serpdotai","family":"Sparsetral","version":"Sparsetral v2","score":59.9},{"place":164,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":59.71},{"place":165,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":59.45},{"place":166,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":59.17},{"place":167,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":58.33},{"place":168,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":58.15},{"place":169,"model":"qwen1.5-moe-a2.7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":58.07},{"place":170,"model":"jan-v1-edge","company":"menlo","family":"Jan","version":"Jan v1","score":57.2},{"place":171,"model":"phi-2-orange","company":"rhysjones","family":"Phi","version":"Phi-2","score":56.94},{"place":172,"model":"zephyr-7b-alpha","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Alpha","score":56.82},{"place":173,"model":"falcon-180b-chat","company":"tii","family":"Falcon","version":"Falcon","score":56.82},{"place":174,"model":"phi-2-psy","company":"vince62s","family":"Phi","version":"Phi-2","score":56.44},{"place":175,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":56.05},{"place":176,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":54.74},{"place":177,"model":"phixtral-2x2.8","company":"mlabonne","family":"Phixtral","version":"Phixtral","score":54.58},{"place":178,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.53},{"place":179,"model":"phi-2-dpo","company":"microsoft","family":"Phi","version":"Phi","score":54.42},{"place":180,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":54.41},{"place":181,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":52.15},{"place":182,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":50.11},{"place":183,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.76},{"place":184,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":49.12},{"place":185,"model":"pplx-7b-online","company":"perplexity","family":"pplx","version":"pplx online","score":48.91},{"place":186,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":36.32},{"place":187,"model":"guanaco-33b","company":"timdettmers","family":"Guanaco","version":"Guanaco-33B","score":36.11},{"place":188,"model":"nous-capybara-7b-v1","company":"nousresearch","family":"Capybara","version":"Nous-Capybara","score":34.37},{"place":189,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":30},{"place":190,"model":"qwen1.5-4b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":28.75},{"place":191,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":27.6},{"place":192,"model":"vicuna-7b-v1.1","company":"lmsys","family":"Vicuna","version":"Vicuna v1.1","score":26.12},{"place":193,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":24.12},{"place":194,"model":"gemma-2b-it","company":"google","family":"Gemma","version":"Gemma","score":23.26},{"place":195,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":22.65},{"place":196,"model":"koala-7b","company":"berkeley","family":"Koala","version":"Koala","score":21.54},{"place":197,"model":"stablelm-2-zephyr-1.6b","company":"stabilityai","family":"StableLM","version":"StableLM 2","score":15.04}]},{"id":"eqbench-3","name":"EQ-Bench 3","topic":"Emotional intelligence (roleplay)","description":"A benchmark measuring emotional intelligence in challenging roleplays, judged by Sonnet 3.7.","url":"https://eqbench.com/index.html","leaderboard":"https://eqbench.com/index.html","github":"https://github.com/EQ-bench","paper":"https://arxiv.org/abs/2312.06281","metric":"ELO","stars":"21","top_model":"Claude Fable 5","top_percent":2049.7,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":83,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":2049.7},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":2029.8},{"place":3,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1884.3},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1717.4},{"place":5,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1714.1},{"place":6,"model":"hivemind-32b-preview","company":"hivelabsai","family":"Hivemind","version":"Hivemind","score":1618.1},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1576.9},{"place":8,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":1575.1},{"place":9,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1570.2},{"place":10,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":1566.5},{"place":11,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":1562.9},{"place":12,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1562.2},{"place":13,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":1561.2},{"place":14,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":1559.4},{"place":15,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":1558.8},{"place":16,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1554.9},{"place":17,"model":"horizon-alpha","company":"openai","family":"GPT","version":"Horizon","score":1554.4},{"place":18,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":1551},{"place":19,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1545.7},{"place":20,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":1545},{"place":21,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1544.7},{"place":22,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1537.7},{"place":23,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":1526},{"place":24,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1511},{"place":25,"model":"o3","company":"openai","family":"o3","version":"o3","score":1500},{"place":26,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1491.3},{"place":27,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":1488.2},{"place":28,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1454.8},{"place":29,"model":"hermes-4-405b","company":"nousresearch","family":"Hermes","version":"Hermes 4","score":1438.1},{"place":30,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1434.1},{"place":31,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1430.6},{"place":32,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":1428.3},{"place":33,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1413.1},{"place":34,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1399.8},{"place":35,"model":"gemini-2.5-pro-preview-03-25","company":"google","family":"Gemini","version":"Gemini 2.5","score":1393.2},{"place":36,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":1393},{"place":37,"model":"chatgpt-4o-latest-20250425","company":"openai","family":"GPT","version":"GPT-4o","score":1389.9},{"place":38,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":1386.5},{"place":39,"model":"hermes-4-405b","company":"nousresearch","family":"Hermes","version":"Hermes 4","score":1361.4},{"place":40,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1361.2},{"place":41,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":1349},{"place":42,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":1342},{"place":43,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1297.4},{"place":44,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":1277.6},{"place":45,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1276.9},{"place":46,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1276.3},{"place":47,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1261.8},{"place":48,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1242.9},{"place":49,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":1232.8},{"place":50,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1230.6},{"place":51,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1213.6},{"place":52,"model":"gemini-2.5-pro-preview-05-06","company":"google","family":"Gemini","version":"Gemini 2.5","score":1208.5},{"place":53,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":1184.6},{"place":54,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":1179.5},{"place":55,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":1167.7},{"place":56,"model":"gemini-2.5-flash-preview-04-17","company":"google","family":"Gemini","version":"Gemini 2.5","score":1164.5},{"place":57,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":1149.8},{"place":58,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":1147.8},{"place":59,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1111.6},{"place":60,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":1099.3},{"place":61,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1093.9},{"place":62,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":1083},{"place":63,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1082.2},{"place":64,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1080.8},{"place":65,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1075.8},{"place":66,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":1071.6},{"place":67,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":1064.5},{"place":68,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":1053.3},{"place":69,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":1047.5},{"place":70,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1043.3},{"place":71,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":1029.4},{"place":72,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":977.2},{"place":73,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":956},{"place":74,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":950.7},{"place":75,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":910.9},{"place":76,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":868.2},{"place":77,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":865.5},{"place":78,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":851.5},{"place":79,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":845.6},{"place":80,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":806.8},{"place":81,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":801.7},{"place":82,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":799},{"place":83,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":783.6},{"place":84,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":675},{"place":85,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":608.2},{"place":86,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":577.6},{"place":87,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":554.3},{"place":88,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":200}]},{"id":"eqbench-3-rubric","name":"EQ-Bench 3 (Rubric)","topic":"Emotional intelligence (roleplay)","description":"EQ-Bench 3 rubric score (0-100) for emotional intelligence in challenging roleplays; the Elo variant is eqbench-3.","url":"https://eqbench.com/eqbench3.html","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 E4B IT","top_percent":41.17,"top_model_id":"gemma-4-e4b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 E4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.17},{"place":2,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":39.77},{"place":3,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":39.4},{"place":4,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":38.15},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.92},{"place":6,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.07},{"place":7,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":19.45},{"place":8,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":19.31}]},{"id":"erqa","name":"ERQA","topic":"Spatial reasoning","description":"Spatial recognition and reasoning QA benchmark (ERQA).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Glimpse","top_percent":83.75,"top_model_id":"glimpse","top_generation":"Glimpse","top_model_base":"Glimpse","top_model_family":"Glimpse","top_company":"elorian","top_open_source":0,"lower_is_better":false,"bench_models":114,"total_models":3854,"placements":[{"place":1,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":83.75},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":83.75},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":82.45},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":82.2},{"place":5,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":81.2},{"place":6,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":77.8},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":75.8},{"place":8,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":72.3},{"place":9,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":72.3},{"place":10,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":72},{"place":11,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.5},{"place":12,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":71.3},{"place":13,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":71},{"place":14,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":71},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.8},{"place":16,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.5},{"place":17,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.2},{"place":18,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70},{"place":19,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":70},{"place":20,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":69.8},{"place":21,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":69.4},{"place":22,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":68.5},{"place":23,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":68},{"place":24,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":67.8},{"place":25,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.5},{"place":26,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":66},{"place":27,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":65.8},{"place":28,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":65.8},{"place":29,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":30,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":65.7},{"place":31,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.5},{"place":32,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":65.4},{"place":33,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.8},{"place":34,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":64.7},{"place":35,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":64.5},{"place":36,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":64.5},{"place":37,"model":"o3","company":"openai","family":"o3","version":"o3","score":64},{"place":38,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62.5},{"place":39,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62},{"place":40,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":61.8},{"place":41,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":61.5},{"place":42,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":60.8},{"place":43,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":60.8},{"place":44,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":60.7},{"place":45,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.5},{"place":46,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60},{"place":47,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":59.8},{"place":48,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":59.8},{"place":49,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":59},{"place":50,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":58.8},{"place":51,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.5},{"place":52,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57.5},{"place":53,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":57.3},{"place":54,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":57.2},{"place":55,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":56.5},{"place":56,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":56.3},{"place":57,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":56},{"place":58,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.5},{"place":59,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.3},{"place":60,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":54.8},{"place":61,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":54.8},{"place":62,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":54.5},{"place":63,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":54.1},{"place":64,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54},{"place":65,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":54},{"place":66,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54},{"place":67,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":53.7},{"place":68,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":52.8},{"place":69,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.5},{"place":70,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.5},{"place":71,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":52.5},{"place":72,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":51.6},{"place":73,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":51},{"place":74,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.3},{"place":75,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":50.1},{"place":76,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":50},{"place":77,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":50},{"place":78,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":49.8},{"place":79,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.8},{"place":80,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":48.5},{"place":81,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":48},{"place":82,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":47.75},{"place":83,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":47.5},{"place":84,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.3},{"place":85,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.3},{"place":86,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":47},{"place":87,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":47},{"place":88,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":47},{"place":89,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":46.8},{"place":90,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":46.8},{"place":91,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":46.8},{"place":92,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":46.8},{"place":93,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.5},{"place":94,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":46.5},{"place":95,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":46.3},{"place":96,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":46.3},{"place":97,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":46.3},{"place":98,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.25},{"place":99,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":46},{"place":100,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":46},{"place":101,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":46},{"place":102,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":45.8},{"place":103,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.8},{"place":104,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":45.8},{"place":105,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":45.8},{"place":106,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.3},{"place":107,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":45.3},{"place":108,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":45.3},{"place":109,"model":"cosmos-reason2-32b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":45.25},{"place":110,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":45},{"place":111,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.8},{"place":112,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":44.8},{"place":113,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.6},{"place":114,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":44.5},{"place":115,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.3},{"place":116,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":44.3},{"place":117,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":44},{"place":118,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44},{"place":119,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":44},{"place":120,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.8},{"place":121,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":43.3},{"place":122,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":43.25},{"place":123,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43},{"place":124,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":43},{"place":125,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.5},{"place":126,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":42.3},{"place":127,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":42.3},{"place":128,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":42.25},{"place":129,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":42},{"place":130,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":41.8},{"place":131,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.8},{"place":132,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.8},{"place":133,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.5},{"place":134,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.5},{"place":135,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.3},{"place":136,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":41.25},{"place":137,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":41},{"place":138,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40.8},{"place":139,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":40.5},{"place":140,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":39.8},{"place":141,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":39.8},{"place":142,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":39.75},{"place":143,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":39.5},{"place":144,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":39.3},{"place":145,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":38.5},{"place":146,"model":"cosmos-reason2-2b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":37.75},{"place":147,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":37.75},{"place":148,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":37.5},{"place":149,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":37},{"place":150,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":36.5},{"place":151,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":36.3},{"place":152,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":36},{"place":153,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":35.2},{"place":154,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.5},{"place":155,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.2},{"place":156,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.3},{"place":157,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":27.5}]},{"id":"erqa-plus","name":"ERQA-PLUS","topic":"Embodied reasoning","description":"Extended Embodied Reasoning QA benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.6 Flash","top_percent":92.2,"top_model_id":"gemini-3.6-flash","top_generation":"Gemini 3.6","top_model_base":"Gemini 3.6 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":92.2},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.3},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":86.1},{"place":4,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":85.2},{"place":5,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":83.6},{"place":6,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":83.5},{"place":7,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.5},{"place":8,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":82.2},{"place":9,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":81.4},{"place":10,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":81.1},{"place":11,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":81.1},{"place":12,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":80.7},{"place":13,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":79.2}]},{"id":"et-bench","name":"E.T. Bench","topic":"Video event understanding","description":"E.T. Bench: event-level and time-sensitive video understanding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Glimpse","top_percent":63.55,"top_model_id":"glimpse","top_generation":"Glimpse","top_model_base":"Glimpse","top_model_family":"Glimpse","top_company":"elorian","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":63.55},{"place":2,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":63.45},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":59.79}]},{"id":"evalperf","name":"EvalPerf","topic":"Code evaluation performance","description":"Measures performance of LLM code evaluation, including runtime, memory, and efficiency metrics.","url":"https://evalplus.github.io/evalperf.html","leaderboard":"https://evalplus.github.io/evalperf.html","github":"https://github.com/evalplus/evalplus","paper":"https://openreview.net/forum?id=IBCBMeAhmC","metric":"percent","stars":"","top_model":"GPT-4o (2024-08-06)","top_percent":100,"top_model_id":"gpt-4o-2024-08-06","top_generation":"GPT-4o","top_model_base":"GPT-4o","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":34,"total_models":3854,"placements":[{"place":1,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":100},{"place":2,"model":"deepseek-chat-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":97},{"place":3,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":93.9},{"place":4,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":90.9},{"place":5,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":87.9},{"place":6,"model":"o1-mini-2024-09-12-high","company":"openai","family":"o1","version":"o1","score":84.8},{"place":7,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":81.8},{"place":8,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":78.8},{"place":9,"model":"deepseek-chat-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":75.8},{"place":10,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.7},{"place":11,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":69.7},{"place":12,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.7},{"place":13,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.6},{"place":14,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":57.6},{"place":15,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":57.6},{"place":16,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":54.5},{"place":17,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":54.5},{"place":18,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":51.5},{"place":19,"model":"mistral-small-instruct-2409","company":"mistral","family":"Mistral","version":"Mistral","score":42.4},{"place":20,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":39.4},{"place":21,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.4},{"place":22,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36.4},{"place":23,"model":"grok-beta","company":"xai","family":"Grok","version":"Grok","score":33.3},{"place":24,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":30.3},{"place":25,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":27.3},{"place":26,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":24.2},{"place":27,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":24.2},{"place":28,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":21.2},{"place":29,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":15.2},{"place":30,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":12.1},{"place":31,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":9.1},{"place":32,"model":"llama-3.1-nemotron-70b-instruct-hf","company":"nvidia","family":"Llama","version":"Llama 3.1","score":6.1},{"place":33,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":3},{"place":34,"model":"meta-llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":0}]},{"id":"evalplus","name":"EvalPlus","topic":"Code generation","description":"Aggregated code evaluation suite from EvalPlus.","url":"https://github.com/evalplus/evalplus","leaderboard":"https://evalplus.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"1577","top_model":"o1 Mini","top_percent":89,"top_model_id":"o1-mini","top_generation":"o1","top_model_base":"o1 Mini","top_model_family":"o1","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":173,"total_models":3854,"placements":[{"place":1,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":89},{"place":2,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":89},{"place":3,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":89},{"place":4,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":89},{"place":5,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":87.2},{"place":6,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.2},{"place":7,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":87.2},{"place":8,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.6},{"place":9,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":86.6},{"place":10,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":86.6},{"place":11,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":83.5},{"place":12,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":83.5},{"place":13,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":83.5},{"place":14,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":82.3},{"place":15,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81.7},{"place":16,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81.7},{"place":17,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":81.7},{"place":18,"model":"grok-beta","company":"xai","family":"Grok","version":"Grok","score":80.5},{"place":19,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":80.3},{"place":20,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":79.3},{"place":21,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":79.3},{"place":22,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":79},{"place":23,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":78.7},{"place":24,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":78.4},{"place":25,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":78.1},{"place":26,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":77.6},{"place":27,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":77.4},{"place":28,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":77.4},{"place":29,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":76.2},{"place":30,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":75.6},{"place":31,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":75.2},{"place":32,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":75},{"place":33,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":74.1},{"place":34,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":73.8},{"place":35,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":73.8},{"place":36,"model":"opencodeinterpreter-ds-33b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":73.8},{"place":37,"model":"wizardcoder-33b-v1.1","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.1","score":73.2},{"place":38,"model":"artigenz-coder-ds-6.7b","company":"artigenz","family":"Artigenz-Coder-DS-6.7B","version":"Artigenz Coder DS","score":72.6},{"place":39,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.23},{"place":40,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":72.22},{"place":41,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.05},{"place":42,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":72},{"place":43,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":72},{"place":44,"model":"opencodeinterpreter-ds-6.7b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":72},{"place":45,"model":"speechless-codellama-34b-v2.0","company":"speechless","family":"speechless-codellama-34B-v2.0","version":"speechless-codellama-34B-v2.0","score":72},{"place":46,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.8},{"place":47,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":71.6},{"place":48,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.45},{"place":49,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":71.3},{"place":50,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":71.3},{"place":51,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":71.3},{"place":52,"model":"starchat2-15b-v0.1","company":"huggingface","family":"starchat2-15b-v0.1","version":"starchat2-15b-v0.1","score":71.3},{"place":53,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":70.7},{"place":54,"model":"code-millenials-34b","company":"code","family":"code-millenials-34B","version":"code-millenials-34B","score":70.7},{"place":55,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":70.3},{"place":56,"model":"databricks-dbrx-instruct","company":"databricks","family":"databricks/dbrx-instruct","version":"databricks/dbrx-instruct","score":70.1},{"place":57,"model":"wavecoder-ultra-6.7b","company":"wavecoder","family":"WaveCoder-Ultra-6.7B","version":"WaveCoder-Ultra-6.7B","score":69.5},{"place":58,"model":"xwincoder-34b","company":"xwin","family":"XwinCoder-34B","version":"XwinCoder-34B","score":69.5},{"place":59,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.4},{"place":60,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":68.9},{"place":61,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":68.9},{"place":62,"model":"magicoder-s-cl-7b","company":"magicoder","family":"Magicoder-S-CL-7B","version":"Magicoder-S-CL-7B","score":67.7},{"place":63,"model":"openchat-3.5-7b-0106","company":"openchat","family":"OpenChat-3.5-7B-0106","version":"OpenChat-3.5-7B-0106","score":67.7},{"place":64,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.3},{"place":65,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":67.1},{"place":66,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.9},{"place":67,"model":"gpt-3.5-may-2023","company":"openai","family":"GPT","version":"GPT-3.5","score":66.5},{"place":68,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":65.9},{"place":69,"model":"whiterabbitneo-33b-v1","company":"whiterabbit","family":"WhiteRabbitNeo-33B-v1","version":"WhiteRabbitNeo-33B-v1","score":65.9},{"place":70,"model":"speechless-coder-ds-6.7b","company":"speechless","family":"speechless-coder-ds-6.7B","version":"speechless-coder-ds-6.7B","score":65.9},{"place":71,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":65.6},{"place":72,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":65.5},{"place":73,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":65.4},{"place":74,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":64.9},{"place":75,"model":"wizardcoder-python-34b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":64.6},{"place":76,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":64},{"place":77,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":63.6},{"place":78,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":62.8},{"place":79,"model":"speechless-starcoder2-15b","company":"bigcode","family":"speechless-starcoder2-15b","version":"speechless-starcoder2-15b","score":62.8},{"place":80,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":62.2},{"place":81,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":61.6},{"place":82,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":61},{"place":83,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":60.9},{"place":84,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.4},{"place":85,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":60.4},{"place":86,"model":"code-290k-6.7b-instruct","company":"code","family":"Code","version":"Code 290k","score":59.7},{"place":87,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":59.1},{"place":88,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":59.1},{"place":89,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":57.7},{"place":90,"model":"dolphin-2.6-mixtral-8x7b","company":"mistral","family":"dolphin-2.6-mixtral-8x7b","version":"dolphin-2.6-mixtral-8x7b","score":57.3},{"place":91,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":57.2},{"place":92,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":56.7},{"place":93,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":56.7},{"place":94,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":55.5},{"place":95,"model":"coda-1.7b-instruct","company":"salesforce","family":"CoDA","version":"CoDA","score":55.4},{"place":96,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":55},{"place":97,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":54.9},{"place":98,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":54.8},{"place":99,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":54.2},{"place":100,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":54.1},{"place":101,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":53.7},{"place":102,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":52.9},{"place":103,"model":"code-13b","company":"code","family":"Code-13B","version":"Code-13B","score":52.4},{"place":104,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":51.9},{"place":105,"model":"codegemma-7b-it","company":"google","family":"Codegemma","version":"Codegemma","score":51.8},{"place":106,"model":"speechless-starcoder2-7b","company":"bigcode","family":"speechless-starcoder2-7b","version":"speechless-starcoder2-7b","score":51.8},{"place":107,"model":"codellama-70b","company":"meta","family":"CodeLlama","version":"CodeLlama","score":50.6},{"place":108,"model":"wizardcoder-15b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":50.6},{"place":109,"model":"claude-instant-1-mar-2024","company":"anthropic","family":"claude-instant-1","version":"claude-instant-1 (Mar 2024)","score":50.6},{"place":110,"model":"speechless-coding-7b-16k-tora","company":"speechless","family":"speechless-coding-7B-16k-tora","version":"speechless-coding-7B-16k-tora","score":50.6},{"place":111,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":50.4},{"place":112,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":50.3},{"place":113,"model":"code-33b","company":"code","family":"Code-33B","version":"Code-33B","score":49.4},{"place":114,"model":"openhermes-2.5-code-290k-13b","company":"openhermes","family":"OpenHermes-2.5-Code-290k-13B","version":"OpenHermes-2.5-Code-290k-13B","score":48.8},{"place":115,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":48.5},{"place":116,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":46.4},{"place":117,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":45.7},{"place":118,"model":"wizardcoder-python-7b-v1.0","company":"microsoft","family":"WizardCoder-Python-7B-V1.0","version":"WizardCoder-Python-7B-V1.0","score":45.1},{"place":119,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":45.1},{"place":120,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":44.8},{"place":121,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":44.5},{"place":122,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":43.9},{"place":123,"model":"mistral-codealpaca-7b","company":"mistral","family":"Mistral","version":"Mistral Codealpaca","score":42.1},{"place":124,"model":"mistralhermes-codepro-7b-v1","company":"mistral","family":"MistralHermes","version":"MistralHermes CodePro v1","score":42.1},{"place":125,"model":"codegemma-7b","company":"google","family":"Codegemma","version":"codegemma-7b","score":41.5},{"place":126,"model":"speechless-code-mistral-7b-v1.0","company":"speechless","family":"speechless-code-mistral-7B-v1.0","version":"speechless-code-mistral-7B-v1.0","score":41.5},{"place":127,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":40.3},{"place":128,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":40},{"place":129,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.6},{"place":130,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":39.6},{"place":131,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":39.6},{"place":132,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":38.4},{"place":133,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":37.8},{"place":134,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":37.2},{"place":135,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":36.4},{"place":136,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":36},{"place":137,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":35.4},{"place":138,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":35.4},{"place":139,"model":"coda-1.7b-base","company":"salesforce","family":"CoDA","version":"CoDA","score":34.9},{"place":140,"model":"xdan-l1-chat-rl-v1-7b","company":"xdan","family":"xDAN-L1-Chat-RL-v1-7B","version":"xDAN-L1-Chat-RL-v1-7B","score":32.9},{"place":141,"model":"python-code-13b","company":"python","family":"Python-Code-13B","version":"Python-Code-13B","score":30.5},{"place":142,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":30.2},{"place":143,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":29.9},{"place":144,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":29.3},{"place":145,"model":"starcoder-15b","company":"bigcode","family":"StarCoder-15B","version":"StarCoder","score":29.3},{"place":146,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":28.7},{"place":147,"model":"codegen-16b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":28},{"place":148,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":27.4},{"place":149,"model":"codet5plus-16b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":26.8},{"place":150,"model":"codegen-6b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":25.6},{"place":151,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":25.6},{"place":152,"model":"stablecode-3b","company":"stability","family":"StableCode","version":"StableCode","score":25.6},{"place":153,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":25},{"place":154,"model":"codet5plus-6b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":24.4},{"place":155,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":23.8},{"place":156,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":23.2},{"place":157,"model":"codegen-2b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":22.6},{"place":158,"model":"codet5-2b","company":"salesforce","family":"CodeT5+-2B","version":"CodeT5+-2B","score":22},{"place":159,"model":"starcoderbase-7b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":21.3},{"place":160,"model":"codegemma-2b","company":"google","family":"Codegemma","version":"codegemma-2b","score":20.7},{"place":161,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":20.7},{"place":162,"model":"codegen2-7b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":17.7},{"place":163,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":17.7},{"place":164,"model":"codegen2-16b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":16.5},{"place":165,"model":"starcoderbase-3b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":15.9},{"place":166,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":15.9},{"place":167,"model":"gemma-2b-it","company":"google","family":"Gemma","version":"Gemma","score":15.2},{"place":168,"model":"santacoder-1.1b","company":"bigcode","family":"SantaCoder","version":"SantaCoder","score":14},{"place":169,"model":"codegen2-3b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":12.8},{"place":170,"model":"incoder-6.7b","company":"ai21","family":"InCoder","version":"InCoder","score":12.2},{"place":171,"model":"starcoderbase-1b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":12.2},{"place":172,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":11.6},{"place":173,"model":"gpt-j-6b","company":"openai","family":"GPT","version":"GPT-J","score":11},{"place":174,"model":"incoder-1.3b","company":"ai21","family":"InCoder","version":"InCoder","score":11},{"place":175,"model":"codegen2-1b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":9.1},{"place":176,"model":"gpt-neo-2.7b","company":"openai","family":"GPT","version":"GPT-Neo","score":6.7},{"place":177,"model":"polycoder-2.7b","company":"cmu","family":"PolyCoder-2.7B","version":"PolyCoder-2.7B","score":6.1},{"place":178,"model":"stablelm-7b","company":"stabilityai","family":"StableLM-7B","version":"StableLM-7B","score":2.4},{"place":179,"model":"zyte-1b","company":"zysecai","family":"Zyte","version":"Zyte","score":1.8}]},{"id":"evg","name":"EVG","topic":"Document OCR","description":"EVG document OCR benchmark evaluating recognition accuracy and layout extraction.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Dolphin 1.5","top_percent":2.98,"top_model_id":"dolphin-1.5","top_generation":"Dolphin","top_model_base":"Dolphin 1.5","top_model_family":"Dolphin","top_company":"bytedance","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"dolphin-1.5","company":"bytedance","family":"Dolphin","version":"Dolphin","score":2.98},{"place":2,"model":"dolphin","company":"bytedance","family":"Dolphin","version":"Dolphin","score":4.24}]},{"id":"execute","name":"EXECUTE","topic":"Multilingual character tasks","description":"Multilingual character-level evaluation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Bolmo 7B","top_percent":71.6,"top_model_id":"bolmo-7b","top_generation":"Bolmo 7B","top_model_base":"Bolmo 7B","top_model_family":"Bolmo","top_company":"allenai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"bolmo-7b","company":"allenai","family":"Bolmo","version":"Bolmo 7B","score":71.6},{"place":2,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":55.1},{"place":3,"model":"blt-7b","company":"meta","family":"BLT","version":"BLT 7B","score":46.3},{"place":4,"model":"evabyte-6.5b","company":"hku","family":"EvaByte","version":"EvaByte 6.5B","score":43.8},{"place":5,"model":"tfree-hat-pretrained-7b-base","company":"alephalpha","family":"TFree","version":"TFree Hat","score":41.6}]},{"id":"expertfactsqa-law","name":"ExpertFactsQA Law","topic":"Expert knowledge (law)","description":"Yandex expert-written factual QA benchmark, law (hard) subset.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":49.6,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":49.6},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40.5},{"place":3,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.9},{"place":4,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":24.3},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":22.5}]},{"id":"expertfactsqa-medicine","name":"ExpertFactsQA Medicine","topic":"Expert knowledge (medicine)","description":"Yandex expert-written factual QA benchmark, medicine subset.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":63.6,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":63.6},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":60.7},{"place":3,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":4,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":50.6},{"place":5,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":42.3}]},{"id":"exploitbench","name":"ExploitBench","topic":"Cybersecurity","description":"Developing V8 vulnerabilities into increasingly capable exploits (capability coverage).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":100,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.7},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":97.1},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":81.7},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":78.5},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":78},{"place":7,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":78},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":76.5},{"place":9,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":74.2},{"place":10,"model":"gpt-5.5-cyber","company":"openai","family":"GPT","version":"GPT-5.5","score":73.9},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.5},{"place":12,"model":"gpt-5.6-cyber","company":"openai","family":"GPT","version":"GPT-5.6","score":73},{"place":13,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70},{"place":14,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":69},{"place":15,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":54.4},{"place":16,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":52.9},{"place":17,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":47.9},{"place":18,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":47.9},{"place":19,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":43.4},{"place":20,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":40},{"place":21,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":34},{"place":22,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":33.2},{"place":23,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":32.2},{"place":24,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":28.8},{"place":25,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":25.3},{"place":26,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":24.4},{"place":27,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":16.6}]},{"id":"exploitbench-2026-jun-aug","name":"ExploitBench (Jun-Aug 2026)","topic":"Cybersecurity","description":"ExploitBench restricted to vulnerabilities disclosed June-August 2026, after model training cutoffs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":39,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":39},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":5.5}]},{"id":"exploitgym","name":"ExploitGym","topic":"Cybersecurity","description":"UC Berkeley-led benchmark: agents turn real known vulnerabilities into working exploits achieving arbitrary code execution.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":42.4,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":42.4},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":35.1},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":33.7},{"place":4,"model":"gpt-5.6-cyber","company":"openai","family":"GPT","version":"GPT-5.6","score":32.1},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":30.8},{"place":6,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":30.4},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":30.3},{"place":8,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":28.4},{"place":9,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":23.2},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":22.1},{"place":11,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":22.1},{"place":12,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":22},{"place":13,"model":"gpt-5.5-cyber","company":"openai","family":"GPT","version":"GPT-5.5","score":21.2},{"place":14,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":17.8},{"place":15,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":15.3},{"place":16,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":15.1},{"place":17,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":15},{"place":18,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":12.4},{"place":19,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":11.6},{"place":20,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":6},{"place":21,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":5.4},{"place":22,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1.8},{"place":23,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":0.2}]},{"id":"exploitgym-honeypot","name":"ExploitGym-Honeypot","topic":"Safety","description":"ExploitGym honeypot variant measuring how often agents take bait out of scope (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":8.9},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":48.2},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":49.5}]},{"id":"facts-benchmark-suite","name":"FACTS Benchmark Suite","topic":"Held out internal grounding, parametric, MM, and search retrieval benchmarks","description":"Comprehensive factuality benchmark suite covering held-out internal grounding, parametric knowledge, multimodal understanding, and search retrieval benchmarks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":70.5,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.5},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.4},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":61.9},{"place":4,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":61.4},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":50.8},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.4},{"place":7,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":50.4},{"place":8,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":48.9},{"place":9,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":42.1},{"place":10,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":40.6},{"place":11,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":33.7},{"place":12,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":33.7},{"place":13,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":18.6},{"place":14,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":17.9}]},{"id":"facts-grounding","name":"FACTS Grounding","topic":"Grounding / factuality","description":"Grounded factuality benchmark evaluating model alignment with source facts.","url":"https://goo.gle/FACTS_paper","leaderboard":"https://www.kaggle.com/benchmarks/google/facts-grounding","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi K2 Instruct","top_percent":88.5,"top_model_id":"kimi-k2-instruct","top_generation":"Kimi K2","top_model_base":"Kimi K2","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":81,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":88.5},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.8},{"place":3,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.6},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":85.22},{"place":5,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":84.6},{"place":6,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":83.6},{"place":7,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":82.9},{"place":8,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":82.8},{"place":9,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":82.42},{"place":10,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":81.98},{"place":11,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.88},{"place":12,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.67},{"place":13,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":80},{"place":14,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":79.2},{"place":15,"model":"jamba-mini-1.7","company":"ai21","family":"Jamba","version":"Jamba Mini","score":79},{"place":16,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":78.63},{"place":17,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":76.2},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":76.19},{"place":19,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":75.8},{"place":20,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":75.8},{"place":21,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":75.54},{"place":22,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":74.9},{"place":23,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":74.9},{"place":24,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":74.52},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.29},{"place":26,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":73.24},{"place":27,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":73.09},{"place":28,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":72.7},{"place":29,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":72.51},{"place":30,"model":"llama-3-glm-v2","company":"contextual-ai","family":"Llama","version":"Llama 3","score":71.76},{"place":31,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":71.21},{"place":32,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":71.2},{"place":33,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":70.29},{"place":34,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":70.1},{"place":35,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":70.1},{"place":36,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.98},{"place":37,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.68},{"place":38,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":69.63},{"place":39,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":68.75},{"place":40,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.5},{"place":41,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":68.46},{"place":42,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":68.3},{"place":43,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":66.55},{"place":44,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":65.83},{"place":45,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":65.67},{"place":46,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":62.4},{"place":47,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.07},{"place":48,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":62},{"place":49,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.77},{"place":50,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":61.73},{"place":51,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":58.98},{"place":52,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.73},{"place":53,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":58.33},{"place":54,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":58.3},{"place":55,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":57.42},{"place":56,"model":"jamba2-mini","company":"ai21","family":"Jamba","version":"Jamba2","score":57},{"place":57,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":56.37},{"place":58,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":56.24},{"place":59,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":56.08},{"place":60,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":55.99},{"place":61,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":54.91},{"place":62,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":54.77},{"place":63,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":54.74},{"place":64,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54},{"place":65,"model":"jamba2-3b","company":"ai21","family":"Jamba","version":"Jamba2","score":54},{"place":66,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54},{"place":67,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":50.03},{"place":68,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":49.74},{"place":69,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":49},{"place":70,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.23},{"place":71,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":48},{"place":72,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":45.64},{"place":73,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":45.61},{"place":74,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":44},{"place":75,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":43.8},{"place":76,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":43.3},{"place":77,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":43.15},{"place":78,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":40.81},{"place":79,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":38.43},{"place":80,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":36.4},{"place":81,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":36.4},{"place":82,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":36.21},{"place":83,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":33.39},{"place":84,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":30.72},{"place":85,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":29.35},{"place":86,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":23.09}]},{"id":"facts-parametric","name":"FACTS Parametric","topic":"Factuality","description":"FACTS suite parametric-knowledge split: closed-book factoid questions answered without retrieval.","url":"https://www.kaggle.com/benchmarks/google/facts","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Pro Base","top_percent":62.6,"top_model_id":"deepseek-v4-pro-base","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Pro Base","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.6},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":33.9},{"place":3,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":27.1}]},{"id":"factscore","name":"FActScore","topic":"Factuality on open-source prompts","description":"Measures factuality on an open-source prompt suite; scored as 100 - hallucination rate, higher is better.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":99,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":99},{"place":2,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":96.1},{"place":3,"model":"o3","company":"openai","family":"o3","version":"o3","score":94.3},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":92.6},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":92},{"place":6,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":91.9},{"place":7,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91.1},{"place":8,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.6},{"place":9,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.2},{"place":10,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":62.4},{"place":11,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":50.4}]},{"id":"fairpoliticsqa","name":"FairPoliticsQA","topic":"Political fairness (Japanese)","description":"Sakana AI benchmark of balanced, fair answers to Japanese political questions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Sakana Namazu","top_percent":56.3,"top_model_id":"sakana-namazu","top_generation":"Namazu","top_model_base":"Sakana Namazu","top_model_family":"Namazu","top_company":"sakana","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"sakana-namazu","company":"sakana","family":"Namazu","version":"Namazu","score":56.3},{"place":2,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":34.1}]},{"id":"faitheval-inconsistent","name":"FaithEval (Inconsistent)","topic":"Context faithfulness","description":"FaithEval inconsistent-context subset: detecting contradictory evidence in retrieved context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Thomson-1.0-Small","top_percent":97.7,"top_model_id":"thomson-1.0-small","top_generation":"Thomson-1.0","top_model_base":"Thomson 1.0 Small","top_model_family":"Thomson","top_company":"thomsonreuters","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"thomson-1.0-small","company":"thomsonreuters","family":"Thomson","version":"Thomson-1.0","score":97.7},{"place":2,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":96.9},{"place":3,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":96.7}]},{"id":"faithjudge-1-hallu","name":"FaithJudge (1-Hallu.)","topic":"Hallucination detection","description":"FaithJudge hallucination rate with 1-hallucination metric (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Moonlight-Instruct","top_percent":56,"top_model_id":"moonlight-instruct","top_generation":"Moonlight","top_model_base":"Moonlight Instruct","top_model_family":"Moonlight","top_company":"moonshotai","top_open_source":1,"lower_is_better":true,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":56},{"place":2,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":64.2},{"place":3,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.7},{"place":4,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":83},{"place":5,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":83.4},{"place":6,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":91},{"place":7,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":92.6},{"place":8,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":93.2}]},{"id":"faix-agent","name":"Meta Score Agent","topic":"Composite capability index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":100,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":76,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":100},{"place":2,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":90.67},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":60},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.8},{"place":5,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":58.4},{"place":6,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":56},{"place":7,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":54.44},{"place":8,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":52},{"place":9,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":49.33},{"place":10,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":47.67},{"place":11,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.67},{"place":12,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":42.91},{"place":13,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42},{"place":14,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":41.68},{"place":15,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":41.14},{"place":16,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40},{"place":17,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":36},{"place":18,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":31.43},{"place":19,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":29.6},{"place":20,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":24.8},{"place":21,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":24},{"place":22,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":24},{"place":23,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":21.33},{"place":24,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":20},{"place":25,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":19.2},{"place":26,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":18.67},{"place":27,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":18.5},{"place":28,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":16},{"place":29,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":16},{"place":30,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":16},{"place":31,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":16},{"place":32,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":16},{"place":33,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":15},{"place":34,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":14.4},{"place":35,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":13.6},{"place":36,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":13.33},{"place":37,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":12},{"place":38,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":12},{"place":39,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":11.56},{"place":40,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":9.33},{"place":41,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":9},{"place":42,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":8},{"place":43,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":8},{"place":44,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":8},{"place":45,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":8},{"place":46,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":5.33},{"place":47,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":5.14},{"place":48,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":4.92},{"place":49,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":4},{"place":50,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":4},{"place":51,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":4},{"place":52,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":2.86},{"place":53,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":2.67},{"place":54,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":2},{"place":55,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1.6},{"place":56,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":1.33},{"place":57,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":0.8},{"place":58,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":0},{"place":59,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":0},{"place":60,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":61,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":0},{"place":62,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":0},{"place":63,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":0},{"place":64,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":0},{"place":65,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":0},{"place":66,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":0},{"place":67,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":0},{"place":68,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":69,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":70,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":71,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":72,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0},{"place":73,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":74,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":75,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":0},{"place":76,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":0}]},{"id":"faix-code","name":"Meta Score Code","topic":"Composite capability index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":100,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":163,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":100},{"place":2,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.27},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":57},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":53.33},{"place":5,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":49.14},{"place":6,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":43.5},{"place":7,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":42},{"place":8,"model":"o1","company":"openai","family":"o1","version":"o1","score":40.33},{"place":9,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":40},{"place":10,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":37.6},{"place":11,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":35.56},{"place":12,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":35.2},{"place":13,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":31},{"place":14,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":30.67},{"place":15,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":30},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":29.82},{"place":17,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":29.6},{"place":18,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":29.33},{"place":19,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":29.33},{"place":20,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":26.67},{"place":21,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":26.13},{"place":22,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":24},{"place":23,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":23.33},{"place":24,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":22.4},{"place":25,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":22},{"place":26,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":20.8},{"place":27,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":20},{"place":28,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":19},{"place":29,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":18.67},{"place":30,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":18.2},{"place":31,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":17.82},{"place":32,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":17.2},{"place":33,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":17.09},{"place":34,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":16.57},{"place":35,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":16.36},{"place":36,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":16},{"place":37,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":16},{"place":38,"model":"o3-mini-low","company":"openai","family":"o3","version":"o3","score":15},{"place":39,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":14.8},{"place":40,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":14.5},{"place":41,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":14.4},{"place":42,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":14.29},{"place":43,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":13.6},{"place":44,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":13.33},{"place":45,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":13.33},{"place":46,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.07},{"place":47,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":13},{"place":48,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":12.57},{"place":49,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":12.44},{"place":50,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":10.67},{"place":51,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":10.17},{"place":52,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":9.33},{"place":53,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":9.2},{"place":54,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":9.14},{"place":55,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.09},{"place":56,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":8},{"place":57,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":8},{"place":58,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":8},{"place":59,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":8},{"place":60,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":7.5},{"place":61,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":7.33},{"place":62,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":7},{"place":63,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":6.67},{"place":64,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":6.5},{"place":65,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":6.4},{"place":66,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":6},{"place":67,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":6},{"place":68,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":4.57},{"place":69,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":4},{"place":70,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":4},{"place":71,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":3.43},{"place":72,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":2.67},{"place":73,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":2.29},{"place":74,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":2},{"place":75,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":2},{"place":76,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":2},{"place":77,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":2},{"place":78,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2},{"place":79,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":2},{"place":80,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":2},{"place":81,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":1.78},{"place":82,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":1.78},{"place":83,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":1.33},{"place":84,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":1},{"place":85,"model":"deepseek-coder-33b","company":"deepseek","family":"DeepSeek Coder","version":"DeepSeek Coder","score":0.8},{"place":86,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":0.67},{"place":87,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.44},{"place":88,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":0},{"place":89,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":0},{"place":90,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":0},{"place":91,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":0},{"place":92,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":93,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":94,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":0},{"place":95,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":0},{"place":96,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":0},{"place":97,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":0},{"place":98,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":99,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":100,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":101,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":102,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":103,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":104,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":105,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":106,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":107,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":0},{"place":108,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":0},{"place":109,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":0},{"place":110,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":111,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":112,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":113,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":0},{"place":114,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":115,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":116,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":0},{"place":117,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":118,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":0},{"place":119,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":120,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":121,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":122,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":123,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":124,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":0},{"place":125,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":0},{"place":126,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":0},{"place":127,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":0},{"place":128,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":0},{"place":129,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":0},{"place":130,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":0},{"place":131,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":132,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":133,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":134,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":0},{"place":135,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":136,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":137,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":138,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":0},{"place":139,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":0},{"place":140,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":0},{"place":141,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":0},{"place":142,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":0},{"place":143,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":0},{"place":144,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":0},{"place":145,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":0},{"place":146,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":0},{"place":147,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":0},{"place":148,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":0},{"place":149,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":0},{"place":150,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":0},{"place":151,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":0},{"place":152,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":153,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":154,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":155,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":156,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":157,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":158,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":159,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":160,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":0},{"place":161,"model":"qwen3-omni-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":162,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":163,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0}]},{"id":"faix-math","name":"Meta Score Math","topic":"Composite capability index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-VL-235B-A22B Instruct","top_percent":100,"top_model_id":"qwen3-vl-235b-a22b-instruct","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":175,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":100},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":63.33},{"place":3,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":61.33},{"place":4,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":54},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50},{"place":6,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":50},{"place":7,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":48},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.33},{"place":9,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44},{"place":10,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40},{"place":11,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":38.67},{"place":12,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":37},{"place":13,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":36},{"place":14,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":33.33},{"place":15,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":33.33},{"place":16,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":33.33},{"place":17,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":33},{"place":18,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":32},{"place":19,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":31.43},{"place":20,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":30.4},{"place":21,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":30},{"place":22,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":28},{"place":23,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":26},{"place":24,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":24.67},{"place":25,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":22},{"place":26,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":22},{"place":27,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":21.33},{"place":28,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":20.67},{"place":29,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":20},{"place":30,"model":"o3-mini-low","company":"openai","family":"o3","version":"o3","score":20},{"place":31,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":19},{"place":32,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":18.67},{"place":33,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":18},{"place":34,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":18},{"place":35,"model":"o1","company":"openai","family":"o1","version":"o1","score":18},{"place":36,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":18},{"place":37,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":17.33},{"place":38,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":16.8},{"place":39,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":16.67},{"place":40,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":16},{"place":41,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":15},{"place":42,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":15},{"place":43,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":14.4},{"place":44,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":13.33},{"place":45,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":12},{"place":46,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":12},{"place":47,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":12},{"place":48,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":11.56},{"place":49,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":11.2},{"place":50,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":11.2},{"place":51,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.11},{"place":52,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":10},{"place":53,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":10},{"place":54,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":10},{"place":55,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":10},{"place":56,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.2},{"place":57,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":9},{"place":58,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":8},{"place":59,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":8},{"place":60,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":8},{"place":61,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":8},{"place":62,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":8},{"place":63,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":8},{"place":64,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":7.33},{"place":65,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":7},{"place":66,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":6.86},{"place":67,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":6.29},{"place":68,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":6},{"place":69,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":6},{"place":70,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":5.33},{"place":71,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":5.33},{"place":72,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":4.44},{"place":73,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":4},{"place":74,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":4},{"place":75,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":4},{"place":76,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":4},{"place":77,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4},{"place":78,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":3.43},{"place":79,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.43},{"place":80,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":3.2},{"place":81,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":2.67},{"place":82,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":2.67},{"place":83,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.29},{"place":84,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":2},{"place":85,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":2},{"place":86,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":2},{"place":87,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":1.6},{"place":88,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":1.33},{"place":89,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":1.33},{"place":90,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1},{"place":91,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":1},{"place":92,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":0.8},{"place":93,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0.57},{"place":94,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":0},{"place":95,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0},{"place":96,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":0},{"place":97,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":0},{"place":98,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":0},{"place":99,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":100,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":101,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":102,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":103,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":104,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":105,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":106,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":107,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":0},{"place":108,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":0},{"place":109,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":110,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":0},{"place":111,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":112,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":0},{"place":113,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":114,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":0},{"place":115,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":0},{"place":116,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":0},{"place":117,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":0},{"place":118,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":0},{"place":119,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":0},{"place":120,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":121,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":122,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":123,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":0},{"place":124,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":0},{"place":125,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":0},{"place":126,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":0},{"place":127,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":0},{"place":128,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":129,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":130,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":131,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":0},{"place":132,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":0},{"place":133,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":0},{"place":134,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":0},{"place":135,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":136,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":137,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":138,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":0},{"place":139,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":0},{"place":140,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":0},{"place":141,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":0},{"place":142,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":0},{"place":143,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":0},{"place":144,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":0},{"place":145,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":0},{"place":146,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":0},{"place":147,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":0},{"place":148,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":0},{"place":149,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":0},{"place":150,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":0},{"place":151,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":0},{"place":152,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":0},{"place":153,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":0},{"place":154,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":0},{"place":155,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":0},{"place":156,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":0},{"place":157,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":0},{"place":158,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":0},{"place":159,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":160,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":161,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":162,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":163,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":164,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":165,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0},{"place":166,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":167,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":168,"model":"qwen3-omni-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":169,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":170,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":171,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":172,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":0},{"place":173,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":174,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":175,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0}]},{"id":"faix-ocr","name":"Meta Score OCR","topic":"Composite capability index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"o3 (low)","top_percent":80,"top_model_id":"o3-low","top_generation":"o3","top_model_base":"o3","top_model_family":"o3","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":82,"total_models":3854,"placements":[{"place":1,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":80},{"place":2,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.5},{"place":3,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.36},{"place":4,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":37},{"place":5,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":34.67},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.6},{"place":7,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":29.33},{"place":8,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":28},{"place":9,"model":"mimo-vl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":27.43},{"place":10,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.4},{"place":11,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":26.29},{"place":12,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":25},{"place":13,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":24.73},{"place":14,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":21.71},{"place":15,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":20},{"place":16,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":20},{"place":17,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":19},{"place":18,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":15.33},{"place":19,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":14},{"place":20,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":12.8},{"place":21,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":12.57},{"place":22,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":12},{"place":23,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":10.5},{"place":24,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":10},{"place":25,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":9.6},{"place":26,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":6.86},{"place":27,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":6},{"place":28,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":6},{"place":29,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":5.33},{"place":30,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":5.33},{"place":31,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4.36},{"place":32,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":4},{"place":33,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":4},{"place":34,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":4},{"place":35,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":3.64},{"place":36,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":3.27},{"place":37,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":2},{"place":38,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":1.6},{"place":39,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1.33},{"place":40,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":0.73},{"place":41,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":0.67},{"place":42,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":0},{"place":43,"model":"blip-3o-4b","company":"salesforce","family":"BLIP","version":"BLIP-3O","score":0},{"place":44,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":0},{"place":45,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":0},{"place":46,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":0},{"place":47,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":0},{"place":48,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":0},{"place":49,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":0},{"place":50,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":0},{"place":51,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":0},{"place":52,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":0},{"place":53,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":0},{"place":54,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":0},{"place":55,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":56,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":57,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":0},{"place":58,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":0},{"place":59,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":60,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":0},{"place":61,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":0},{"place":62,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":0},{"place":63,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":0},{"place":64,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":0},{"place":65,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":0},{"place":66,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":67,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":0},{"place":68,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":0},{"place":69,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":0},{"place":70,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":0},{"place":71,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":0},{"place":72,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":0},{"place":73,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":0},{"place":74,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":0},{"place":75,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":0},{"place":76,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":0},{"place":77,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":0},{"place":78,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":0},{"place":79,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":0},{"place":80,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":0},{"place":81,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0},{"place":82,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":0}]},{"id":"faix-overall","name":"Meta Score Overall","topic":"Composite capability index","description":"Overall Meta Score across the benchmarks of all Meta Score categories.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":51.74,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":303,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":51.74},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":36},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":30.73},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":29.25},{"place":5,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":28.91},{"place":6,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":28.17},{"place":7,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":25.33},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":24.96},{"place":9,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":24.77},{"place":10,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":23.62},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":22.42},{"place":12,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":21.29},{"place":13,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":20.76},{"place":14,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.16},{"place":15,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":20},{"place":16,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":19.83},{"place":17,"model":"o1","company":"openai","family":"o1","version":"o1","score":19.74},{"place":18,"model":"gpt-o3","company":"openai","family":"o3","version":"o3","score":18.92},{"place":19,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":18.64},{"place":20,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":18.51},{"place":21,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":17.38},{"place":22,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":17.36},{"place":23,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":16.89},{"place":24,"model":"llada2.1-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":16.86},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.66},{"place":26,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":16.05},{"place":27,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":16.04},{"place":28,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":15.91},{"place":29,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":15.9},{"place":30,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":15.56},{"place":31,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":14.86},{"place":32,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":14.58},{"place":33,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":14.46},{"place":34,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":14.09},{"place":35,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":13.91},{"place":36,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":13.84},{"place":37,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":13.48},{"place":38,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":13.11},{"place":39,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":12.83},{"place":40,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":12.7},{"place":41,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":12.57},{"place":42,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":12.51},{"place":43,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":12.24},{"place":44,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":12.22},{"place":45,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":12.12},{"place":46,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":12},{"place":47,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":11.84},{"place":48,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":11.83},{"place":49,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":11.79},{"place":50,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":11.78},{"place":51,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":11.61},{"place":52,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":11.54},{"place":53,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":11.53},{"place":54,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":11.48},{"place":55,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":11.3},{"place":56,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":11.07},{"place":57,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":10.92},{"place":58,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":10.81},{"place":59,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":10.63},{"place":60,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":10.6},{"place":61,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":10.58},{"place":62,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":10.55},{"place":63,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":10.48},{"place":64,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":10.41},{"place":65,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":10.4},{"place":66,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":10.35},{"place":67,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":10.29},{"place":68,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":10.21},{"place":69,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":10.19},{"place":70,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":10.1},{"place":71,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":10},{"place":72,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":9.95},{"place":73,"model":"mimo-vl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":9.91},{"place":74,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":9.78},{"place":75,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":9.71},{"place":76,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":9.64},{"place":77,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":9.62},{"place":78,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":9.6},{"place":79,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":9.31},{"place":80,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":9.22},{"place":81,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":9.02},{"place":82,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":8.94},{"place":83,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.94},{"place":84,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":8.93},{"place":85,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":8.8},{"place":86,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":8.77},{"place":87,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":8.62},{"place":88,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":8.11},{"place":89,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":8},{"place":90,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":7.91},{"place":91,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":7.87},{"place":92,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":7.83},{"place":93,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":7.82},{"place":94,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":7.71},{"place":95,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":7.67},{"place":96,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":7.57},{"place":97,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":7.49},{"place":98,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":7.4},{"place":99,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":7.39},{"place":100,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":7.27},{"place":101,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":7.2},{"place":102,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":7.14},{"place":103,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":6.96},{"place":104,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":6.91},{"place":105,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":6.87},{"place":106,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":6.83},{"place":107,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":6.8},{"place":108,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":6.62},{"place":109,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":6.56},{"place":110,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":6.43},{"place":111,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":6.35},{"place":112,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":6.34},{"place":113,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":6.29},{"place":114,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":6.26},{"place":115,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":6.25},{"place":116,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":6.24},{"place":117,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":6.21},{"place":118,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":6.14},{"place":119,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":6.06},{"place":120,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.92},{"place":121,"model":"ministral-3-14b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":5.91},{"place":122,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.91},{"place":123,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":5.83},{"place":124,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":5.8},{"place":125,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":5.73},{"place":126,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":5.6},{"place":127,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":5.56},{"place":128,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":5.46},{"place":129,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5.33},{"place":130,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":5.25},{"place":131,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":5},{"place":132,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":5},{"place":133,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":5},{"place":134,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":5},{"place":135,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":4.94},{"place":136,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":4.89},{"place":137,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":4.78},{"place":138,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4.67},{"place":139,"model":"ministral-3-8b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":4.57},{"place":140,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":4.46},{"place":141,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":4.44},{"place":142,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.43},{"place":143,"model":"deepseek-chat-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":4.41},{"place":144,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":4.35},{"place":145,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":4.35},{"place":146,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":4.16},{"place":147,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":4.11},{"place":148,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":4},{"place":149,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":4},{"place":150,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":4},{"place":151,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4},{"place":152,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":4},{"place":153,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":3.93},{"place":154,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":3.89},{"place":155,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":3.87},{"place":156,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":3.85},{"place":157,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":3.71},{"place":158,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":3.68},{"place":159,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":3.67},{"place":160,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":3.6},{"place":161,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":3.58},{"place":162,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":3.57},{"place":163,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.56},{"place":164,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":3.56},{"place":165,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":3.52},{"place":166,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":3.48},{"place":167,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":3.43},{"place":168,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.3},{"place":169,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.24},{"place":170,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":3.2},{"place":171,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.08},{"place":172,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":3.06},{"place":173,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":3.04},{"place":174,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":3.02},{"place":175,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":3},{"place":176,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":2.93},{"place":177,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.91},{"place":178,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":2.88},{"place":179,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":2.86},{"place":180,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":2.8},{"place":181,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":2.75},{"place":182,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":2.74},{"place":183,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":2.67},{"place":184,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":2.67},{"place":185,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":2.67},{"place":186,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.67},{"place":187,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":2.53},{"place":188,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":2.48},{"place":189,"model":"qwen3-omni-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.46},{"place":190,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":2.4},{"place":191,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":2.33},{"place":192,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":2.29},{"place":193,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":2.24},{"place":194,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":2.16},{"place":195,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":2.15},{"place":196,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":2.12},{"place":197,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":2.11},{"place":198,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":2.08},{"place":199,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":2.07},{"place":200,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":2},{"place":201,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":2},{"place":202,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":1.95},{"place":203,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":1.9},{"place":204,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":1.85},{"place":205,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":1.74},{"place":206,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":1.71},{"place":207,"model":"exaone-4.5-33b","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":1.67},{"place":208,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":1.58},{"place":209,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":1.57},{"place":210,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":1.57},{"place":211,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":1.54},{"place":212,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1.52},{"place":213,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":1.4},{"place":214,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":1.33},{"place":215,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":1.33},{"place":216,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1.22},{"place":217,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1.09},{"place":218,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1.05},{"place":219,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1},{"place":220,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1},{"place":221,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":0.91},{"place":222,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":0.9},{"place":223,"model":"kimi-vl-a3b-a2b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":0.9},{"place":224,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":0.89},{"place":225,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":0.89},{"place":226,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":0.88},{"place":227,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":0.87},{"place":228,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0.78},{"place":229,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":0.7},{"place":230,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":0.6},{"place":231,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":0.59},{"place":232,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":0.59},{"place":233,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":0.59},{"place":234,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":0.57},{"place":235,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":0.54},{"place":236,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":0.53},{"place":237,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":0.5},{"place":238,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0.46},{"place":239,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":0.42},{"place":240,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":0.39},{"place":241,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":0.35},{"place":242,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":0.33},{"place":243,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.32},{"place":244,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":0.26},{"place":245,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":0.2},{"place":246,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":0.17},{"place":247,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":0.16},{"place":248,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.15},{"place":249,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":0},{"place":250,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":0},{"place":251,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":0},{"place":252,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":253,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":254,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":255,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":0},{"place":256,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":257,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":258,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":259,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":260,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":261,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":262,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":263,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":0},{"place":264,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":0},{"place":265,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":266,"model":"gemma-3n-e2b","company":"google","family":"Gemma","version":"Gemma 3n","score":0},{"place":267,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":0},{"place":268,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":0},{"place":269,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":0},{"place":270,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":0},{"place":271,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":0},{"place":272,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":273,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":274,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":275,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":0},{"place":276,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":0},{"place":277,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":0},{"place":278,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":0},{"place":279,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":0},{"place":280,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":0},{"place":281,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":0},{"place":282,"model":"olmo-2-0425-1b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":0},{"place":283,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":0},{"place":284,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":0},{"place":285,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":0},{"place":286,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":0},{"place":287,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":0},{"place":288,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":289,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":290,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":291,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":292,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":0},{"place":293,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":0},{"place":294,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":295,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":296,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0},{"place":297,"model":"seed-coder-8b-base","company":"bytedance","family":"Seed","version":"Seed Coder","score":0},{"place":298,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":299,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":300,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":0},{"place":301,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":0},{"place":302,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":0},{"place":303,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":0}]},{"id":"faix-safety","name":"Meta Score Safety","topic":"Composite safety index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Granite 3.3 8B Instruct","top_percent":70,"top_model_id":"granite-3.3-8b-instruct","top_generation":"Granite 3.3","top_model_base":"Granite 3.3 8B","top_model_family":"Granite","top_company":"IBM","top_open_source":1,"lower_is_better":false,"bench_models":53,"total_models":3854,"placements":[{"place":1,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":70},{"place":2,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":68},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66},{"place":4,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":60},{"place":5,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":59},{"place":6,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":56},{"place":7,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":50},{"place":8,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":48},{"place":9,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":45.33},{"place":10,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":36},{"place":11,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":36},{"place":12,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36},{"place":13,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":33},{"place":14,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":33},{"place":15,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":30},{"place":16,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":28},{"place":17,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":26.4},{"place":18,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":24},{"place":19,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":24},{"place":20,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":24},{"place":21,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":24},{"place":22,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":22.86},{"place":23,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":22.67},{"place":24,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":22},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":20.8},{"place":26,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":20},{"place":27,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":20},{"place":28,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":20},{"place":29,"model":"o3-mini-low","company":"openai","family":"o3","version":"o3","score":20},{"place":30,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":18},{"place":31,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":16},{"place":32,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":13.33},{"place":33,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":13},{"place":34,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":12},{"place":35,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":12},{"place":36,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":12},{"place":37,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":6},{"place":38,"model":"o1","company":"openai","family":"o1","version":"o1","score":4},{"place":39,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.67},{"place":40,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":1.6},{"place":41,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0},{"place":42,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":43,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":44,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":0},{"place":45,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":0},{"place":46,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":0},{"place":47,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":48,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":0},{"place":49,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":50,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":51,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":0},{"place":52,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":0},{"place":53,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":0}]},{"id":"faix-stem","name":"Meta Score STEM","topic":"Composite capability index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-VL-235B-A22B Instruct","top_percent":100,"top_model_id":"qwen3-vl-235b-a22b-instruct","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":226,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":100},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":66.13},{"place":3,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":54},{"place":4,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":50},{"place":5,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":50},{"place":6,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":46},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44},{"place":8,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":42.59},{"place":10,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":40},{"place":11,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":38.86},{"place":12,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":38},{"place":13,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":37},{"place":14,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":36},{"place":15,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":36},{"place":16,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":33.33},{"place":17,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":33.33},{"place":18,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":32},{"place":19,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":32},{"place":20,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":31.43},{"place":21,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":30},{"place":22,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":29.6},{"place":23,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":29.6},{"place":24,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":29},{"place":25,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":27},{"place":26,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":24},{"place":27,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":24},{"place":28,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":23.2},{"place":29,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":22.4},{"place":30,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":21.14},{"place":31,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":20.8},{"place":32,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":20.5},{"place":33,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":20},{"place":34,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":18},{"place":35,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":18},{"place":36,"model":"o1","company":"openai","family":"o1","version":"o1","score":18},{"place":37,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":17.6},{"place":38,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":17.33},{"place":39,"model":"o3-mini-low","company":"openai","family":"o3","version":"o3","score":16.67},{"place":40,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":16.4},{"place":41,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":16.33},{"place":42,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":16},{"place":43,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":15.2},{"place":44,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":15},{"place":45,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":15},{"place":46,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":14.4},{"place":47,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":14.4},{"place":48,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":14.15},{"place":49,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":14},{"place":50,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":13.71},{"place":51,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":13.33},{"place":52,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":13.33},{"place":53,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":12},{"place":54,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":12},{"place":55,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":12},{"place":56,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":10.67},{"place":57,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":10.67},{"place":58,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":10},{"place":59,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":10},{"place":60,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":10},{"place":61,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":9.6},{"place":62,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":9.6},{"place":63,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":9.33},{"place":64,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":9.33},{"place":65,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":9.33},{"place":66,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":9},{"place":67,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":9},{"place":68,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9},{"place":69,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":8.57},{"place":70,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":8.36},{"place":71,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":8},{"place":72,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":8},{"place":73,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":8},{"place":74,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":8},{"place":75,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":8},{"place":76,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":8},{"place":77,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":7.5},{"place":78,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":7.11},{"place":79,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":6.86},{"place":80,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":6.55},{"place":81,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":6.4},{"place":82,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":6},{"place":83,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":6},{"place":84,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":5.71},{"place":85,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":5.33},{"place":86,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":5.14},{"place":87,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":4.8},{"place":88,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":4.57},{"place":89,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":4},{"place":90,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":4},{"place":91,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":4},{"place":92,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":3.64},{"place":93,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.56},{"place":94,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":3.43},{"place":95,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":3.2},{"place":96,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":3.2},{"place":97,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":3},{"place":98,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":2.67},{"place":99,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":2.67},{"place":100,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":2.67},{"place":101,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.67},{"place":102,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":2.5},{"place":103,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":2.29},{"place":104,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":2},{"place":105,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":1.6},{"place":106,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":1.45},{"place":107,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":1.45},{"place":108,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":1.33},{"place":109,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":1.33},{"place":110,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":1.33},{"place":111,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":1},{"place":112,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":0.8},{"place":113,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":0.8},{"place":114,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":0.67},{"place":115,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":0.67},{"place":116,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0.44},{"place":117,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":0},{"place":118,"model":"blip-3o-4b","company":"salesforce","family":"BLIP","version":"BLIP-3O","score":0},{"place":119,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":0},{"place":120,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":0},{"place":121,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":0},{"place":122,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":0},{"place":123,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":0},{"place":124,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":0},{"place":125,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":0},{"place":126,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":0},{"place":127,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":128,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":129,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":0},{"place":130,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":0},{"place":131,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":0},{"place":132,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":0},{"place":133,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":134,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":135,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":136,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":137,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":138,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":139,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":140,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":141,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":0},{"place":142,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":143,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":0},{"place":144,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":0},{"place":145,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":146,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":0},{"place":147,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":0},{"place":148,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":149,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":0},{"place":150,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":0},{"place":151,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":0},{"place":152,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":0},{"place":153,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":0},{"place":154,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":0},{"place":155,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":156,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":157,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":158,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":159,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":0},{"place":160,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":0},{"place":161,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":0},{"place":162,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":0},{"place":163,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":0},{"place":164,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":0},{"place":165,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":0},{"place":166,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":0},{"place":167,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":0},{"place":168,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":0},{"place":169,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":0},{"place":170,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":0},{"place":171,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":0},{"place":172,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":173,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":174,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":0},{"place":175,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":0},{"place":176,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":0},{"place":177,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":178,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":179,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":180,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":181,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":0},{"place":182,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":0},{"place":183,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":0},{"place":184,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":0},{"place":185,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":0},{"place":186,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":0},{"place":187,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":0},{"place":188,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":0},{"place":189,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":0},{"place":190,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":0},{"place":191,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":0},{"place":192,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":0},{"place":193,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":0},{"place":194,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":0},{"place":195,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":0},{"place":196,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":0},{"place":197,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":0},{"place":198,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":0},{"place":199,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":0},{"place":200,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":0},{"place":201,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":0},{"place":202,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":0},{"place":203,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":0},{"place":204,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":205,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":0},{"place":206,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":0},{"place":207,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":208,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":209,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":210,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":211,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":212,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":213,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":0},{"place":214,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0},{"place":215,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0},{"place":216,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":217,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":218,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":219,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":220,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":221,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":0},{"place":222,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":0},{"place":223,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":224,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":225,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":226,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":0}]},{"id":"faix-text","name":"Meta Score Text","topic":"Composite capability index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":85.71,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":197,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.71},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":63},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":58.81},{"place":4,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":48.22},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.03},{"place":6,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":44.57},{"place":7,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":42.86},{"place":9,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":42.31},{"place":10,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42},{"place":11,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":40},{"place":12,"model":"o1","company":"openai","family":"o1","version":"o1","score":38.08},{"place":13,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":35.43},{"place":14,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":30.79},{"place":15,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":30.33},{"place":16,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":30.12},{"place":17,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":29.14},{"place":18,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":28.17},{"place":19,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":28.17},{"place":20,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":27.44},{"place":21,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":27.43},{"place":22,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":27.27},{"place":23,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":24.56},{"place":24,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":24.4},{"place":25,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":24.4},{"place":26,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":24.29},{"place":27,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":23.33},{"place":28,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":21.71},{"place":29,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":21.5},{"place":30,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":21.12},{"place":31,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":20.5},{"place":32,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":20},{"place":33,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":20},{"place":34,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":20},{"place":35,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":20},{"place":36,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":19.08},{"place":37,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":18.75},{"place":38,"model":"o3-mini-low","company":"openai","family":"o3","version":"o3","score":18.17},{"place":39,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":18.12},{"place":40,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":18},{"place":41,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":18},{"place":42,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":18},{"place":43,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":17.68},{"place":44,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":17.33},{"place":45,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":17.25},{"place":46,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.2},{"place":47,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":16.49},{"place":48,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":16.33},{"place":49,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":16.29},{"place":50,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":16.21},{"place":51,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":16},{"place":52,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":15.92},{"place":53,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":15.78},{"place":54,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":15.67},{"place":55,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":15.47},{"place":56,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":15.2},{"place":57,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":14.96},{"place":58,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":14.57},{"place":59,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":14.5},{"place":60,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":14.4},{"place":61,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":14.07},{"place":62,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":13.29},{"place":63,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":13.17},{"place":64,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.1},{"place":65,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":13},{"place":66,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":13},{"place":67,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":12.95},{"place":68,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":12.92},{"place":69,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":12.33},{"place":70,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":12.29},{"place":71,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":12},{"place":72,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":12},{"place":73,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":11.82},{"place":74,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":11.79},{"place":75,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":11.43},{"place":76,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":11.43},{"place":77,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":11.29},{"place":78,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":11.29},{"place":79,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":11.29},{"place":80,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":11.23},{"place":81,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":11},{"place":82,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":10.75},{"place":83,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":10},{"place":84,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":9.78},{"place":85,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":9.6},{"place":86,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":9.33},{"place":87,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":9.23},{"place":88,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":9.05},{"place":89,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":9},{"place":90,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":8.73},{"place":91,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":8.44},{"place":92,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":8.36},{"place":93,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.29},{"place":94,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":7.83},{"place":95,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":7.58},{"place":96,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":7},{"place":97,"model":"qwen3-omni-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":6.91},{"place":98,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":6.77},{"place":99,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":6.67},{"place":100,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":6.55},{"place":101,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":6.5},{"place":102,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":6},{"place":103,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":5.78},{"place":104,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":5.76},{"place":105,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":5.54},{"place":106,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":5.33},{"place":107,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":5},{"place":108,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":4.95},{"place":109,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":4.86},{"place":110,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":4.84},{"place":111,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":4.57},{"place":112,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":4.51},{"place":113,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":4},{"place":114,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":4},{"place":115,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":4},{"place":116,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":4},{"place":117,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":4},{"place":118,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":4},{"place":119,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":3.11},{"place":120,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":3},{"place":121,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":2.91},{"place":122,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.88},{"place":123,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":2.86},{"place":124,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":2.86},{"place":125,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":2.67},{"place":126,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":2.63},{"place":127,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":2.4},{"place":128,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":2.33},{"place":129,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":2.29},{"place":130,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":2.11},{"place":131,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":2},{"place":132,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":2},{"place":133,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":2},{"place":134,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":1.9},{"place":135,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":1.85},{"place":136,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":1.78},{"place":137,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":1.71},{"place":138,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":1.6},{"place":139,"model":"mimo-vl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":1.6},{"place":140,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":1.5},{"place":141,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":1.45},{"place":142,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1.33},{"place":143,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":1.03},{"place":144,"model":"deepseek-coder-33b","company":"deepseek","family":"DeepSeek Coder","version":"DeepSeek Coder","score":1},{"place":145,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":0.86},{"place":146,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":0.76},{"place":147,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0.67},{"place":148,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":0.62},{"place":149,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":0.62},{"place":150,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":0.43},{"place":151,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":0.42},{"place":152,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":0.4},{"place":153,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":0.33},{"place":154,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0.29},{"place":155,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":0.21},{"place":156,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0.13},{"place":157,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":0},{"place":158,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":0},{"place":159,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":160,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":161,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":0},{"place":162,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":0},{"place":163,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":164,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":165,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":166,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":167,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":0},{"place":168,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":169,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":170,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":171,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":0},{"place":172,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":0},{"place":173,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":0},{"place":174,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":0},{"place":175,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":0},{"place":176,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":177,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":178,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":179,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":0},{"place":180,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":0},{"place":181,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":0},{"place":182,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":0},{"place":183,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":0},{"place":184,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":0},{"place":185,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":0},{"place":186,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":0},{"place":187,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":0},{"place":188,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":189,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":190,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":191,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0},{"place":192,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":193,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":194,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":0},{"place":195,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":196,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":197,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0}]},{"id":"faix-visual","name":"Meta Score Visual","topic":"Composite capability index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":100,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":103,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":100},{"place":2,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":88.8},{"place":3,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":74},{"place":4,"model":"grok-4-thinking","company":"xai","family":"Grok","version":"Grok 4","score":70},{"place":5,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":66.67},{"place":6,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66},{"place":7,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.29},{"place":8,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":52},{"place":9,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":49.6},{"place":10,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":48.8},{"place":11,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":46.67},{"place":12,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":46.67},{"place":13,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.09},{"place":14,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.77},{"place":15,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":44.36},{"place":16,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":42.87},{"place":17,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":42.4},{"place":18,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":40.52},{"place":19,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":38.81},{"place":20,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":31.67},{"place":21,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":28},{"place":22,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":27.68},{"place":23,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.67},{"place":24,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":26.55},{"place":25,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":24.4},{"place":26,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":24},{"place":27,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":23.35},{"place":28,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":23.33},{"place":29,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":22.35},{"place":30,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":22},{"place":31,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":21.33},{"place":32,"model":"mimo-vl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":20.53},{"place":33,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":19.69},{"place":34,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":18.67},{"place":35,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":18.22},{"place":36,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":18.06},{"place":37,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":17},{"place":38,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.67},{"place":39,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":15.72},{"place":40,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":15.05},{"place":41,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":14.91},{"place":42,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":14.8},{"place":43,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":14.5},{"place":44,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":12.73},{"place":45,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":12.67},{"place":46,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":11.78},{"place":47,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":11.56},{"place":48,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":11.27},{"place":49,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":10.8},{"place":50,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":10.33},{"place":51,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":10.15},{"place":52,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":9.67},{"place":53,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":9.09},{"place":54,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":9.09},{"place":55,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":9},{"place":56,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":8.33},{"place":57,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":8.1},{"place":58,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":8},{"place":59,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":7.6},{"place":60,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":6.91},{"place":61,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":6.64},{"place":62,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":6.18},{"place":63,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":5.82},{"place":64,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":5.67},{"place":65,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":5.64},{"place":66,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":5.1},{"place":67,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.62},{"place":68,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":4},{"place":69,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":3.88},{"place":70,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":3.69},{"place":71,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":2.91},{"place":72,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":2.91},{"place":73,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":2.5},{"place":74,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":2.4},{"place":75,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":2.4},{"place":76,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":2.15},{"place":77,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":1.6},{"place":78,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0.94},{"place":79,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":0.8},{"place":80,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":0.8},{"place":81,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":0.4},{"place":82,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":0.4},{"place":83,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":0.33},{"place":84,"model":"blip-3o-4b","company":"salesforce","family":"BLIP","version":"BLIP-3O","score":0},{"place":85,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":0},{"place":86,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":0},{"place":87,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":0},{"place":88,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":0},{"place":89,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":0},{"place":90,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":0},{"place":91,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":0},{"place":92,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":0},{"place":93,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":0},{"place":94,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":0},{"place":95,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":0},{"place":96,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":0},{"place":97,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":0},{"place":98,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":0},{"place":99,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":0},{"place":100,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":0},{"place":101,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":0},{"place":102,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":0},{"place":103,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":0},{"place":104,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0}]},{"id":"faix-writing","name":"Meta Score Writing","topic":"Composite capability index","description":"","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-235B-A22B-Instruct-2507","top_percent":60,"top_model_id":"qwen3-235b-a22b-instruct-2507","top_generation":"Qwen3","top_model_base":"Qwen3 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":57.33},{"place":3,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":54},{"place":4,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":48},{"place":5,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":36},{"place":6,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":33.33},{"place":7,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":30},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":29.33},{"place":9,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":24},{"place":10,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":24},{"place":11,"model":"qwen3-omni-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":24},{"place":12,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":16},{"place":13,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":14},{"place":14,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":12},{"place":15,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":8},{"place":16,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":2},{"place":17,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0},{"place":18,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0},{"place":19,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0},{"place":20,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":0},{"place":21,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":0},{"place":22,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":0}]},{"id":"fate-h","name":"FATE-H","topic":"Formal theorem proving (abstract algebra)","description":"FATE-H: graduate-level abstract algebra problems formalized in Lean 4 (100 problems).","url":"https://github.com/frenzymath/FATE","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Leanstral 1.5","top_percent":87,"top_model_id":"leanstral-1.5","top_generation":"Leanstral 1.5","top_model_base":"Leanstral 1.5","top_model_family":"Leanstral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"leanstral-1.5","company":"mistral","family":"Leanstral","version":"Leanstral 1.5","score":87},{"place":2,"model":"seed-prover-1.5-high","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover 1.5","score":80},{"place":3,"model":"axproverbase","company":"axiomatic","family":"Ax-Prover","version":"AxProverBase","score":66},{"place":4,"model":"seed-prover-1.5-agentic","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover 1.5","score":57}]},{"id":"fate-x","name":"FATE-X","topic":"Formal theorem proving (abstract algebra)","description":"FATE-X: PhD-level abstract algebra problems formalized in Lean 4 (100 problems).","url":"https://github.com/frenzymath/FATE","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Leanstral 1.5","top_percent":34,"top_model_id":"leanstral-1.5","top_generation":"Leanstral 1.5","top_model_base":"Leanstral 1.5","top_model_family":"Leanstral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"leanstral-1.5","company":"mistral","family":"Leanstral","version":"Leanstral 1.5","score":34},{"place":2,"model":"seed-prover-1.5-high","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover 1.5","score":33},{"place":3,"model":"axproverbase","company":"axiomatic","family":"Ax-Prover","version":"AxProverBase","score":24},{"place":4,"model":"seed-prover-1.5-agentic","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover 1.5","score":10}]},{"id":"fd-bench-v1-latency","name":"Full-Duplex-Bench V1 Turn-taking Latency","topic":"Full-duplex speech interaction","description":"Full-Duplex-Bench v1 smooth turn-taking latency in seconds (lower is better).","url":"https://github.com/DanielLin94144/Full-Duplex-Bench","leaderboard":"","github":"","paper":"","metric":"seconds","stars":"","top_model":"PersonaPlex 7B v1","top_percent":0.07,"top_model_id":"personaplex-7b-v1","top_generation":"PersonaPlex","top_model_base":"PersonaPlex 7B","top_model_family":"PersonaPlex","top_company":"nvidia","top_open_source":1,"lower_is_better":true,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"personaplex-7b-v1","company":"nvidia","family":"PersonaPlex","version":"PersonaPlex","score":0.07},{"place":2,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":0.4},{"place":3,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":0.45},{"place":4,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":0.57},{"place":5,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":0.59},{"place":6,"model":"gpt-live-1-low","company":"openai","family":"GPT","version":"GPT-Live-1","score":0.8},{"place":7,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":0.94},{"place":8,"model":"raon-speechchat-9b","company":"krafton","family":"Raon","version":"Raon-SpeechChat","score":1.03},{"place":9,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":1.18},{"place":10,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":1.41},{"place":11,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":1.63},{"place":12,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":1.63},{"place":13,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.14}]},{"id":"fd-bench-v1.5","name":"FD-Bench V1.5","topic":"Full-duplex speech interaction","description":"Full-duplex spoken dialogue benchmark v1.5 (interruption handling, backchannel, turn-taking quality); average score.","url":"https://thinkingmachines.ai/blog/interaction-models/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-Live-1 (low)","top_percent":80.1,"top_model_id":"gpt-live-1-low","top_generation":"GPT-Live-1","top_model_base":"GPT-Live-1","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-live-1-low","company":"openai","family":"GPT","version":"GPT-Live-1","score":80.1},{"place":2,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":77.8},{"place":3,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.3},{"place":4,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":48.3},{"place":5,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":47.8},{"place":6,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":47.8},{"place":7,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":46.8},{"place":8,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":45.5},{"place":9,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":45.43},{"place":10,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39}]},{"id":"fd-bench-v3","name":"FD-Bench V3","topic":"Full-duplex speech + tool use","description":"Full-duplex spoken dialogue benchmark v3 with tool calling; response quality (%).","url":"https://thinkingmachines.ai/blog/interaction-models/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-Live-1 (medium)","top_percent":90,"top_model_id":"gpt-live-1-medium","top_generation":"GPT-Live-1","top_model_base":"GPT-Live-1","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-live-1-medium","company":"openai","family":"GPT","version":"GPT-Live-1","score":90},{"place":2,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":88},{"place":3,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":82.8},{"place":4,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":81},{"place":5,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":81},{"place":6,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":80},{"place":7,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":77.9},{"place":8,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.4},{"place":9,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":68.5},{"place":10,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60}]},{"id":"fd-bench-v3-pass1","name":"FD-Bench V3 Pass@1","topic":"Full-duplex speech + tool use","description":"Full-Duplex-Bench v3: tool-calling task success (pass@1, %) in full-duplex spoken dialogue.","url":"https://github.com/DanielLin94144/Full-Duplex-Bench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2604.04847","metric":"percent","stars":"","top_model":"GPT-Live-1 (medium)","top_percent":87,"top_model_id":"gpt-live-1-medium","top_generation":"GPT-Live-1","top_model_base":"GPT-Live-1","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gpt-live-1-medium","company":"openai","family":"GPT","version":"GPT-Live-1","score":87},{"place":2,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":68},{"place":3,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":60},{"place":4,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":60},{"place":5,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":58},{"place":6,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":58},{"place":7,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":55},{"place":8,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":54},{"place":9,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":52},{"place":10,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50},{"place":11,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":48},{"place":12,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":48},{"place":13,"model":"grok-voice-agent","company":"xai","family":"Grok","version":"Grok Voice","score":43},{"place":14,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":33}]},{"id":"featbench","name":"FeatBench","topic":"Code (feature implementation)","description":"Benchmark of feature implementation in real repositories from natural-language requirements (vibe coding).","url":"https://arxiv.org/abs/2509.22237","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2509.22237","metric":"percent","stars":"","top_model":"openPangu-2.0-Pro","top_percent":48.4,"top_model_id":"openpangu-2.0-pro","top_generation":"openPangu-2.0","top_model_base":"openPangu-2.0-Pro","top_model_family":"openPangu","top_company":"huawei","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":48.4},{"place":2,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":47.1},{"place":3,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":45.9},{"place":4,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":45.8}]},{"id":"fetaqa","name":"FeTaQA","topic":"Table QA","description":"Free-form table QA (MMTab subset; BLEU).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":39.2,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":39.2},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":12},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":9.6},{"place":4,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":8.7},{"place":5,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":7.4},{"place":6,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":6.2}]},{"id":"figqa","name":"FigQA","topic":"Figure understanding and QA","description":"Figure question answering benchmark evaluating visual reasoning over scientific figures and diagrams.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Mythos 5","top_percent":88.9,"top_model_id":"claude-mythos-5","top_generation":"Claude 5","top_model_base":"Claude Mythos 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.9},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80.4},{"place":3,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":78.6},{"place":4,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":34},{"place":5,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":29}]},{"id":"finance-reasoning","name":"FinanceReasoning","topic":"Financial reasoning","description":"Financial reasoning benchmark evaluating quantitative and qualitative finance problem solving.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ling 1T","top_percent":87.45,"top_model_id":"ling-1t","top_generation":"Ling 1T","top_model_base":"Ling 1T","top_model_family":"Ling","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":87.45},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.65},{"place":3,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":86.44},{"place":4,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86.28},{"place":5,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":84.83}]},{"id":"financeagent","name":"FinanceAgent","topic":"Agentic finance tasks","description":"Interactive financial agent benchmark requiring multi-step tool use.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":60.7,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":60.7},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":60.7},{"place":3,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":56.6},{"place":4,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":56.6},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.9},{"place":6,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.9},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.3},{"place":8,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":54.7},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.2},{"place":10,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.2},{"place":11,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":50.9},{"place":12,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":46.9},{"place":13,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":44.5},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":44.1},{"place":15,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":44.1},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":29.4}]},{"id":"financeagent-v1.1","name":"FinanceAgent v1.1","topic":"Agentic finance tasks","description":"Finance Agent v1.1 benchmark for interactive financial agent evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.7 Flash","top_percent":71,"top_model_id":"gemini-3.7-flash","top_generation":"Gemini 3.7","top_model_base":"Gemini 3.7 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":71},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.5},{"place":3,"model":"ling-3.0-flash-fin","company":"antgroup","family":"Ling","version":"Ling 3.0","score":69.19},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":67},{"place":5,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":66.5},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":65.3},{"place":7,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":64.4},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.18},{"place":9,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":64.05},{"place":10,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":63.3},{"place":11,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":63},{"place":12,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.3},{"place":13,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":61.5},{"place":14,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":60.7},{"place":15,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":60.7},{"place":16,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":60.1},{"place":17,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":60.1},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":60},{"place":19,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":59.7},{"place":20,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":59.5},{"place":21,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":59},{"place":22,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":23,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.8},{"place":24,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":58.8},{"place":25,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.5},{"place":26,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":57.2},{"place":27,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":56},{"place":28,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":56},{"place":29,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":55.2},{"place":30,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.5},{"place":31,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":54},{"place":32,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":53.7},{"place":33,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":50.5}]},{"id":"financeagent-v2","name":"FinanceAgent v2","topic":"Agentic finance tasks","description":"Vals AI Finance Agent Benchmark v2: agentic financial-research tasks over SEC filings; new dataset, not comparable to v1.1.","url":"https://www.vals.ai/benchmarks/finance_agent","leaderboard":"https://www.vals.ai/benchmarks/finance_agent","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":65.4,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":65.4},{"place":2,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":64.2},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":62.96},{"place":4,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":61.57},{"place":5,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":61.4},{"place":6,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":61.11},{"place":7,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":60.49},{"place":8,"model":"ling-3.0-flash-fin","company":"antgroup","family":"Ling","version":"Ling 3.0","score":59.81},{"place":9,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":59.26},{"place":10,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":59.1},{"place":11,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":59},{"place":12,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":58.9},{"place":13,"model":"minimax-m3.1-flash-max","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":58.83},{"place":14,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":58.6},{"place":15,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":58.6},{"place":16,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":57.9},{"place":17,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":57.87},{"place":18,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":57.2},{"place":19,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":56.6},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":56.48},{"place":21,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.31},{"place":22,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.3},{"place":23,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":54.4},{"place":24,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":54.4},{"place":25,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":53.9},{"place":26,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.9},{"place":27,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":53.89},{"place":28,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":53.8},{"place":29,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":53.5},{"place":30,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53.09},{"place":31,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":51.8},{"place":32,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":51.5},{"place":33,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":51},{"place":34,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":49.7},{"place":35,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":48.61},{"place":36,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":44.9},{"place":37,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":43},{"place":38,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":42.6}]},{"id":"financebench-fulldoc","name":"FinanceBench (FullDoc)","topic":"Finance QA","description":"FinanceBench full-document question answering benchmark requiring long-context financial understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Jamba Mini 1.6","top_percent":45.4,"top_model_id":"jamba-mini-1.6","top_generation":"Jamba Mini","top_model_base":"Jamba Mini 1.6","top_model_family":"Jamba","top_company":"ai21","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":45.4},{"place":2,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":28.4},{"place":3,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":19.2},{"place":4,"model":"command-r7b","company":"cohere","family":"Command","version":"Command","score":2.8}]},{"id":"financialphrasebank","name":"FinancialPhraseBank","topic":"Financial sentiment","description":"Sentence-level financial news sentiment classification.","url":"https://huggingface.co/datasets/takala/financial_phrasebank","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"pplx-decider-v1-27b","top_percent":84.18,"top_model_id":"pplx-decider-v1-27b","top_generation":"v1","top_model_base":"pplx-decider","top_model_family":"pplx-decider","top_company":"perplexity","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":84.18},{"place":2,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":76.98}]},{"id":"finentity-decision","name":"FinEntity (decision)","topic":"Financial sentiment","description":"Entity-level financial sentiment; macro-F1. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://huggingface.co/datasets/yixuantt/FinEntity","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"Clef-Flash","top_percent":97.1,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":97.1},{"place":2,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":96.3},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":96.2},{"place":4,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":95.7},{"place":5,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":94.3},{"place":6,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":94.3},{"place":7,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":93.5},{"place":8,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":92.1},{"place":9,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":90.5},{"place":10,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":90.4},{"place":11,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":90.2},{"place":12,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":89},{"place":13,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":88.9},{"place":14,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":88.9},{"place":15,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":88.4},{"place":16,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":88.1},{"place":17,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":88},{"place":18,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":87.7},{"place":19,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":87.6},{"place":20,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":87},{"place":21,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":86.3},{"place":22,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":83.4},{"place":23,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":82.7},{"place":24,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":80.9},{"place":25,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":80.5},{"place":26,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":79.8},{"place":27,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":76.2},{"place":28,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":72.7},{"place":29,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":68},{"place":30,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":66.2},{"place":31,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":65.5},{"place":32,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":63.2},{"place":33,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":62.9},{"place":34,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":61},{"place":35,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":61},{"place":36,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59.8},{"place":37,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":57.8},{"place":38,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":57.1}]},{"id":"finqa-128k","name":"FinQA 128k","topic":"Long-context financial QA","description":"Long-context (128k) variant of FinQA: analytics questions over financial reports.","url":"https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":74.1,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":74.1},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.1},{"place":3,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.5},{"place":4,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.7},{"place":5,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":35.5}]},{"id":"finsearchcomp","name":"FinSearchComp","topic":"Financial retrieval","description":"Financial search and comprehension benchmark measuring retrieval grounded reasoning over financial content.","url":"https://randomtutu.github.io/FinSearchComp/","leaderboard":"https://randomtutu.github.io/FinSearchComp/","github":"","paper":"https://arxiv.org/pdf/2509.13160","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":70.2,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":70.2},{"place":2,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":68.9},{"place":3,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":67.8},{"place":4,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.2},{"place":5,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":65.5},{"place":6,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":65.1},{"place":7,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":63.9},{"place":8,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.8},{"place":9,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":61.8},{"place":10,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60.8},{"place":11,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":59.1},{"place":12,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":49.9},{"place":13,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":48.5},{"place":14,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":47.4},{"place":15,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44},{"place":16,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":43.7},{"place":17,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":42.6},{"place":18,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":42},{"place":19,"model":"doubao-1.5-vision-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":39.1},{"place":20,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":37.4},{"place":21,"model":"yuanbao-deepseek-v3","company":"yuanbao","family":"YuanBao","version":"YuanBao DeepSeek V3","score":30.5},{"place":22,"model":"yuanbao-hunyuan-t1-thinking","company":"yuanbao","family":"YuanBao","version":"YuanBao Hunyuan T1","score":29.8},{"place":23,"model":"yuanbao-deepseek-r1","company":"yuanbao","family":"YuanBao","version":"YuanBao DeepSeek R1","score":29.8},{"place":24,"model":"doubao-1.5-vision-pro-thinking","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":29.8},{"place":25,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":29.5},{"place":26,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":29.5},{"place":27,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":29.2},{"place":28,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":27},{"place":29,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":26.2},{"place":30,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":17.2},{"place":31,"model":"ernie-x1","company":"baidu","family":"ERNIE","version":"ERNIE X1","score":16.6},{"place":32,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":10.4}]},{"id":"finsearchcomp-cn","name":"FinSearchComp-CN","topic":"Financial retrieval (Chinese)","description":"Chinese financial search and comprehension benchmark measuring retrieval-grounded reasoning over regional financial content.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"doubao-1-5-vision-pro","top_percent":54.2,"top_model_id":"doubao-1.5-vision-pro","top_generation":"Doubao 1.5","top_model_base":"Doubao 1.5 Vision Pro","top_model_family":"Doubao","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"doubao-1.5-vision-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":54.2},{"place":2,"model":"yuanbao-deepseek-r1","company":"yuanbao","family":"YuanBao","version":"YuanBao DeepSeek R1","score":52.5},{"place":3,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":51.9},{"place":4,"model":"yuanbao-hunyuan-t1-thinking","company":"yuanbao","family":"YuanBao","version":"YuanBao Hunyuan T1","score":50.5},{"place":5,"model":"doubao-1.5-vision-pro-thinking","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":49},{"place":6,"model":"yuanbao-deepseek-v3","company":"yuanbao","family":"YuanBao","version":"YuanBao DeepSeek V3","score":48.8},{"place":7,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":46.4},{"place":8,"model":"ernie-x1","company":"baidu","family":"ERNIE","version":"ERNIE X1","score":40.8},{"place":9,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":40.5},{"place":10,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":38.3},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":36.8},{"place":12,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":21.9}]},{"id":"finsearchcomp-t2t3","name":"FinSearchComp (T2&T3)","topic":"Finance search","description":"Finance search competition tasks (tracks T2 and T3).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":64.5,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":64.5},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":62.8},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.6},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":49.9},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":34}]},{"id":"flame-react-eval","name":"Flame-React-Eval","topic":"Frontend coding","description":"Front-end React coding tasks and evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":98.8,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":98.8},{"place":2,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":93.8},{"place":3,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":88.8},{"place":4,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":86.3},{"place":5,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":82.5},{"place":6,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":78.8},{"place":7,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":72.5},{"place":8,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":63.8},{"place":9,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":36.3},{"place":10,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":27.5}]},{"id":"fleurs","name":"FLEURS","topic":"Speech recognition","description":"FLEURS multilingual automatic speech recognition benchmark; word error rate, lower is better.","url":"https://huggingface.co/datasets/google/fleurs","leaderboard":"","github":"","paper":"","metric":"wer","stars":"","top_model":"Gemma 4 E4B IT","top_percent":0.08,"top_model_id":"gemma-4-e4b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 E4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.08},{"place":2,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.09}]},{"id":"flickr30k","name":"Flickr30K Captions","topic":"Image captioning","description":"Flickr30K image captioning (Karpathy test split, CIDEr).","url":"https://shannon.cs.illinois.edu/DenotationGraph/","leaderboard":"","github":"","paper":"https://aclanthology.org/Q14-1006/","metric":"cider","stars":"","top_model":"Qwen-VL","top_percent":85.8,"top_model_id":"qwen-vl","top_generation":"Qwen-VL","top_model_base":"Qwen-VL","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":85.8},{"place":2,"model":"instructblip-vicuna-13b","company":"salesforce","family":"BLIP","version":"InstructBLIP","score":82.8},{"place":3,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":81},{"place":4,"model":"kosmos2","company":"microsoft","family":"Kosmos2","version":"Kosmos-2","score":80.5},{"place":5,"model":"shikra-13b","company":"sensetime","family":"Shikra","version":"Shikra","score":73.9},{"place":6,"model":"blip-2-vicuna-13b","company":"salesforce","family":"BLIP","version":"BLIP-2","score":71.6},{"place":7,"model":"flamingo-80b","company":"google","family":"Flamingo","version":"Flamingo","score":67.2},{"place":8,"model":"kosmos-1","company":"microsoft","family":"Kosmos","version":"Kosmos-1","score":67.1},{"place":9,"model":"flamingo-9b","company":"google","family":"Flamingo","version":"Flamingo","score":61.5}]},{"id":"flores","name":"Flores","topic":"Machine translation (multilingual)","description":"FLORES multilingual translation benchmark.","url":"https://github.com/facebookresearch/flores","leaderboard":"","github":"https://github.com/facebookresearch/flores","paper":"","metric":"percent","stars":"","top_model":"EuroLLM-22B","top_percent":88.88,"top_model_id":"eurollm-22b","top_generation":"EuroLLM","top_model_base":"EuroLLM 22B","top_model_family":"EuroLLM","top_company":"eurollm","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":88.88},{"place":2,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":88.81},{"place":3,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":88.17},{"place":4,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":88.15},{"place":5,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.57},{"place":6,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.36},{"place":7,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":82.73},{"place":8,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":82.39},{"place":9,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":43.5},{"place":10,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":41.8},{"place":11,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":38.9},{"place":12,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":33.8},{"place":13,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":32},{"place":14,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":30.5},{"place":15,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":28.8},{"place":16,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":25},{"place":17,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":23.9}]},{"id":"flteval","name":"FLTEval","topic":"Formal proof engineering","description":"Mistral benchmark built from real pull requests to the Fermat's Last Theorem Lean repository: complete all formal proofs and new definitions per PR.","url":"https://mistral.ai/news/leanstral","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":39.6,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":39.6},{"place":2,"model":"leanstral-1.5","company":"mistral","family":"Leanstral","version":"Leanstral 1.5","score":28.9},{"place":3,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":23.7},{"place":4,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":23},{"place":5,"model":"leanstral","company":"mistral","family":"Leanstral","version":"Leanstral","score":21.9}]},{"id":"forecastbench-decision","name":"ForecastBench (decision)","topic":"Forecasting","description":"ForecastBench questions answered as probabilities; Brier score x100 (lower is better). Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://www.forecastbench.org/","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"brier","stars":"","top_model":"Clef-Flash","top_percent":10.6,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":true,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":10.6},{"place":2,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":11.7},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":13.9},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":17.4},{"place":5,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":17.6},{"place":6,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":29.6},{"place":7,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":41.1}]},{"id":"forte","name":"FORTE","topic":"General agent","description":"AGI-Eval FORTE general agentic task benchmark.","url":"https://github.com/AGI-Eval-Official/FORTE","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":77.8,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":77.8},{"place":2,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":77.6},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":77.2},{"place":4,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":73.2},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.2},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.3}]},{"id":"fortress-adversarial","name":"FORTRESS (Adversarial)","topic":"Safety","description":"Scale AI FORTRESS adversarial prompts (CBRNE, political violence, crime); safety score.","url":"https://arxiv.org/abs/2506.14922","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":96,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":96},{"place":2,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91.3},{"place":3,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":86.3},{"place":4,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":83.8},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":82.4},{"place":6,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":78},{"place":7,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":77.6},{"place":8,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.3},{"place":9,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":71.6},{"place":10,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":71.3},{"place":11,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":70.7},{"place":12,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":65.6},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":65.2},{"place":14,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":64.8},{"place":15,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":54.1},{"place":16,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":36},{"place":17,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":32}]},{"id":"fortress-benign","name":"FORTRESS (Benign)","topic":"Safety (over-refusal)","description":"Scale AI FORTRESS benign counterpart prompts; share answered without over-refusal.","url":"https://arxiv.org/abs/2506.14922","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Flash-Thinking (max)","top_percent":99.2,"top_model_id":"deepseek-v4-flash-thinking-max","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Flash","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":99.2},{"place":2,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":98.5},{"place":3,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":98.3},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.1},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":98},{"place":6,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":97.8},{"place":7,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":97.2},{"place":8,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":96.9},{"place":9,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":95.9},{"place":10,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":95.5},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.4},{"place":12,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":94.6},{"place":13,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":94.1},{"place":14,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.6},{"place":15,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.5},{"place":16,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":90.1},{"place":17,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":90},{"place":18,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":55.1}]},{"id":"fox-page-cn","name":"Fox-Page-cn","topic":"Document OCR (Chinese)","description":"Fox Page benchmark evaluating OCR accuracy and layout understanding on Chinese document pages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Dolphin 1.5","top_percent":0.77,"top_model_id":"dolphin-1.5","top_generation":"Dolphin","top_model_base":"Dolphin 1.5","top_model_family":"Dolphin","top_company":"bytedance","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"dolphin-1.5","company":"bytedance","family":"Dolphin","version":"Dolphin","score":0.77},{"place":2,"model":"dolphin","company":"bytedance","family":"Dolphin","version":"Dolphin","score":1.31}]},{"id":"fox-page-en","name":"Fox-Page-en","topic":"Document OCR (English)","description":"Fox Page benchmark evaluating OCR accuracy and layout understanding on English document pages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Dolphin 1.5","top_percent":0.74,"top_model_id":"dolphin-1.5","top_generation":"Dolphin","top_model_base":"Dolphin 1.5","top_model_family":"Dolphin","top_company":"bytedance","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"dolphin-1.5","company":"bytedance","family":"Dolphin","version":"Dolphin","score":0.74},{"place":2,"model":"dolphin","company":"bytedance","family":"Dolphin","version":"Dolphin","score":1.14}]},{"id":"fr-bench-pdf2md","name":"fr-bench-pdf2md","topic":"Document parsing","description":"French PDF-to-Markdown conversion benchmark (baseline, forms, graphics, handwritten, long tables, multi-column, tiny text); overall score.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LightOnOCR-3-4B","top_percent":74.1,"top_model_id":"lightonocr-3-4b","top_generation":"LightOnOCR-3","top_model_base":"LightOnOCR-3 4B","top_model_family":"LightOnOCR","top_company":"lighton","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"lightonocr-3-4b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":74.1},{"place":2,"model":"lightonocr-3-0.8b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":70.5},{"place":3,"model":"lightonocr-3-1b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":69.6},{"place":4,"model":"chandra-ocr-2","company":"chandra","family":"Chandra OCR","version":"Chandra OCR 2","score":69},{"place":5,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":63.2},{"place":6,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":59.3},{"place":7,"model":"surya-ocr-2","company":"datalab","family":"Surya OCR","version":"Surya OCR 2","score":54.1},{"place":8,"model":"mistral-ocr-4.1","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":54.1},{"place":9,"model":"jina-ocr-v1","company":"jina","family":"jina-ocr","version":"jina-ocr-v1","score":53.2}]},{"id":"frames","name":"FRAMES","topic":"Interactive reasoning","description":"Frame-based interactive reasoning and dialogue benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Tongyi DeepResearch","top_percent":90.6,"top_model_id":"tongyi-deepresearch","top_generation":"Tongyi","top_model_base":"Tongyi DeepResearch","top_model_family":"Tongyi","top_company":"tongyi","top_open_source":0,"lower_is_better":false,"bench_models":55,"total_models":3854,"placements":[{"place":1,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":90.6},{"place":2,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":88.3},{"place":3,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":87.4},{"place":4,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":87.3},{"place":5,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":87},{"place":6,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86},{"place":7,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":86},{"place":8,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85},{"place":10,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.7},{"place":11,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":84.59},{"place":12,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":84.5},{"place":13,"model":"o3","company":"openai","family":"o3","version":"o3","score":84},{"place":14,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":84},{"place":15,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":83.7},{"place":16,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":83.7},{"place":17,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":83.4},{"place":18,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":82.9},{"place":19,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":82.7},{"place":20,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":82.5},{"place":21,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.9},{"place":22,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":80.7},{"place":23,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":80.6},{"place":24,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.5},{"place":25,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":80.5},{"place":26,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":80.2},{"place":27,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":79.2},{"place":28,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":78.9},{"place":29,"model":"kimi-researcher","company":"moonshotai","family":"Kimi","version":"Kimi Researcher","score":78.8},{"place":30,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.7},{"place":31,"model":"qwen3-max-thinking-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":77.93},{"place":32,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":77.1},{"place":33,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":76.86},{"place":34,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":76.3},{"place":35,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":75.12},{"place":36,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.88},{"place":37,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":74.76},{"place":38,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.51},{"place":39,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":74.5},{"place":40,"model":"golongrl-30b-a3b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":74.5},{"place":41,"model":"asearcher-web-qwq-v2","company":"antgroup","family":"ASearcher","version":"ASearcher","score":74.5},{"place":42,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":73.54},{"place":43,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":73.3},{"place":44,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.9},{"place":45,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":72.69},{"place":46,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":72.5},{"place":47,"model":"qwenlong-l1","company":"qwen","family":"QwenLong","version":"QwenLong","score":72.39},{"place":48,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":72},{"place":49,"model":"iterresearch-30b-a3b","company":"tongyi","family":"IterResearch","version":"IterResearch","score":71},{"place":50,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.87},{"place":51,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.27},{"place":52,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.2},{"place":53,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":70},{"place":54,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.8},{"place":55,"model":"golongrl-4b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":67.4},{"place":56,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":66.9},{"place":57,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.78},{"place":58,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":65.4},{"place":59,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":64.4},{"place":60,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":58.1}]},{"id":"freshqa","name":"FreshQA","topic":"Recency QA","description":"Question answering benchmark emphasizing up-to-date knowledge and recency.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-4B Thinking 2507","top_percent":66.89,"top_model_id":"qwen3-4b-thinking-2507","top_generation":"Qwen3","top_model_base":"Qwen3 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.89},{"place":2,"model":"jan-v1-2509","company":"menlo","family":"Jan","version":"Jan v1","score":55.07},{"place":3,"model":"jan-v1","company":"menlo","family":"Jan","version":"Jan v1","score":54.05},{"place":4,"model":"jan-v1-edge","company":"menlo","family":"Jan","version":"Jan v1","score":21.28},{"place":5,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":17.57}]},{"id":"frontier-cs","name":"Frontier-CS","topic":"Algorithmic / open-ended CS problems","description":"Frontier-CS agent track (188 tasks): open-ended computer-science optimization problems scored by verifiable feedback.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":76.4,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":76.4},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":74.5},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":72.1},{"place":4,"model":"arex-2","company":"baai","family":"AREX","version":"AREX-2","score":70.7},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":68.9},{"place":6,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":61.9},{"place":7,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":54.7},{"place":8,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":50.4},{"place":9,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":46.9},{"place":10,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.7},{"place":11,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":39.1},{"place":12,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":23.4}]},{"id":"frontierbench","name":"FrontierBench","topic":"Agentic terminal tasks","description":"Successor to Terminal-Bench 2.1 (v0.1): 74 harder terminal tasks emphasizing science and engineering.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":43.3,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":43.3},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":34.4},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":33.8},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":33.7},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":23},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":21.1},{"place":7,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":13.5},{"place":8,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":6.1},{"place":9,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":5.1},{"place":10,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":5.1},{"place":11,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":2.7},{"place":12,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":1.4},{"place":13,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1.4},{"place":14,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1.4}]},{"id":"frontiercode","name":"FrontierCode","topic":"Software engineering","description":"Cognition's agentic coding benchmark of 150 tasks from real PRs, graded on hidden tests plus code-quality rubric (Main set, v1.1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":54.4,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":54.4},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.4},{"place":3,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":46.4},{"place":4,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":46.2}]},{"id":"frontiercode-diamond","name":"FrontierCode (Diamond)","topic":"Software engineering","description":"Cognition's FrontierCode agentic coding benchmark, Diamond subset; patch correctness graded by held-out tests plus rubric.","url":"https://cognition.ai/blog/frontier-code","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":29.3,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":29.3},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":13.4},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":5.7}]},{"id":"frontiercode-extended","name":"FrontierCode Extended","topic":"Software engineering","description":"Cognition FrontierCode 1.1 Extended set (score).","url":"https://cognition.com/frontiercode","leaderboard":"https://cognition.com/frontiercode","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":65.3,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":46,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":65.3},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":64.9},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":64.5},{"place":4,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":64.4},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":63.6},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.6},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.6},{"place":8,"model":"swe-2","company":"cognition","family":"SWE","version":"SWE-2","score":62.5},{"place":9,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":61.3},{"place":10,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":60.7},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":60.6},{"place":12,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":60.6},{"place":13,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":60.4},{"place":14,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59.6},{"place":15,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":59.4},{"place":16,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":58.4},{"place":17,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":58.2},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":56.7},{"place":19,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":56.6},{"place":20,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":56.6},{"place":21,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":56.5},{"place":22,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":56.3},{"place":23,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":56.3},{"place":24,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.2},{"place":25,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":56.1},{"place":26,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":55.8},{"place":27,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":55.1},{"place":28,"model":"swe-1.7","company":"cognition","family":"SWE","version":"SWE-1.7","score":54.3},{"place":29,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":53.9},{"place":30,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":53.4},{"place":31,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":53.2},{"place":32,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":52.6},{"place":33,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":48},{"place":34,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":46.2},{"place":35,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":45.4},{"place":36,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.5},{"place":37,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":43.7},{"place":38,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":43},{"place":39,"model":"composer-2.5","company":"cursor","family":"Composer","version":"Composer 2.5","score":40.8},{"place":40,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":40.1},{"place":41,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40},{"place":42,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":31.7},{"place":43,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":31},{"place":44,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":28.5},{"place":45,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":27.2},{"place":46,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":24.8},{"place":47,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":21.8},{"place":48,"model":"swe-1.6","company":"cognition","family":"SWE","version":"SWE-1.6","score":20.5},{"place":49,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":18.7}]},{"id":"frontiercode-main","name":"FrontierCode Main","topic":"Software engineering","description":"Cognition FrontierCode 1.1 Main: coding-agent changes graded on correctness and mergeability (tests, scope, style, conventions).","url":"https://cognition.com/frontiercode","leaderboard":"https://cognition.com/frontiercode","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":54.6,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":46,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":54.6},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.5},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.4},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":53.3},{"place":5,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":52.1},{"place":6,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":50.9},{"place":7,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":50.3},{"place":8,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":50.2},{"place":9,"model":"swe-2","company":"cognition","family":"SWE","version":"SWE-2","score":50},{"place":10,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":49.3},{"place":11,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":48},{"place":12,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":48},{"place":13,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":47.6},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":47.5},{"place":15,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":47.5},{"place":16,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":46.5},{"place":17,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":46.4},{"place":18,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":45.8},{"place":19,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":44.2},{"place":20,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":43.9},{"place":21,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":43.6},{"place":22,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":43.6},{"place":23,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":43},{"place":24,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":42.7},{"place":25,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":42.4},{"place":26,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":42.4},{"place":27,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":42.4},{"place":28,"model":"swe-1.7","company":"cognition","family":"SWE","version":"SWE-1.7","score":42.3},{"place":29,"model":"swe-1.7","company":"cognition","family":"SWE","version":"SWE-1.7","score":42},{"place":30,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":41.3},{"place":31,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":41.2},{"place":32,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":40.1},{"place":33,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":39.8},{"place":34,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":39.4},{"place":35,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":38.5},{"place":36,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":34.4},{"place":37,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":31.8},{"place":38,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":30.1},{"place":39,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":28.5},{"place":40,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":27},{"place":41,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":26.6},{"place":42,"model":"composer-2.5","company":"cursor","family":"Composer","version":"Composer 2.5","score":25.6},{"place":43,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":24.5},{"place":44,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":24.3},{"place":45,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":18.8},{"place":46,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":17.6},{"place":47,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":14.7},{"place":48,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":14},{"place":49,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":13.6},{"place":50,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":10.2},{"place":51,"model":"swe-1.6","company":"cognition","family":"SWE","version":"SWE-1.6","score":9.4},{"place":52,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":8}]},{"id":"frontierfinance","name":"FrontierFinance","topic":"Finance","description":"Professional finance benchmark combining quantitative reasoning with analysis of financial data and documents (reported in Step 5 Preview release).","url":"https://www.stepfun.com/step-5-preview","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":69.7,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":69.7},{"place":2,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":66.4},{"place":3,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":64.1},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":62.6},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":60.8},{"place":6,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":58.6},{"place":7,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":57.5},{"place":8,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":56.7},{"place":9,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":55},{"place":10,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":54.5},{"place":11,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":54.3},{"place":12,"model":"apodex-1.1-mini","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":50.2},{"place":13,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":49.2},{"place":14,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":48.8},{"place":15,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":48.7},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.8},{"place":17,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":46.3},{"place":18,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":45.5},{"place":19,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":45},{"place":20,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.2},{"place":21,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":42.8},{"place":22,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":40.3},{"place":23,"model":"apodex-1.1-mini","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":40}]},{"id":"frontiermath","name":"FrontierMath","topic":"Math (frontier)","description":"Frontier mathematics benchmark.","url":"","leaderboard":"https://epoch.ai/frontiermath","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 pro","top_percent":32.1,"top_model_id":"gpt-5-pro","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":32.1},{"place":2,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":6.3},{"place":3,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.8}]},{"id":"frontierscience","name":"FrontierScience","topic":"Science reasoning","description":"Frontier-level scientific reasoning and QA benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MAI-Code-1-Flash","top_percent":58.2,"top_model_id":"mai-code-1-flash","top_generation":"MAI-Code-1","top_model_base":"MAI-Code-1-Flash","top_model_family":"MAI","top_company":"microsoft","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":58.2},{"place":2,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.3},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":25.2},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.5},{"place":5,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":15.9},{"place":6,"model":"o3","company":"openai","family":"o3","version":"o3","score":14.1},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":12.4},{"place":8,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":8.3},{"place":9,"model":"o1","company":"openai","family":"o1","version":"o1","score":3.2},{"place":10,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0.4}]},{"id":"frontierscience-olympiad","name":"FrontierScience Olympiad","topic":"Science reasoning (olympiad)","description":"Olympiad-level problems from the FrontierScience benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-S2-397B","top_percent":87,"top_model_id":"intern-s2-397b","top_generation":"Intern-S2","top_model_base":"Intern-S2-397B","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":87},{"place":2,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":81},{"place":3,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":79.67},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":79},{"place":5,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":79},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":78},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":77},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.8},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":76.8},{"place":10,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":76},{"place":11,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":76},{"place":12,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76},{"place":13,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":75},{"place":14,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":75},{"place":15,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":74.8},{"place":16,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":74.3},{"place":17,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":74.3},{"place":18,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":74},{"place":19,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":73.8},{"place":20,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":73},{"place":21,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":73},{"place":22,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73},{"place":23,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":73},{"place":24,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73},{"place":25,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":72.5},{"place":26,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":72},{"place":27,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71},{"place":28,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":70},{"place":29,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":70},{"place":30,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":70},{"place":31,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":70},{"place":32,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":70},{"place":33,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":70},{"place":34,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":69},{"place":35,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69},{"place":36,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":69},{"place":37,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":69},{"place":38,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":68},{"place":39,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":67.8},{"place":40,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.67},{"place":41,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":67},{"place":42,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":65.9},{"place":43,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":65.67},{"place":44,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":65},{"place":45,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":65},{"place":46,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.5},{"place":47,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":63.3},{"place":48,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":61},{"place":49,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":60.33},{"place":50,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":60.3},{"place":51,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60},{"place":52,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58},{"place":53,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":53.33},{"place":54,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":52},{"place":55,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":45.41},{"place":56,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":44},{"place":57,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":31.67},{"place":58,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":20.13}]},{"id":"frontierscience-research","name":"FrontierScience Research","topic":"Science reasoning (research)","description":"Research-level problems from the FrontierScience benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Apodex 1.1","top_percent":63.3,"top_model_id":"apodex-1.1","top_generation":"Apodex 1.1","top_model_base":"Apodex 1.1","top_model_family":"Apodex","top_company":"apodex","top_open_source":0,"lower_is_better":false,"bench_models":55,"total_models":3854,"placements":[{"place":1,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":63.3},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.3},{"place":3,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":57.22},{"place":4,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":55},{"place":5,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":55},{"place":6,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55},{"place":7,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":52.4},{"place":8,"model":"apodex-1.1-mini","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":51.7},{"place":9,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":51.11},{"place":10,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":46.2},{"place":11,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":45.2},{"place":12,"model":"apodex-1.1-mini","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":45},{"place":13,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":42.22},{"place":14,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":41.67},{"place":15,"model":"seed2.1-deep-think","company":"bytedance","family":"Seed","version":"Seed 2.1","score":40.7},{"place":16,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40.7},{"place":17,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":40},{"place":18,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":38.4},{"place":19,"model":"muse-spark-contemplating","company":"meta","family":"Muse","version":"Muse Spark","score":38.3},{"place":20,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":38},{"place":21,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.7},{"place":22,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":37.2},{"place":23,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":36.8},{"place":24,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":36.7},{"place":25,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":36.67},{"place":26,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":33.9},{"place":27,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":33.3},{"place":28,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":33.3},{"place":29,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":33},{"place":30,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":32.9},{"place":31,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":29.6},{"place":32,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":28.3},{"place":33,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":28.3},{"place":34,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":26.7},{"place":35,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.67},{"place":36,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":25.2},{"place":37,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":25},{"place":38,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":25},{"place":39,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":25},{"place":40,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":24.8},{"place":41,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":24.8},{"place":42,"model":"gemini-3.1-deep-think","company":"google","family":"Gemini","version":"Gemini 3.1","score":23.3},{"place":43,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":21.7},{"place":44,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":21.3},{"place":45,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":21.3},{"place":46,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":20},{"place":47,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":19.8},{"place":48,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":19.44},{"place":49,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":19},{"place":50,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":18.3},{"place":51,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":18.3},{"place":52,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":17.9},{"place":53,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.78},{"place":54,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":16.7},{"place":55,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":16.7},{"place":56,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":16.7},{"place":57,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":15},{"place":58,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":13.5},{"place":59,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":13.3},{"place":60,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":12.22},{"place":61,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":11.9},{"place":62,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":11.7},{"place":63,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":10},{"place":64,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":10},{"place":65,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":6.7},{"place":66,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":5.56},{"place":67,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":5},{"place":68,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":3.89},{"place":69,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.33},{"place":70,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":3.3},{"place":71,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":2.9},{"place":72,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.5},{"place":73,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1.7}]},{"id":"frontierswe","name":"FrontierSWE","topic":"Software engineering","description":"Proximal's FrontierSWE benchmark of frontier-difficulty software engineering tasks; dominance score (snapshot-dependent).","url":"https://www.proximal.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":88.8,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.8},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.2},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.6},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":81.2},{"place":5,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":78.2},{"place":6,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":78.1},{"place":7,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":75.16},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75.1},{"place":9,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":74.4},{"place":10,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":74.34},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":73.52},{"place":12,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.5},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":72.6},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":71.3},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":70},{"place":16,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":67.5},{"place":17,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":67.3},{"place":18,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":66.7},{"place":19,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":66.5},{"place":20,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":65.5},{"place":21,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":64.9},{"place":22,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":62.3},{"place":23,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":58.55},{"place":24,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":56.3},{"place":25,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":55},{"place":26,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":40.7},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":39.6},{"place":28,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":30.5},{"place":29,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":29}]},{"id":"frontiervep","name":"FrontierVEP","topic":"Genomics","description":"Single-base variant-effect prediction benchmark.","url":"https://huggingface.co/HuggingFaceBio/Carbon-X","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5 (max)","top_percent":76.2,"top_model_id":"claude-opus-5.5-max","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":76.2},{"place":2,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":74.9},{"place":3,"model":"carbon-x","company":"huggingface","family":"Carbon","version":"Carbon","score":70.4},{"place":4,"model":"gemini-4-argon-low","company":"google","family":"Gemini","version":"Gemini 4","score":58},{"place":5,"model":"deepseek-v4.1-flash-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":51.3},{"place":6,"model":"kimi-k3-low","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":50.1},{"place":7,"model":"glm-5.3-low","company":"zai","family":"GLM","version":"GLM 5.3","score":32.7}]},{"id":"fsc-147","name":"FSC-147","topic":"Few-shot counting","description":"Few-shot counting benchmark across 147 categories.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Glimpse","top_percent":83.36,"top_model_id":"glimpse","top_generation":"Glimpse","top_model_base":"Glimpse","top_model_family":"Glimpse","top_company":"elorian","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":83.36},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":82.69},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":82.02},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":73.78},{"place":5,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":67.06},{"place":6,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":33.8},{"place":7,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":29.7},{"place":8,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":28},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":24.5},{"place":10,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":22},{"place":11,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":17.9},{"place":12,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":15.33},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":12.1}]},{"id":"fullstackbench","name":"FullStackBench","topic":"Full-stack development","description":"End-to-end web/app development tasks and evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":72.3,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":56,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.3},{"place":2,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":71.4},{"place":3,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":70.3},{"place":4,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":70.2},{"place":5,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70.1},{"place":6,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":69.9},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.7},{"place":8,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":69.4},{"place":9,"model":"o3","company":"openai","family":"o3","version":"o3","score":69.3},{"place":10,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":68.5},{"place":11,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":68.3},{"place":12,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":68.3},{"place":13,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":67.6},{"place":14,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":67.1},{"place":15,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":66.4},{"place":16,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":64.9},{"place":17,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":64.7},{"place":18,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":63.5},{"place":19,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.9},{"place":20,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":62.7},{"place":21,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.6},{"place":22,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.1},{"place":23,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":60.9},{"place":24,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.1},{"place":25,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":58.9},{"place":26,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":58.8},{"place":27,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.2},{"place":28,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.1},{"place":29,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":57.4},{"place":30,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":57.1},{"place":31,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":56.55},{"place":32,"model":"hunyuan-7b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":56.3},{"place":33,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":55.8},{"place":34,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.7},{"place":35,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":55.48},{"place":36,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":54.95},{"place":37,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54.4},{"place":38,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":54},{"place":39,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":53.1},{"place":40,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":52.9},{"place":41,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.5},{"place":42,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":51.16},{"place":43,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":50.92},{"place":44,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":50.86},{"place":45,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":50.39},{"place":46,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":49.61},{"place":47,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":49.4},{"place":48,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":48.43},{"place":49,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.19},{"place":50,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":48},{"place":51,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.1},{"place":52,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.2},{"place":53,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":39.48},{"place":54,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":38.6},{"place":55,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":38.59},{"place":56,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.23},{"place":57,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.14},{"place":58,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":30.6}]},{"id":"fullstackbench-zh","name":"FullStackBench (zh)","topic":"Full-stack development","description":"Chinese language full-stack development tasks and evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-235B-A22B","top_percent":63.1,"top_model_id":"qwen3-235b-a22b","top_generation":"Qwen3","top_model_base":"Qwen3 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.1},{"place":2,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":60.4},{"place":3,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.7},{"place":4,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.4},{"place":5,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55},{"place":6,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":35.2}]},{"id":"futureomni","name":"FutureOmni","topic":"Video forecasting","description":"FutureOmni: omni-modal (audio-visual) future event forecasting benchmark from video.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiMo V2 Omni","top_percent":66.7,"top_model_id":"mimo-v2-omni","top_generation":"MiMo V2","top_model_base":"MiMo V2 Omni","top_model_family":"MiMo","top_company":"xiaomi","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":66.7},{"place":2,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":62.9},{"place":3,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":62.1},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":60.3},{"place":5,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":56.1},{"place":6,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.6}]},{"id":"gaia","name":"GAIA","topic":"General AI tasks","description":"Comprehensive benchmark for agentic tasks.","url":"https://github.com/GAIA-benchmark/GAIA","leaderboard":"https://gaia-benchmark.github.io/leaderboard/","github":"https://github.com/GAIA-benchmark/GAIA","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Pro-Thinking (max)","top_percent":98.06,"top_model_id":"deepseek-v4-pro-thinking-max","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Pro","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":93,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":98.06},{"place":2,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":96.04},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":91.69},{"place":4,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":89.04},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":88.7},{"place":6,"model":"mirothinker-h1","company":"miromind","family":"MiroThinker","version":"MiroThinker H1","score":88.5},{"place":7,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":87.4},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":87.38},{"place":9,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":86.38},{"place":10,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.05},{"place":11,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":84.72},{"place":12,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":84.5},{"place":13,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":83.06},{"place":14,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":82.7},{"place":15,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":82.52},{"place":16,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":81.9},{"place":17,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":80.8},{"place":18,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.58},{"place":19,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.4},{"place":20,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":80.3},{"place":21,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":79.9},{"place":22,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78.64},{"place":23,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":78.41},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78.07},{"place":25,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.41},{"place":26,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":77.4},{"place":27,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":76.7},{"place":28,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":76.4},{"place":29,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":76.4},{"place":30,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":75.75},{"place":31,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":75.7},{"place":32,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":75.5},{"place":33,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.8},{"place":34,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":74.75},{"place":35,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.75},{"place":36,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74.09},{"place":37,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.42},{"place":38,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.09},{"place":39,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":72},{"place":40,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":71.9},{"place":41,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":71.76},{"place":42,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.2},{"place":43,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":71.1},{"place":44,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":70.9},{"place":45,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.1},{"place":46,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.09},{"place":47,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":68.77},{"place":48,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":68.44},{"place":49,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":68.3},{"place":50,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":68.3},{"place":51,"model":"openai-deepresearch","company":"openai","family":"DeepResearch","version":"DeepResearch","score":67.4},{"place":52,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":66.45},{"place":53,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":66},{"place":54,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66},{"place":55,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":65.45},{"place":56,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":64.45},{"place":57,"model":"mirothinker-v0.2-32b","company":"miromind","family":"MiroThinker","version":"MiroThinker v0.2","score":64.1},{"place":58,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":63.5},{"place":59,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":63.1},{"place":60,"model":"qwen3.8-27b-nvfp4","company":"qwen","family":"Qwen","version":"Qwen3.8","score":62.79},{"place":61,"model":"o3","company":"openai","family":"o3","version":"o3","score":62.13},{"place":62,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":60.8},{"place":63,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":60.2},{"place":64,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":60.2},{"place":65,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":60},{"place":66,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.8},{"place":67,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":58.8},{"place":68,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":57.7},{"place":69,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.3},{"place":70,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":56.15},{"place":71,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":55.48},{"place":72,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":55.48},{"place":73,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":54.49},{"place":74,"model":"o1","company":"openai","family":"o1","version":"o1","score":49.83},{"place":75,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.88},{"place":76,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.8},{"place":77,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":43.85},{"place":78,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":42.52},{"place":79,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":40.2},{"place":80,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":40},{"place":81,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":38.21},{"place":82,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":37.21},{"place":83,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":37.21},{"place":84,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":35.55},{"place":85,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":33.9},{"place":86,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":33.22},{"place":87,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":32.23},{"place":88,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":32.12},{"place":89,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":30.91},{"place":90,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":27.91},{"place":91,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":26.91},{"place":92,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.5},{"place":93,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":24.92},{"place":94,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":23.59},{"place":95,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":23.26},{"place":96,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":23.03},{"place":97,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":22.26},{"place":98,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.59},{"place":99,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":21.21},{"place":100,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":20.6},{"place":101,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":17.61},{"place":102,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":13.95},{"place":103,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.95},{"place":104,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":11.7},{"place":105,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.4},{"place":106,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.3},{"place":107,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":6.31}]},{"id":"gaia-no-file","name":"GAIA (no file)","topic":"General AI tasks","description":"GAIA benchmark subset without file inputs.","url":"https://github.com/GAIA-benchmark/GAIA","leaderboard":"https://gaia-benchmark.github.io/leaderboard/","github":"https://github.com/GAIA-benchmark/GAIA","paper":"","metric":"percent","stars":"","top_model":"Step-3.5 Flash 20260204","top_percent":84.5,"top_model_id":"step-3.5-flash-20260204","top_generation":"Step 3.5 Flash","top_model_base":"Step 3.5 Flash","top_model_family":"Step","top_company":"stepfun","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":84.5},{"place":2,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":78.2},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":75.9},{"place":4,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":75.6},{"place":5,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":75.1},{"place":6,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":64.3},{"place":7,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":61.9}]},{"id":"gaia-text-only","name":"GAIA (Text Only)","topic":"General AI tasks","description":"GAIA benchmark subset restricted to text-only inputs.","url":"https://github.com/GAIA-benchmark/GAIA","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"XYZ-Aquila-mini","top_percent":97.1,"top_model_id":"xyz-aquila-mini","top_generation":"XYZ-Aquila","top_model_base":"XYZ-Aquila mini","top_model_family":"XYZ-Aquila","top_company":"xyzlab","top_open_source":1,"lower_is_better":false,"bench_models":66,"total_models":3854,"placements":[{"place":1,"model":"xyz-aquila-mini","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":97.1},{"place":2,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":96},{"place":3,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":95.1},{"place":4,"model":"arex-2","company":"baai","family":"AREX","version":"AREX-2","score":92.2},{"place":5,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":88.7},{"place":6,"model":"mirothinker-h1","company":"miromind","family":"MiroThinker","version":"MiroThinker H1","score":88.5},{"place":7,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":87.4},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":87.4},{"place":9,"model":"arex-base","company":"baai","family":"AREX","version":"AREX","score":85.4},{"place":10,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.5},{"place":11,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":82.7},{"place":12,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":82.5},{"place":13,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":81.9},{"place":14,"model":"arex-turbo","company":"baai","family":"AREX","version":"AREX","score":81.6},{"place":15,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.6},{"place":16,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":80.8},{"place":17,"model":"quest-35b","company":"osunlp","family":"QUEST","version":"QUEST","score":80.8},{"place":18,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.6},{"place":19,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.6},{"place":20,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":80.3},{"place":21,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80},{"place":22,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":78.8},{"place":23,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.6},{"place":24,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78.6},{"place":25,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":76.4},{"place":26,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":75.7},{"place":27,"model":"smtl-30b","company":"oppo","family":"SMTL","version":"SMTL","score":75.7},{"place":28,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":75.1},{"place":29,"model":"websailor-v2-30b-a3b","company":"tongyi","family":"WebSailor","version":"WebSailor-V2","score":74.1},{"place":30,"model":"mirothinker-v1.0-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker-v1.0","score":73.5},{"place":31,"model":"webleaper-30b-a3b","company":"tongyi","family":"WebLeaper","version":"WebLeaper","score":73.2},{"place":32,"model":"iterresearch-30b-a3b","company":"tongyi","family":"IterResearch","version":"IterResearch","score":72.8},{"place":33,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":72},{"place":34,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":71.9},{"place":35,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.2},{"place":36,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":71.1},{"place":37,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":70.9},{"place":38,"model":"re-trac-4b","company":"microsoft","family":"RE-TRAC","version":"RE-TRAC","score":70.4},{"place":39,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":70},{"place":40,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":69.9},{"place":41,"model":"marco-deepresearch-8b","company":"alibaba","family":"Marco","version":"Marco DeepResearch","score":69.9},{"place":42,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":68.3},{"place":43,"model":"toolmind-web-3b","company":"boss","family":"Nanbeige","version":"ToolMind-Web","score":67},{"place":44,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":66.4},{"place":45,"model":"dr-venus-4b-sft","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":65.4},{"place":46,"model":"dr-venus-4b-rl","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":64.4},{"place":47,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":64.3},{"place":48,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":63.9},{"place":49,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":63.5},{"place":50,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":63.5},{"place":51,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":61.9},{"place":52,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.8},{"place":53,"model":"deepminer-32b-rl","company":"alibaba","family":"DeepMiner","version":"DeepMiner","score":58.7},{"place":54,"model":"asearcher-web-qwq-v2","company":"antgroup","family":"ASearcher","version":"ASearcher","score":58.7},{"place":55,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.3},{"place":56,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.5},{"place":57,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":57.3},{"place":58,"model":"webdancer-32b","company":"tongyi","family":"WebDancer","version":"WebDancer","score":51.5},{"place":59,"model":"offseeker-8b-dpo","company":"offseeker","family":"OffSeeker","version":"OffSeeker","score":51.5},{"place":60,"model":"webexplorer-8b","company":"hkust","family":"WebExplorer","version":"WebExplorer","score":50},{"place":61,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":49.5},{"place":62,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.9},{"place":63,"model":"offseeker-8b-sft","company":"offseeker","family":"OffSeeker","version":"OffSeeker","score":47.6},{"place":64,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":42.52},{"place":65,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":41.1},{"place":66,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.5},{"place":67,"model":"websailor-7b","company":"tongyi","family":"WebSailor","version":"WebSailor","score":37.9},{"place":68,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.1},{"place":69,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":26.5}]},{"id":"gaia2","name":"GAIA 2","topic":"General agent tasks","description":"Grounded agentic intelligence benchmark version 2 covering multi-tool tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ring-1T-2.5","top_percent":75,"top_model_id":"ring-1t-2.5","top_generation":"Ring 2.5","top_model_base":"Ring-1T-2.5","top_model_family":"Ring","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"ring-1t-2.5","company":"antgroup","family":"Ring","version":"Ring 2.5","score":75},{"place":2,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":68.96},{"place":3,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":55.21},{"place":4,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":43.3},{"place":5,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":42.1},{"place":6,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":40},{"place":7,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":36.4},{"place":8,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":34.8},{"place":9,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":34.6},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":25.8},{"place":11,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":20.1},{"place":12,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":18.2},{"place":13,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":12.9},{"place":14,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.6},{"place":15,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":7.4},{"place":16,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":7.4},{"place":17,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":4.4}]},{"id":"gaokao-2023-en","name":"GaoKao 2023 En","topic":"Math (exam)","description":"English translation of 2023 Chinese college entrance exam (Gaokao) math questions, used in Qwen2.5-Math / DeepSeekMath style evaluations.","url":"https://github.com/QwenLM/Qwen2.5-Math","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2409.12122","metric":"percent","stars":"","top_model":"Qwen2.5-Math-72B-Instruct","top_percent":71.9,"top_model_id":"qwen2.5-math-72b-instruct","top_generation":"Qwen2.5-Math","top_model_base":"Qwen2.5-Math 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":71.9},{"place":2,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.3},{"place":3,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":68.3},{"place":4,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":67.5},{"place":5,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":66.8},{"place":6,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66},{"place":7,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":65.7},{"place":8,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":65.5},{"place":9,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":62.1},{"place":10,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.5},{"place":11,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":59.7},{"place":12,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":58.7},{"place":13,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":58.4},{"place":14,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":56.1},{"place":15,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":54},{"place":16,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":51.9},{"place":17,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":50.1},{"place":18,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":48.8},{"place":19,"model":"numinamath-7b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":47.5},{"place":20,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":46},{"place":21,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":43.6},{"place":22,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":38.4},{"place":23,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":36.4},{"place":24,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":19.7}]},{"id":"gaokao-bench","name":"GAOKAO-Bench","topic":"Chinese exams","description":"GAOKAO benchmark measuring Chinese college entrance exam performance.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-30B-A3B-Instruct-2507","top_percent":94.53,"top_model_id":"qwen3-30b-a3b-instruct-2507","top_generation":"Qwen3","top_model_base":"Qwen3 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":93,"total_models":3854,"placements":[{"place":1,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":94.53},{"place":2,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":93.9},{"place":3,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":93.24},{"place":4,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":86.9},{"place":5,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86.12},{"place":6,"model":"yi-34b-200k","company":"01ai","family":"Yi","version":"Yi","score":83.4},{"place":7,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":82.8},{"place":8,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":81},{"place":9,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":78.7},{"place":10,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":77.3},{"place":11,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":76.9},{"place":12,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":76.5},{"place":13,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":76.3},{"place":14,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":75},{"place":15,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":74.5},{"place":16,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":73.9},{"place":17,"model":"yi-6b-200k","company":"01ai","family":"Yi","version":"Yi","score":73.9},{"place":18,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":72.3},{"place":19,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":72.2},{"place":20,"model":"skywork-13b","company":"skywork","family":"Skywork","version":"Skywork","score":68.1},{"place":21,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":68.1},{"place":22,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":67.5},{"place":23,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":67.4},{"place":24,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":67.3},{"place":25,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":66.15},{"place":26,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":65.3},{"place":27,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":63.5},{"place":28,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":63.3},{"place":29,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":62.5},{"place":30,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":62.3},{"place":31,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":62.1},{"place":32,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":62.1},{"place":33,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":61.9},{"place":34,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":61.7},{"place":35,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":60.3},{"place":36,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":59.4},{"place":37,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":59},{"place":38,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":59},{"place":39,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":58.9},{"place":40,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":58.6},{"place":41,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":58.6},{"place":42,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":58.3},{"place":43,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":58},{"place":44,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":57.7},{"place":45,"model":"xverse-7b-chat","company":"xverse","family":"XVERSE","version":"XVERSE","score":57.5},{"place":46,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":57.3},{"place":47,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":57.1},{"place":48,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":56.3},{"place":49,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":56.1},{"place":50,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":54.7},{"place":51,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54.33},{"place":52,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54.3},{"place":53,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":54.2},{"place":54,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":53.9},{"place":55,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":53.6},{"place":56,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":53.1},{"place":57,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":52.8},{"place":58,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":52.6},{"place":59,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":52.5},{"place":60,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":51.4},{"place":61,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":51.4},{"place":62,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":51.1},{"place":63,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":51.1},{"place":64,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":50.5},{"place":65,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":49.8},{"place":66,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":49.7},{"place":67,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":49.69},{"place":68,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":49.3},{"place":69,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":48.7},{"place":70,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":47.5},{"place":71,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":47.47},{"place":72,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":47.07},{"place":73,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":46.4},{"place":74,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":46.4},{"place":75,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":45.8},{"place":76,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":45.8},{"place":77,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":45.6},{"place":78,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":45.5},{"place":79,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":44.9},{"place":80,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":44.69},{"place":81,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":43},{"place":82,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":42.6},{"place":83,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":42.3},{"place":84,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":40.9},{"place":85,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":40.7},{"place":86,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":40.2},{"place":87,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":39.7},{"place":88,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":38.9},{"place":89,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":37.5},{"place":90,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":36.34},{"place":91,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":36.3},{"place":92,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":36.24},{"place":93,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":35.4},{"place":94,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":35.4},{"place":95,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":34.8},{"place":96,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":34.78},{"place":97,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":34.7},{"place":98,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":34.5},{"place":99,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":33.1},{"place":100,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":32.3},{"place":101,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.3},{"place":102,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":30.83},{"place":103,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":30.11},{"place":104,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":29.1},{"place":105,"model":"bloomz-7b1","company":"bigscience","family":"BLOOM","version":"BLOOMZ","score":28.72},{"place":106,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":28.7},{"place":107,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":28.6},{"place":108,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":28.23},{"place":109,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":27.81},{"place":110,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":27.8},{"place":111,"model":"bloom-7b1","company":"bigscience","family":"BLOOM","version":"BLOOM","score":26.96},{"place":112,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":26.8},{"place":113,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":26.54},{"place":114,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":26.4},{"place":115,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":26.3},{"place":116,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":26},{"place":117,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":25.97},{"place":118,"model":"tigerbot-7b-base","company":"tigerbot","family":"TigerBot","version":"TigerBot","score":25.94},{"place":119,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":25.3},{"place":120,"model":"vicuna-7b-v1.5","company":"lmsys","family":"Vicuna","version":"Vicuna","score":24.4},{"place":121,"model":"aquila-7b","company":"baai","family":"Aquila","version":"Aquila","score":24.39},{"place":122,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":24.24},{"place":123,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":23.98},{"place":124,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":23.3},{"place":125,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":23.2},{"place":126,"model":"ziya-llama-13b-pretrain","company":"idea-ccnl","family":"Ziya","version":"Ziya-LLaMA","score":23.17},{"place":127,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":21.41},{"place":128,"model":"open-llama-7b-v2","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA v2","score":21.41},{"place":129,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":21.3},{"place":130,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":20.4},{"place":131,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":19.8},{"place":132,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":19.8},{"place":133,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":19.1},{"place":134,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":19},{"place":135,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":18.9},{"place":136,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":18.9},{"place":137,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":18.6},{"place":138,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":18.4},{"place":139,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":18.2},{"place":140,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":16.1}]},{"id":"gaokao-math-2026","name":"Gaokao Math 2026","topic":"Math exams","description":"Five 2026 Chinese Gaokao math exams (National I, II, Beijing, Shanghai, Tianjin); average score out of 150.","url":"https://huggingface.co/datasets/XHToken/gaokao_math_2026","leaderboard":"","github":"","paper":"","metric":"points","stars":"","top_model":"Qwen3.5-9B","top_percent":135.5,"top_model_id":"qwen3.5-9b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 9B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":135.5},{"place":2,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":134.9},{"place":3,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":133.4},{"place":4,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":130.6},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":130.3},{"place":6,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":102.4}]},{"id":"gaokao-mathcloze","name":"Gaokao-MathCloze","topic":"Chinese math (exam)","description":"Fill-in-the-blank math problems from Chinese Gaokao (AGIEval).","url":"https://github.com/ruixiangcui/AGIEval","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2304.06364","metric":"percent","stars":"","top_model":"DeepSeek Math 7B","top_percent":20.3,"top_model_id":"deepseek-math-7b","top_generation":"DeepSeek Math","top_model_base":"DeepSeek Math 7B","top_model_family":"DeepSeek Math","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":20.3},{"place":2,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":11.9},{"place":3,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":11.9},{"place":4,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":5.1}]},{"id":"gaokao-mathqa","name":"Gaokao-MathQA","topic":"Chinese math (exam)","description":"Multiple-choice math problems from Chinese Gaokao (AGIEval).","url":"https://github.com/ruixiangcui/AGIEval","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2304.06364","metric":"percent","stars":"","top_model":"DeepSeek Math 7B","top_percent":35.3,"top_model_id":"deepseek-math-7b","top_generation":"DeepSeek Math","top_model_base":"DeepSeek Math 7B","top_model_family":"DeepSeek Math","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":35.3},{"place":2,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":26.2},{"place":3,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":23.6},{"place":4,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":23.4}]},{"id":"garage","name":"GaRAGe","topic":"RAG grounding","description":"Amazon's grounded RAG benchmark with human-annotated passage relevance, scoring grounded and attributed answers.","url":"","leaderboard":"","github":"https://github.com/amazon-science/GaRAGe","paper":"","metric":"percent","stars":"","top_model":"Nemotron-3.5-Bolt-E4B","top_percent":42.61,"top_model_id":"nemotron-3.5-bolt-e4b","top_generation":"Nemotron 3.5","top_model_base":"Nemotron-3.5 Bolt E4B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":42.61},{"place":2,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":40.73},{"place":3,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.73},{"place":4,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.78},{"place":5,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":30.91},{"place":6,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":25.18},{"place":7,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":24.8},{"place":8,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.66}]},{"id":"gdp-pdf","name":"GDP.pdf","topic":"Document understanding","description":"Surge AI multimodal benchmark of 100 professional prompts over information-dense PDFs; strict pass rate.","url":"https://surgehq.ai/blog/gdp-pdf-can-100b-ai-models-master-the-documents-that-run-the-world","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":40,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":33,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":40},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":37},{"place":3,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":35},{"place":4,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":34.6},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":34.2},{"place":6,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":34},{"place":7,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":33.2},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":32.2},{"place":9,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":32},{"place":10,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":30.8},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":30.7},{"place":12,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":30.6},{"place":13,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":29.8},{"place":14,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":29},{"place":15,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":28},{"place":16,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":28},{"place":17,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":27.6},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":26},{"place":19,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":24.9},{"place":20,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":24.7},{"place":21,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":22.7},{"place":22,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":22.5},{"place":23,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":22},{"place":24,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":17.2},{"place":25,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":16.7},{"place":26,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":16},{"place":27,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":11.2},{"place":28,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":11.2},{"place":29,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":8.4},{"place":30,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":7},{"place":31,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":6.6},{"place":32,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":6.2},{"place":33,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":5.8},{"place":34,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":5.2},{"place":35,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":5.2},{"place":36,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":4.6},{"place":37,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":3.6}]},{"id":"gdpval","name":"GDPVal","topic":"General capability","description":"GDPVal benchmark evaluating broad general capabilities of LLMs across diverse tasks.","url":"https://huggingface.co/datasets/openai/gdpval","leaderboard":"https://openai.com/index/gdpval/","github":"","paper":"https://cdn.openai.com/pdf/d5eb7428-c4e9-4a33-bd86-86dd4bcf12ce/GDPval.pdf","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":89.4,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":57,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89.4},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":87.9},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.9},{"place":4,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":83},{"place":5,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":83},{"place":6,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":82.7},{"place":7,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":82.7},{"place":8,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":82.3},{"place":9,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":82},{"place":10,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":80.3},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":79.3},{"place":13,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":78.8},{"place":14,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":75.8},{"place":15,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":74.9},{"place":16,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":74.1},{"place":17,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":73.7},{"place":18,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.5},{"place":19,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72.7},{"place":20,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":71.2},{"place":21,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":70.9},{"place":22,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":70.9},{"place":23,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":70.9},{"place":24,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":70.9},{"place":25,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":70.9},{"place":26,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":69.5},{"place":27,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":68.8},{"place":28,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.4},{"place":29,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":67.3},{"place":30,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":67.3},{"place":31,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":66},{"place":32,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":63.5},{"place":33,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.1},{"place":34,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.6},{"place":35,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":59.3},{"place":36,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":59},{"place":37,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":57.5},{"place":38,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":54.7},{"place":39,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.6},{"place":40,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.5},{"place":41,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":54.4},{"place":42,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":53.5},{"place":43,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":53.1},{"place":44,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":51.4},{"place":45,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":51.2},{"place":46,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":50.6},{"place":47,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":50.4},{"place":48,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.2},{"place":49,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":47.6},{"place":50,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":47.6},{"place":51,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":47.3},{"place":52,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":46.7},{"place":53,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":38.8},{"place":54,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":38.8},{"place":55,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38},{"place":56,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37},{"place":57,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.6},{"place":58,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":34.1},{"place":59,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":28.1},{"place":60,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":27.9},{"place":61,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":25.5},{"place":62,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":24.6},{"place":63,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":24.3},{"place":64,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":13.7},{"place":65,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":12.4}]},{"id":"gdpval-rubrics","name":"GDPval (rubrics)","topic":"Professional knowledge work","description":"GDPval tasks scored pointwise against rubrics (not pairwise win rate), as reported by MiniMax.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":91.64,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":91.64},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.53},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":90.5},{"place":4,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":90.34},{"place":5,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.17},{"place":6,"model":"fx-work","company":"endless-frontier","family":"Fx","version":"Fx","score":86.66},{"place":7,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.49},{"place":8,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.4},{"place":9,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.1},{"place":10,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":84.8},{"place":11,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":82.61},{"place":12,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":80.7},{"place":13,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":79.8},{"place":14,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":79.5},{"place":15,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":78.36},{"place":16,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":75.8},{"place":17,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.7},{"place":18,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":74.8},{"place":19,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":74.31},{"place":20,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":74.3},{"place":21,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.4},{"place":22,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":70.3},{"place":23,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":69.96},{"place":24,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.5},{"place":25,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":68.3},{"place":26,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":66.4},{"place":27,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":65.1},{"place":28,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.9},{"place":29,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":57.8},{"place":30,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.7},{"place":31,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":31.5}]},{"id":"genebench","name":"GeneBench","topic":"Scientific data analysis","description":"OpenAI eval of multi-step scientific data analysis in genetics and quantitative biology, with ambiguous or flawed data and hidden confounders.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5 Pro","top_percent":33.2,"top_model_id":"gpt-5.5-pro","top_generation":"GPT-5.5","top_model_base":"GPT-5.5 Pro","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":33.2},{"place":2,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":25.6},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":25},{"place":4,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":19}]},{"id":"genebench-pro","name":"GeneBench Pro","topic":"Biology agent tasks","description":"Long-horizon genomics and quantitative-biology analysis tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":37.1,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":37.1},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":32.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":28.7},{"place":4,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":23.3},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":16},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":12},{"place":7,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":10.8},{"place":8,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":8.14},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":3.1}]},{"id":"general-tool-use","name":"General Tool Use","topic":"Tool use","description":"General tool-use benchmark covering web and API tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":78.9,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.9},{"place":2,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":78.2},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.7},{"place":4,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":73.9},{"place":5,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.9},{"place":6,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.2},{"place":7,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":70.3},{"place":8,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":68.8},{"place":9,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":68.7},{"place":10,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":64.8},{"place":11,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":64.7},{"place":12,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":64.4},{"place":13,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":63.4},{"place":14,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.3},{"place":15,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.9},{"place":16,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":55.5},{"place":17,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.2},{"place":18,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":51.7}]},{"id":"genomeqa","name":"GenomeQA","topic":"Genomics","description":"DNA sequence understanding QA (enhancers, splice sites, organism, histone marks, TF binding, motifs).","url":"https://huggingface.co/HuggingFaceBio/Carbon-X","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol (max)","top_percent":67.2,"top_model_id":"gpt-6.1-sol-max","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":67.2},{"place":2,"model":"carbon-x","company":"huggingface","family":"Carbon","version":"Carbon","score":63.6},{"place":3,"model":"gemini-4-argon-low","company":"google","family":"Gemini","version":"Gemini 4","score":63.1},{"place":4,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":62.2},{"place":5,"model":"kimi-k3-low","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":52},{"place":6,"model":"deepseek-v4.1-flash-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":49.7},{"place":7,"model":"glm-5.3-low","company":"zai","family":"GLM","version":"GLM 5.3","score":44.6}]},{"id":"geobench1","name":"GeoBench1","topic":"Geospatial reasoning","description":"Geospatial visual QA and reasoning (set 1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-4.5V","top_percent":79.7,"top_model_id":"glm-4.5v","top_generation":"GLM 4.5V","top_model_base":"GLM 4.5V","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":79.7},{"place":2,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":76},{"place":3,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":72.9},{"place":4,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":57.5},{"place":5,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":48}]},{"id":"global-mgsm","name":"GlobalMGSM","topic":"Math (multilingual)","description":"Global multilingual grade school math word problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-4B","top_percent":60.9,"top_model_id":"qwen3-4b","top_generation":"Qwen3","top_model_base":"Qwen3 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.9},{"place":2,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":55.4},{"place":3,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":52.8},{"place":4,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":49.6}]},{"id":"global-mmlu","name":"Global-MMLU","topic":"Multi-domain knowledge (global)","description":"Full Global-MMLU evaluation across diverse languages and regions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":94.3,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":46,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":94.3},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":94},{"place":3,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":93.2},{"place":4,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":92.1},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":90.4},{"place":6,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":89.9},{"place":7,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":87.8},{"place":8,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":86.56},{"place":9,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.7},{"place":10,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":83.6},{"place":11,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83},{"place":12,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":82},{"place":13,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":81.9},{"place":14,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":80.7},{"place":15,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":77.8},{"place":16,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":77.7},{"place":17,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":77.4},{"place":18,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":76.6},{"place":19,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.6},{"place":20,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":73.3},{"place":21,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.2},{"place":22,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":69.6},{"place":23,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":69.2},{"place":24,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":67.4},{"place":25,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":66.5},{"place":26,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.1},{"place":27,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":65},{"place":28,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":62.9},{"place":29,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":59.4},{"place":30,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":58.7},{"place":31,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":58.2},{"place":32,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":57},{"place":33,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":56.9},{"place":34,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":55.5},{"place":35,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":55.4},{"place":36,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":55},{"place":37,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":53.5},{"place":38,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.54},{"place":39,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.5},{"place":40,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":49},{"place":41,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":48.7},{"place":42,"model":"llama-3.1-3b","company":"meta","family":"Llama","version":"Llama 3.1","score":46.8},{"place":43,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":46.4},{"place":44,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.3},{"place":45,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.9},{"place":46,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":44.9},{"place":47,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":43},{"place":48,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":38.4}]},{"id":"global-mmlu-lite","name":"Global-MMLU-Lite","topic":"Multi-domain knowledge (global)","description":"Lightweight global variant of MMLU covering diverse languages and regions.","url":"https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":93.3,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":93.3},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":92.7},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.1},{"place":4,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":92},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":91.8},{"place":6,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":90.7},{"place":7,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.13},{"place":8,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90},{"place":9,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":89.4},{"place":10,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.3},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.2},{"place":12,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":89.2},{"place":13,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":88.7},{"place":14,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":88.7},{"place":15,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":88.4},{"place":16,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.4},{"place":17,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":87.34},{"place":18,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":86.9},{"place":19,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":86.7},{"place":20,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":86.6},{"place":21,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":86.5},{"place":22,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":85.81},{"place":23,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.72},{"place":24,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85.63},{"place":25,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.6},{"place":26,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.59},{"place":27,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84},{"place":28,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":83.9},{"place":29,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":83.5},{"place":30,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":83.4},{"place":31,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.4},{"place":32,"model":"midm-k-2.5-pro","company":"kt","family":"Mi:dm","version":"Mi:dm K 2.5","score":83},{"place":33,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.94},{"place":34,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":80.8},{"place":35,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":79.25},{"place":36,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":75.53},{"place":37,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":75.1},{"place":38,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":74.94},{"place":39,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":74.78},{"place":40,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.62},{"place":41,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.47},{"place":42,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.97},{"place":43,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":73.94},{"place":44,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":73.7},{"place":45,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":69.5},{"place":46,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":68.6},{"place":47,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":64.8},{"place":48,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":54.5},{"place":49,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":53.5},{"place":50,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":41.9},{"place":51,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":34.2},{"place":52,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":33.1},{"place":53,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":23.5}]},{"id":"global-piqa","name":"Global PIQA","topic":"Commonsense reasoning across 100 Languages and Cultures","description":"Physical commonsense reasoning benchmark spanning 100 languages and diverse cultural contexts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Flash","top_percent":95.6,"top_model_id":"gemini-3-flash","top_generation":"Gemini 3","top_model_base":"Gemini 3 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":55,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":95.6},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":95},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":93.9},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":93.9},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.4},{"place":6,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":93.2},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.2},{"place":8,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":92.8},{"place":9,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":92.3},{"place":10,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":92.1},{"place":11,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":91.6},{"place":12,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91.6},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.5},{"place":14,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":91.4},{"place":15,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":91.2},{"place":16,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.2},{"place":17,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":90.9},{"place":18,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":90.9},{"place":19,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.5},{"place":20,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":90.3},{"place":21,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.2},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.1},{"place":23,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.1},{"place":24,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.8},{"place":25,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.8},{"place":26,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":89.5},{"place":27,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":89.4},{"place":28,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":89.3},{"place":29,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":89.2},{"place":30,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":89.2},{"place":31,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":88.5},{"place":32,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.4},{"place":33,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.5},{"place":34,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.6},{"place":35,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":86},{"place":36,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.7},{"place":37,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":85.6},{"place":38,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":84.2},{"place":39,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":84.1},{"place":40,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":83.5},{"place":41,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.2},{"place":42,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":82.2},{"place":43,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.2},{"place":44,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":80.2},{"place":45,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":79.8},{"place":46,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.6},{"place":47,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.9},{"place":48,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.5},{"place":49,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":70.7},{"place":50,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.3},{"place":51,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":69},{"place":52,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":68.3},{"place":53,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.8},{"place":54,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":63.3},{"place":55,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63.1},{"place":56,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":62},{"place":57,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":61.3},{"place":58,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":60.8},{"place":59,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.4},{"place":60,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":50.6}]},{"id":"glue","name":"GLUE","topic":"Multi-task NLU","description":"General Language Understanding Evaluation.","url":"https://gluebenchmark.com/","leaderboard":"https://gluebenchmark.com/leaderboard","github":"","paper":"","metric":"percent","stars":"","top_model":"Turing ULR v6","top_percent":91.3,"top_model_id":"turing-ulr-v6","top_generation":"Turing","top_model_base":"Turing ULR v6","top_model_family":"Turing","top_company":"microsoft","top_open_source":0,"lower_is_better":false,"bench_models":76,"total_models":3854,"placements":[{"place":1,"model":"turing-ulr-v6","company":"microsoft","family":"Turing","version":"Turing","score":91.3},{"place":2,"model":"vega-v1","company":"jd","family":"Vega","version":"Vega v1","score":91.3},{"place":3,"model":"turing-nlr-v5","company":"microsoft","family":"Turing","version":"Turing NLR v5","score":91.2},{"place":4,"model":"deberta-plus-clever","company":"dirl","family":"DeBERTa","version":"DeBERTa + CLEVER","score":91.1},{"place":5,"model":"ernie","company":"baidu","family":"ERNIE","version":"ERNIE","score":91.1},{"place":6,"model":"structbert-plus-clever","company":"alibaba","family":"StructBERT","version":"StructBERT + CLEVER","score":91},{"place":7,"model":"salsa","company":"unknown","family":"SALSA","version":"SALSA","score":90.8},{"place":8,"model":"deberta-turingnlrv4","company":"microsoft","family":"DeBERTa","version":"DeBERTa / TuringNLRv4","score":90.8},{"place":9,"model":"macalbert-plus-dkm","company":"iflytek","family":"MacALBERT","version":"MacALBERT + DKM","score":90.7},{"place":10,"model":"albert-plus-daaf-plus-nas","company":"ping-an","family":"ALBERT","version":"ALBERT + DAAF + NAS","score":90.6},{"place":11,"model":"t5","company":"google","family":"T5","version":"T5","score":90.3},{"place":12,"model":"mt-dnn-smart","company":"microsoft","family":"MT","version":"MT-DNN-SMART","score":89.9},{"place":13,"model":"nezha-large","company":"huawei","family":"NEZHA","version":"NEZHA-Large","score":89.8},{"place":14,"model":"anna","company":"lg","family":"ANNA","version":"ANNA","score":89.8},{"place":15,"model":"funnel-transformer-ensemble-b10-10-10h1024","company":"cmu","family":"Funnel","version":"Funnel-Transformer (Ensemble B10-10-10H1024)","score":89.7},{"place":16,"model":"electra-large-plus-standard-tricks","company":"google","family":"ELECTRA","version":"ELECTRA-Large + Standard Tricks","score":89.4},{"place":17,"model":"2digit-lanet","company":"unknown","family":"2digit","version":"2digit LANet","score":89.3},{"place":18,"model":"dropattack-roberta-large","company":"ncku","family":"DropAttack","version":"DropAttack-RoBERTa-large","score":88.8},{"place":19,"model":"freelb-roberta-ensemble","company":"microsoft","family":"FreeLB","version":"FreeLB-RoBERTa (ensemble)","score":88.4},{"place":20,"model":"hire-roberta","company":"sjtu","family":"HIRE","version":"HIRE-RoBERTa","score":88.3},{"place":21,"model":"electra-large-m-bert4keras","company":"unknown","family":"ELECTRA","version":"ELECTRA-large-M (bert4keras)","score":88.3},{"place":22,"model":"roberta","company":"meta","family":"RoBERTa","version":"RoBERTa","score":88.1},{"place":23,"model":"mt-dnn-ensemble","company":"microsoft","family":"MT","version":"MT-DNN-ensemble","score":87.6},{"place":24,"model":"electra-large-newscl-single","company":"unknown","family":"ELECTRA","version":"ELECTRA-Large-NewSCL(single)","score":85.6},{"place":25,"model":"bort-alexa-ai","company":"amazon","family":"Bort","version":"Bort (Alexa AI)","score":83.6},{"place":26,"model":"convbert-base","company":"lv-nus","family":"ConvBERT","version":"ConvBERT base","score":83.2},{"place":27,"model":"snorkel-metal","company":"stanford","family":"Snorkel","version":"Snorkel MeTaL","score":83.2},{"place":28,"model":"xlm-english-only","company":"meta","family":"XLM","version":"XLM (English only)","score":83.1},{"place":29,"model":"convbert-base-paddle-v1.1","company":"independent","family":"ConvBERT","version":"ConvBERT-base-paddle-v1.1","score":83.1},{"place":30,"model":"robertamoe","company":"unknown","family":"robertamoe","version":"robertamoe","score":83},{"place":31,"model":"sembert","company":"sjtu","family":"SemBERT","version":"SemBERT","score":82.9},{"place":32,"model":"mpnet-base-paddle","company":"independent","family":"mpnet","version":"mpnet-base-paddle","score":82.9},{"place":33,"model":"spanbert-single-task-training","company":"meta","family":"SpanBERT","version":"SpanBERT (single-task training)","score":82.8},{"place":34,"model":"distilroberta-plus-gal-6-layer-transformer-single-model","company":"gal-team","family":"distilRoBERTa+GAL","version":"distilRoBERTa+GAL (6-layer transformer single model)","score":82.6},{"place":35,"model":"bert-plus-bam","company":"google","family":"BERT","version":"BERT + BAM","score":82.3},{"place":36,"model":"span-extractive-bert-on-stilts","company":"salesforce","family":"Span","version":"Span-Extractive BERT on STILTs","score":82.3},{"place":37,"model":"lv-bert-base","company":"lv-nus","family":"LV","version":"LV-BERT-base","score":82.1},{"place":38,"model":"bert-on-stilts","company":"nyu","family":"BERT","version":"BERT on STILTs","score":82},{"place":39,"model":"robustroberta","company":"unknown","family":"RobustRoBERTa","version":"RobustRoBERTa","score":81.9},{"place":40,"model":"warp-with-roberta","company":"yerevann","family":"WARP","version":"WARP with RoBERTa","score":81.6},{"place":41,"model":"bigs-128-1000k","company":"cornell","family":"Bigs","version":"Bigs-128-1000k","score":81.5},{"place":42,"model":"combinedkd-tinyroberta-6-layer-82m-parameters-mate-kd-plus-annealingkd","company":"huawei","family":"CombinedKD","version":"CombinedKD-TinyRoBERTa (6 layer 82M parameters, MATE-KD + AnnealingKD)","score":81.5},{"place":43,"model":"segabert-large","company":"waterloo","family":"segaBERT","version":"segaBERT-large","score":81.4},{"place":44,"model":"u-pmlm-r-huawei-noah-s-ark-lab","company":"huawei","family":"u","version":"u-PMLM-R (Huawei Noah's Ark Lab)","score":81.3},{"place":45,"model":"ambert-base","company":"bytedance","family":"AMBERT","version":"AMBERT-BASE","score":81},{"place":46,"model":"routed-berts","company":"unknown","family":"Routed","version":"Routed BERTs","score":80.7},{"place":47,"model":"cert","company":"ucsd","family":"CERT","version":"CERT","score":80.7},{"place":48,"model":"bert-24-layers-16-heads-1024-hidden","company":"google","family":"BERT:","version":"BERT: 24-layers, 16-heads, 1024-hidden","score":80.5},{"place":49,"model":"kerasnlp-xlm-r","company":"google","family":"KerasNLP","version":"KerasNLP XLM-R","score":80.4},{"place":50,"model":"kerasnlp-roberta","company":"google","family":"KerasNLP","version":"KerasNLP RoBERTa","score":80.4},{"place":51,"model":"multiple-adapter-t5-base","company":"unknown","family":"MULTIPLE_ADAPTER_T5_BASE","version":"MULTIPLE_ADAPTER_T5_BASE","score":80.3},{"place":52,"model":"hf-bert-large-uncased-default-fine-tuning","company":"uci","family":"HF","version":"HF bert-large-uncased (default fine-tuning)","score":80.2},{"place":53,"model":"bert-plus-single-task-adapters","company":"google","family":"BERT","version":"BERT + Single-task Adapters","score":80.2},{"place":54,"model":"ki-bert","company":"embibe","family":"KI","version":"KI-BERT","score":80},{"place":55,"model":"elasticbert-large-12l","company":"fudan","family":"elasticbert","version":"elasticbert-large-12L","score":79.9},{"place":56,"model":"roberta-large-12l","company":"fudan","family":"roberta","version":"roberta-large-12L","score":79.8},{"place":57,"model":"macaron-net-base","company":"pku","family":"Macaron","version":"Macaron Net-base","score":79.7},{"place":58,"model":"gat-bert-base","company":"unknown","family":"GAT","version":"GAT-bert-base","score":79.6},{"place":59,"model":"wt-vat-bert-base","company":"unknown","family":"WT","version":"WT-VAT-BERT (Base)","score":79.5},{"place":60,"model":"fd-cmic-plus-cm-mic-best-mnli-mm","company":"unknown","family":"FD","version":"FD-CMIC+CM-MIC best MNLI-mm","score":79.3},{"place":61,"model":"bert-n-pals","company":"unknown","family":"Bert","version":"Bert-n-Pals","score":79.1},{"place":62,"model":"deeppavlov-multitask-palbert","company":"deeppavlov","family":"DeepPavlov","version":"DeepPavlov Multitask PalBert","score":78.8},{"place":63,"model":"bert-emd-6-layer-single-model-no-da","company":"siat","family":"BERT","version":"BERT-EMD(6-layer; Single model; No DA)","score":78.7},{"place":64,"model":"sesamebert-base","company":"delta-electronics","family":"SesameBERT","version":"SesameBERT-Base","score":78.6},{"place":65,"model":"reptiledistil","company":"ynu","family":"ReptileDistil","version":"ReptileDistil","score":78.5},{"place":66,"model":"mobilebert","company":"google","family":"MobileBERT","version":"MobileBERT","score":78.5},{"place":67,"model":"stackingbert-base","company":"pku","family":"StackingBERT","version":"StackingBERT-Base","score":78.4},{"place":68,"model":"tinybert-6-layer-single-model","company":"huawei","family":"TinyBERT","version":"TinyBERT (6-layer; Single model)","score":78.1},{"place":69,"model":"squeezebert-4.3x-faster-than-bert-base-on-smartphone","company":"berkeley","family":"SqueezeBERT","version":"SqueezeBERT (4.3x faster than BERT-base on smartphone)","score":78.1},{"place":70,"model":"camtl","company":"mila","family":"CAMTL","version":"CAMTL","score":77.9},{"place":71,"model":"krisfu","company":"independent","family":"KRISFU","version":"KRISFU","score":77.8},{"place":72,"model":"memel-tune","company":"hkust","family":"MEmeL","version":"MEmeL-TUNE","score":77.6},{"place":73,"model":"pocket-glue","company":"independent","family":"Pocket","version":"Pocket GLUE","score":77.6},{"place":74,"model":"pavan-neerudu-bert","company":"independent","family":"Pavan","version":"Pavan Neerudu - BERT","score":77.6},{"place":75,"model":"bert-of-theseus-6-layer-single-model","company":"microsoft","family":"BERT","version":"BERT-of-Theseus (6-layer; single model)","score":77.1},{"place":76,"model":"el-bert-6-layer-single-model","company":"unknown","family":"EL","version":"EL-BERT(6-Layer, Single model)","score":75.6}]},{"id":"gorilla-api-bench","name":"Gorilla Benchmark API Bench","topic":"Tool use","description":"Gorilla API Bench tool-use evaluation.","url":"https://gorilla.cs.berkeley.edu/benchmark","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 3.1 405B","top_percent":35.3,"top_model_id":"llama-3.1-405b","top_generation":"Llama 3.1","top_model_base":"Llama 3.1 405B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":35.3},{"place":2,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":29.7},{"place":3,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":14.7},{"place":4,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":8.2},{"place":5,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":1.7}]},{"id":"gpqa","name":"GPQA","topic":"Graduate-level QA","description":"Graduate-level question answering evaluating advanced reasoning.","url":"https://gpqa.github.io/","leaderboard":"","github":"https://github.com/idavidrein/gpqa","paper":"https://arxiv.org/abs/2311.12022","metric":"percent","stars":"406","top_model":"GPT-5.2 Thinking","top_percent":92.4,"top_model_id":"gpt-5.2-thinking","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":323,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":92.4},{"place":2,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":92.4},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.9},{"place":4,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":91},{"place":5,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.5},{"place":6,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":88.4},{"place":7,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.4},{"place":8,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.8},{"place":9,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.6},{"place":10,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":87.4},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.1},{"place":12,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87},{"place":13,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87},{"place":14,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.6},{"place":15,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":86.6},{"place":16,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":86.1},{"place":17,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":85.1},{"place":18,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.4},{"place":19,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.8},{"place":20,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.8},{"place":21,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":82.4},{"place":22,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":81.4},{"place":23,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.1},{"place":24,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":81},{"place":25,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":81},{"place":26,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":80.5},{"place":27,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":80.1},{"place":28,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":79.9},{"place":29,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":79.9},{"place":30,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.23},{"place":31,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.6},{"place":32,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":77.7},{"place":33,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.5},{"place":34,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":77.5},{"place":35,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":77.2},{"place":36,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.2},{"place":37,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":77},{"place":38,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":75.25},{"place":39,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75},{"place":40,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.4},{"place":41,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":74.4},{"place":42,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.2},{"place":43,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.4},{"place":44,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":73.3},{"place":45,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.11},{"place":46,"model":"openreasoning-nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":73.1},{"place":47,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.1},{"place":48,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.1},{"place":49,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":73.1},{"place":50,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73},{"place":51,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":72.9},{"place":52,"model":"ring-flash-linear-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":72.85},{"place":53,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.8},{"place":54,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":72.78},{"place":55,"model":"nemotron-labs-3-elastic-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.1},{"place":56,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.1},{"place":57,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":72},{"place":58,"model":"openreasoning-nemotron-14b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":71.6},{"place":59,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":71.5},{"place":60,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":71.4},{"place":61,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":71.4},{"place":62,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.1},{"place":63,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.83},{"place":64,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.7},{"place":65,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":66,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":67,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.4},{"place":68,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":70},{"place":69,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":69.9},{"place":70,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69.7},{"place":71,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.64},{"place":72,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69.6},{"place":73,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":69.16},{"place":74,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":68.4},{"place":75,"model":"qwen3-32b-thinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":68.4},{"place":76,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.4},{"place":77,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":67.4},{"place":78,"model":"ring-mini-sparse-2.0-exp","company":"antgroup","family":"Ring","version":"Ring 2.0","score":67.3},{"place":79,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.3},{"place":80,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":67.3},{"place":81,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":67.3},{"place":82,"model":"gka-primed-hqwen3-32b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":67.3},{"place":83,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.2},{"place":84,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":67.12},{"place":85,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":66.9},{"place":86,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":66.67},{"place":87,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":66.41},{"place":88,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":65.4},{"place":89,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":64.14},{"place":90,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":64},{"place":91,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":62.9},{"place":92,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":62.72},{"place":93,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":62.31},{"place":94,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":61.98},{"place":95,"model":"gka-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":61.81},{"place":96,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":61.8},{"place":97,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.8},{"place":98,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.5},{"place":99,"model":"gdn-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":61.49},{"place":100,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.4},{"place":101,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":61.2},{"place":102,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":61.1},{"place":103,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":104,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":59.6},{"place":105,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":59.41},{"place":106,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":59.4},{"place":107,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":59.38},{"place":108,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":58.5},{"place":109,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":58.1},{"place":110,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":57.8},{"place":111,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":57.77},{"place":112,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":57.7},{"place":113,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":57.6},{"place":114,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.6},{"place":115,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":57.5},{"place":116,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.34},{"place":117,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":56.6},{"place":118,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":56.2},{"place":119,"model":"qwen3-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":55.9},{"place":120,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":55.7},{"place":121,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":54.8},{"place":122,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.6},{"place":123,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":54.5},{"place":124,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.5},{"place":125,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.4},{"place":126,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":54.4},{"place":127,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54.14},{"place":128,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":53.6},{"place":129,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":53.28},{"place":130,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":53.2},{"place":131,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":53},{"place":132,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":52},{"place":133,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":51.9},{"place":134,"model":"qwen3-4b-saferl-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":51.2},{"place":135,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.1},{"place":136,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":51.1},{"place":137,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":50.9},{"place":138,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":50.7},{"place":139,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":50.4},{"place":140,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.22},{"place":141,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.22},{"place":142,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":50.1},{"place":143,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":50},{"place":144,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":49.7},{"place":145,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.7},{"place":146,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.5},{"place":147,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.49},{"place":148,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":49.3},{"place":149,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.1},{"place":150,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49},{"place":151,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":48.6},{"place":152,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":48.6},{"place":153,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":48.36},{"place":154,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":48.01},{"place":155,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48},{"place":156,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":47.9},{"place":157,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":47.76},{"place":158,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":47.6},{"place":159,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":47},{"place":160,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":46.7},{"place":161,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":46.7},{"place":162,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":46.59},{"place":163,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.21},{"place":164,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":46.2},{"place":165,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":46.2},{"place":166,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.9},{"place":167,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":45.8},{"place":168,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":45.76},{"place":169,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":45.54},{"place":170,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.5},{"place":171,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":45.5},{"place":172,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":45.45},{"place":173,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":45.1},{"place":174,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":45.1},{"place":175,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":45},{"place":176,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":44.87},{"place":177,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":44.6},{"place":178,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":44.6},{"place":179,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":44.42},{"place":180,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":44.4},{"place":181,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":44.3},{"place":182,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":43.94},{"place":183,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":43.8},{"place":184,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":43.8},{"place":185,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":43.5},{"place":186,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":43.43},{"place":187,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":43.1},{"place":188,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":43.1},{"place":189,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":42.5},{"place":190,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":42.4},{"place":191,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":42.4},{"place":192,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.3},{"place":193,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":42.18},{"place":194,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":41.96},{"place":195,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":41.92},{"place":196,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":41.9},{"place":197,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":41.8},{"place":198,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":41.7},{"place":199,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":41.7},{"place":200,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":41.53},{"place":201,"model":"lfm2-2.6b-exp","company":"liquidai","family":"LFM","version":"LFM2","score":41.31},{"place":202,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":41.3},{"place":203,"model":"qwen3-4b-saferl","company":"qwen","family":"Qwen","version":"Qwen3","score":40.8},{"place":204,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":40.63},{"place":205,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":40.4},{"place":206,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":40.2},{"place":207,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.9},{"place":208,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":39.9},{"place":209,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":39.9},{"place":210,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":39.7},{"place":211,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":39.51},{"place":212,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":39.5},{"place":213,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":39.4},{"place":214,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39},{"place":215,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":38.89},{"place":216,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":38.4},{"place":217,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":38.4},{"place":218,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":38.4},{"place":219,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":38.4},{"place":220,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":38},{"place":221,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":37.9},{"place":222,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":37.9},{"place":223,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":37.9},{"place":224,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":37.88},{"place":225,"model":"internlm2.5-20b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":37.88},{"place":226,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37.67},{"place":227,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":37.4},{"place":228,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":37.4},{"place":229,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":37.3},{"place":230,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":36.9},{"place":231,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":36.8},{"place":232,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36.8},{"place":233,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":36.6},{"place":234,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":36.49},{"place":235,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":36.4},{"place":236,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36.4},{"place":237,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36.4},{"place":238,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":36.4},{"place":239,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":36.33},{"place":240,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":36.3},{"place":241,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":36.3},{"place":242,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":36},{"place":243,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":36},{"place":244,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":35.9},{"place":245,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":35.7},{"place":246,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":35.7},{"place":247,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":35.7},{"place":248,"model":"glm-4-0116","company":"zai","family":"GLM","version":"GLM 4","score":35.7},{"place":249,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.6},{"place":250,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.6},{"place":251,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":35.35},{"place":252,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":35.3},{"place":253,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":34.9},{"place":254,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":34.85},{"place":255,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":34.85},{"place":256,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":34.85},{"place":257,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":34.85},{"place":258,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":34.6},{"place":259,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.31},{"place":260,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":34.3},{"place":261,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":34.3},{"place":262,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":34.3},{"place":263,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":34.3},{"place":264,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":34.3},{"place":265,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":34.2},{"place":266,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":34},{"place":267,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":33.98},{"place":268,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":33.89},{"place":269,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":33.84},{"place":270,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":33.8},{"place":271,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":33.5},{"place":272,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":33.39},{"place":273,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":33.3},{"place":274,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":33.26},{"place":275,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":33.22},{"place":276,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":33},{"place":277,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":32.8},{"place":278,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.8},{"place":279,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":32.8},{"place":280,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":32.8},{"place":281,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":32.8},{"place":282,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":32.72},{"place":283,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":32.59},{"place":284,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":32.3},{"place":285,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":32.2},{"place":286,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":32.15},{"place":287,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":32.1},{"place":288,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":32.1},{"place":289,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":32.1},{"place":290,"model":"apertus-v1.5-8b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":32.1},{"place":291,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":31.99},{"place":292,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":31.82},{"place":293,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":31.82},{"place":294,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":31.8},{"place":295,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":31.8},{"place":296,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":31.79},{"place":297,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":31.7},{"place":298,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":31.6},{"place":299,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":31.5},{"place":300,"model":"lfm2-1.2b","company":"liquidai","family":"LFM","version":"LFM2","score":31.47},{"place":301,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":31.31},{"place":302,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":31.3},{"place":303,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":31.3},{"place":304,"model":"internlm2.5-7b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":31.3},{"place":305,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":31.3},{"place":306,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":31.21},{"place":307,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":31.11},{"place":308,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":30.8},{"place":309,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":30.8},{"place":310,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":30.8},{"place":311,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":30.6},{"place":312,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":30.4},{"place":313,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":30.3},{"place":314,"model":"aquif-3.5-a0.6b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":30.2},{"place":315,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":30.2},{"place":316,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":30.14},{"place":317,"model":"apertus-v1.5-70b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":30.1},{"place":318,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":30},{"place":319,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":29.95},{"place":320,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":29.8},{"place":321,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":29.8},{"place":322,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":29.8},{"place":323,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":29.8},{"place":324,"model":"nemotron-flash-3b","company":"nvidia","family":"Nemotron Flash","version":"Nemotron Flash","score":29.54},{"place":325,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.51},{"place":326,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":29.3},{"place":327,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":29.3},{"place":328,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":29.29},{"place":329,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":29.2},{"place":330,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.19},{"place":331,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":28.99},{"place":332,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":28.94},{"place":333,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":28.84},{"place":334,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":28.8},{"place":335,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":28.8},{"place":336,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":28.69},{"place":337,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28.69},{"place":338,"model":"aquif-3-0.4b","company":"aquif","family":"Aquif","version":"Aquif 3","score":28.5},{"place":339,"model":"lfm2-700m","company":"liquidai","family":"LFM","version":"LFM2","score":28.48},{"place":340,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":28.3},{"place":341,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":28.3},{"place":342,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":28.3},{"place":343,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":28.28},{"place":344,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":28.12},{"place":345,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":28.1},{"place":346,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.02},{"place":347,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":27.9},{"place":348,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":27.9},{"place":349,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":27.8},{"place":350,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":27.8},{"place":351,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":27.8},{"place":352,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.72},{"place":353,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":27.6},{"place":354,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":27.46},{"place":355,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":27.3},{"place":356,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":27.2},{"place":357,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":27.2},{"place":358,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":27.2},{"place":359,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.85},{"place":360,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":26.8},{"place":361,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":26.76},{"place":362,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":26.7},{"place":363,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":26.6},{"place":364,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":26.59},{"place":365,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":26.57},{"place":366,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":26.56},{"place":367,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":26.46},{"place":368,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":26.34},{"place":369,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":26.31},{"place":370,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.3},{"place":371,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.26},{"place":372,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":26.1},{"place":373,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":25.9},{"place":374,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.84},{"place":375,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":25.8},{"place":376,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":25.7},{"place":377,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":25.66},{"place":378,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":25.3},{"place":379,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":25.3},{"place":380,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.8},{"place":381,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":24.7},{"place":382,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":24.24},{"place":383,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":24.24},{"place":384,"model":"internlm2.5-1.8b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":24.24},{"place":385,"model":"internlm2-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":24.24},{"place":386,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.2},{"place":387,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":23.84},{"place":388,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":23.7},{"place":389,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":23.7},{"place":390,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":23.13},{"place":391,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":22.14},{"place":392,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":22.1},{"place":393,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":21.72},{"place":394,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":21.2},{"place":395,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":21.07},{"place":396,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":20.7},{"place":397,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":17.6},{"place":398,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":16.57},{"place":399,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":11.34},{"place":400,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":10.5},{"place":401,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":9.6},{"place":402,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":9.3},{"place":403,"model":"llama-spark-8b","company":"arcee","family":"Llama Spark","version":"Llama Spark 8B","score":6.6},{"place":404,"model":"falcon-e-1b-base","company":"tii","family":"Falcon","version":"Falcon E","score":2.8},{"place":405,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0}]},{"id":"gpqa-diamond","name":"GPQA-diamond","topic":"Graduate-level QA","description":"Hard subset of GPQA (diamond level).","url":"https://gpqa.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":96,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":634,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":96},{"place":2,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":95.5},{"place":3,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":95.5},{"place":4,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":95.3},{"place":5,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":94.6},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":94.6},{"place":7,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":94.5},{"place":8,"model":"darwin-180b-rsi","company":"finalbench","family":"Darwin","version":"Darwin","score":94.44},{"place":9,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":94.4},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":94.3},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":94.2},{"place":12,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":94.1},{"place":13,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":94.1},{"place":14,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":94.1},{"place":15,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":93.9},{"place":16,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":93.7},{"place":17,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":93.7},{"place":18,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":93.6},{"place":19,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":93.6},{"place":20,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93.5},{"place":21,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":93.5},{"place":22,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":93.5},{"place":23,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":93.4},{"place":24,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":93.2},{"place":25,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":93.2},{"place":26,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":93.2},{"place":27,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":93},{"place":28,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":93},{"place":29,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":92.9},{"place":30,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":92.9},{"place":31,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":92.9},{"place":32,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":92.9},{"place":33,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":92.8},{"place":34,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":92.8},{"place":35,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":92.8},{"place":36,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":92.7},{"place":37,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":92.7},{"place":38,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":92.6},{"place":39,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":92.6},{"place":40,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":92.6},{"place":41,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":92.4},{"place":42,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":92.4},{"place":43,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":92.4},{"place":44,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":92.4},{"place":45,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":92.4},{"place":46,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":92.4},{"place":47,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":92.4},{"place":48,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":92.4},{"place":49,"model":"interfaze","company":"interfaze","family":"Interfaze","version":"Interfaze 1","score":92.4},{"place":50,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":92.3},{"place":51,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":92.3},{"place":52,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":92.3},{"place":53,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":92.2},{"place":54,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":92},{"place":55,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":92},{"place":56,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.9},{"place":57,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.9},{"place":58,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":91.9},{"place":59,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.7},{"place":60,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":91.7},{"place":61,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.4},{"place":62,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.3},{"place":63,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.3},{"place":64,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":91.3},{"place":65,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":91.2},{"place":66,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":91.2},{"place":67,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":91.1},{"place":68,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":91.1},{"place":69,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":91.1},{"place":70,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":91.1},{"place":71,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91},{"place":72,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":91},{"place":73,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":91},{"place":74,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":91},{"place":75,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":90.9},{"place":76,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":90.9},{"place":77,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.8},{"place":78,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":90.7},{"place":79,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":90.7},{"place":80,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":90.7},{"place":81,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":90.6},{"place":82,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":90.6},{"place":83,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":90.5},{"place":84,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":90.5},{"place":85,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.5},{"place":86,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":90.5},{"place":87,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":90.4},{"place":88,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90.4},{"place":89,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":90.4},{"place":90,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":90.3},{"place":91,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.1},{"place":92,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.1},{"place":93,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":90.1},{"place":94,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":90},{"place":95,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":90},{"place":96,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":90},{"place":97,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.9},{"place":98,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.9},{"place":99,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":89.9},{"place":100,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":89.9},{"place":101,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":89.8},{"place":102,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":89.7},{"place":103,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.6},{"place":104,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.6},{"place":105,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":89.6},{"place":106,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":89.52},{"place":107,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":89.5},{"place":108,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":89.5},{"place":109,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":89.5},{"place":110,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":89.5},{"place":111,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":89.5},{"place":112,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":89.5},{"place":113,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":89.46},{"place":114,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":89.4},{"place":115,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.4},{"place":116,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.3},{"place":117,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":89.23},{"place":118,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":89.2},{"place":119,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.2},{"place":120,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":89.2},{"place":121,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.1},{"place":122,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":89},{"place":123,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":89},{"place":124,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":88.9},{"place":125,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":88.9},{"place":126,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.9},{"place":127,"model":"nemotron-3.5-bolt-74b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":88.83},{"place":128,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.8},{"place":129,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":88.64},{"place":130,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":88.6},{"place":131,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":88.57},{"place":132,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":88.5},{"place":133,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":88.5},{"place":134,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.4},{"place":135,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":88.4},{"place":136,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":88.38},{"place":137,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":88.1},{"place":138,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":88.1},{"place":139,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.1},{"place":140,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":88.1},{"place":141,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":88.1},{"place":142,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.1},{"place":143,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":88},{"place":144,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.9},{"place":145,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":87.9},{"place":146,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.8},{"place":147,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":87.7},{"place":148,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.6},{"place":149,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.6},{"place":150,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":87.5},{"place":151,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.4},{"place":152,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":87.4},{"place":153,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":87.4},{"place":154,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":87.3},{"place":155,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":87.2},{"place":156,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":87.2},{"place":157,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.1},{"place":158,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87},{"place":159,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87},{"place":160,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87},{"place":161,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":87},{"place":162,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87},{"place":163,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":86.9},{"place":164,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":86.9},{"place":165,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":86.9},{"place":166,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":86.9},{"place":167,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":86.9},{"place":168,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":86.9},{"place":169,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":86.8},{"place":170,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.7},{"place":171,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.7},{"place":172,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.6},{"place":173,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.4},{"place":174,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":86.4},{"place":175,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":86.36},{"place":176,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":86.36},{"place":177,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":86.3},{"place":178,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":86.2},{"place":179,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":86.2},{"place":180,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":86.2},{"place":181,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":86},{"place":182,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86},{"place":183,"model":"interfaze-1.1-lite","company":"interfaze","family":"Interfaze","version":"Interfaze 1.1","score":85.9},{"place":184,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":85.89},{"place":185,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.8},{"place":186,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":85.7},{"place":187,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":85.7},{"place":188,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":85.7},{"place":189,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.7},{"place":190,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":85.7},{"place":191,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.7},{"place":192,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":85.6},{"place":193,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":85.6},{"place":194,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":85.6},{"place":195,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.5},{"place":196,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85.4},{"place":197,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":85.4},{"place":198,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.35},{"place":199,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":85.2},{"place":200,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.2},{"place":201,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":85.1},{"place":202,"model":"agnes-3.0-flash-preview","company":"agnes","family":"Agnes","version":"Agnes 3.0","score":85.05},{"place":203,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":84.9},{"place":204,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":84.9},{"place":205,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":84.7},{"place":206,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":84.6},{"place":207,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.51},{"place":208,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":84.51},{"place":209,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":84.5},{"place":210,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.4},{"place":211,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":84.3},{"place":212,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.3},{"place":213,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.3},{"place":214,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":84.3},{"place":215,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":84.3},{"place":216,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.2},{"place":217,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.2},{"place":218,"model":"mai-thinking-1","company":"microsoft","family":"MAI","version":"MAI-Thinking-1","score":84.2},{"place":219,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.1},{"place":220,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":84},{"place":221,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":83.9},{"place":222,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":83.8},{"place":223,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":83.8},{"place":224,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":83.8},{"place":225,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.8},{"place":226,"model":"omnicoder-9b","company":"tesslate","family":"OmniCoder","version":"OmniCoder","score":83.8},{"place":227,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":83.7},{"place":228,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":83.7},{"place":229,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":83.7},{"place":230,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.69},{"place":231,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":83.5},{"place":232,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":83.5},{"place":233,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.4},{"place":234,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.4},{"place":235,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.4},{"place":236,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.4},{"place":237,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":83.4},{"place":238,"model":"o3","company":"openai","family":"o3","version":"o3","score":83.3},{"place":239,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":83.3},{"place":240,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":83.2},{"place":241,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.2},{"place":242,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":83},{"place":243,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83},{"place":244,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":83},{"place":245,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83},{"place":246,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":83},{"place":247,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.8},{"place":248,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.8},{"place":249,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.8},{"place":250,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":82.8},{"place":251,"model":"k2-horizon-32b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":82.8},{"place":252,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.8},{"place":253,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":82.8},{"place":254,"model":"o3","company":"openai","family":"o3","version":"o3","score":82.7},{"place":255,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":82.6},{"place":256,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":82.6},{"place":257,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":82.5},{"place":258,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":82.4},{"place":259,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":82.4},{"place":260,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.3},{"place":261,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.3},{"place":262,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":82.3},{"place":263,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":82.2},{"place":264,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":82.2},{"place":265,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":82.1},{"place":266,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":81.9},{"place":267,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.7},{"place":268,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":81.6},{"place":269,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":81.6},{"place":270,"model":"longcat-flash-thinking","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":81.5},{"place":271,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":81.4},{"place":272,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":81.3},{"place":273,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":81.3},{"place":274,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.3},{"place":275,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.1},{"place":276,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.1},{"place":277,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":81.1},{"place":278,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":81.1},{"place":279,"model":"deepseek-v3-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":81},{"place":280,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":81},{"place":281,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":81},{"place":282,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":81},{"place":283,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.93},{"place":284,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":80.9},{"place":285,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":80.9},{"place":286,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":80.81},{"place":287,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":80.81},{"place":288,"model":"k2-horizon-mova-36b-a4b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":80.8},{"place":289,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":80.7},{"place":290,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.7},{"place":291,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":80.7},{"place":292,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":80.6},{"place":293,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.6},{"place":294,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":80.52},{"place":295,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.5},{"place":296,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":80.5},{"place":297,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":80.5},{"place":298,"model":"g9v3-39a5b","company":"ai9stars","family":"G9","version":"G9v3","score":80.5},{"place":299,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.43},{"place":300,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.3},{"place":301,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.24},{"place":302,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":80.1},{"place":303,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":80.1},{"place":304,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":80.1},{"place":305,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":80},{"place":306,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":80},{"place":307,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":79.9},{"place":308,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":79.9},{"place":309,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":79.8},{"place":310,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":79.8},{"place":311,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.8},{"place":312,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.61},{"place":313,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":79.6},{"place":314,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":79.6},{"place":315,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":79.46},{"place":316,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":79.2},{"place":317,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.2},{"place":318,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":79.2},{"place":319,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":79.1},{"place":320,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":79},{"place":321,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":79},{"place":322,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":79},{"place":323,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":79},{"place":324,"model":"mercury-2.5","company":"inception","family":"Mercury","version":"Mercury 2.5","score":79},{"place":325,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":79},{"place":326,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.9},{"place":327,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":78.8},{"place":328,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":78.7},{"place":329,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.6},{"place":330,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":78.5},{"place":331,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":78.3},{"place":332,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":78.2},{"place":333,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":78.2},{"place":334,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.2},{"place":335,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":78},{"place":336,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":78},{"place":337,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":78},{"place":338,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78},{"place":339,"model":"deepseek-tng-r1t2-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T2","score":77.9},{"place":340,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.8},{"place":341,"model":"cogito-671b-v2.1","company":"deepcogito","family":"Cogito","version":"Cogito 671B v2.1","score":77.72},{"place":342,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.71},{"place":343,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":77.7},{"place":344,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":77.7},{"place":345,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":77.5},{"place":346,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":77.3},{"place":347,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":77.2},{"place":348,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.2},{"place":349,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":77.2},{"place":350,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":77.15},{"place":351,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":77.11},{"place":352,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.1},{"place":353,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.1},{"place":354,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":77.1},{"place":355,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":77.04},{"place":356,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":77},{"place":357,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":76.89},{"place":358,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":76.8},{"place":359,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":76.8},{"place":360,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.8},{"place":361,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":76.7},{"place":362,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":76.7},{"place":363,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":76.4},{"place":364,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":76.4},{"place":365,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":76.4},{"place":366,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":76.3},{"place":367,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":76.26},{"place":368,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":76.2},{"place":369,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.2},{"place":370,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":76.17},{"place":371,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":76.1},{"place":372,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":76.1},{"place":373,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":76.1},{"place":374,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":76},{"place":375,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":75.9},{"place":376,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":75.8},{"place":377,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":75.6},{"place":378,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":75.6},{"place":379,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":75.57},{"place":380,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":75.57},{"place":381,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":75.5},{"place":382,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":75.44},{"place":383,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":75.4},{"place":384,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":75.4},{"place":385,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":75.3},{"place":386,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.3},{"place":387,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":75.2},{"place":388,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":75.1},{"place":389,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75.1},{"place":390,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":75},{"place":391,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":74.98},{"place":392,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":74.9},{"place":393,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.9},{"place":394,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":74.8},{"place":395,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":74.7},{"place":396,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":74.6},{"place":397,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.6},{"place":398,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":74.43},{"place":399,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":74.42},{"place":400,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":74.33},{"place":401,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":74.2},{"place":402,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74.2},{"place":403,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.05},{"place":404,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.04},{"place":405,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":74},{"place":406,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":73.9},{"place":407,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":73.9},{"place":408,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.9},{"place":409,"model":"llama-4-behemoth","company":"meta","family":"Llama","version":"Llama 4","score":73.7},{"place":410,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":73.7},{"place":411,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":73.6},{"place":412,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":73.48},{"place":413,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.4},{"place":414,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.4},{"place":415,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.4},{"place":416,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":73.4},{"place":417,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.4},{"place":418,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":73.3},{"place":419,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":73.3},{"place":420,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":73.2},{"place":421,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.2},{"place":422,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":73.2},{"place":423,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":73.1},{"place":424,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73},{"place":425,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73},{"place":426,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":73},{"place":427,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73},{"place":428,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":72.98},{"place":429,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72.9},{"place":430,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.8},{"place":431,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":72.7},{"place":432,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":72.6},{"place":433,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":72.42},{"place":434,"model":"nemotron-labs-dory1.0-4b","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":72.41},{"place":435,"model":"golongrl-30b-a3b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":72.3},{"place":436,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":72.3},{"place":437,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":72.2},{"place":438,"model":"nemotron-labs-dory1.0-4b-4loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":72.16},{"place":439,"model":"deepseek-tng-r1t-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T","score":72},{"place":440,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":71.9},{"place":441,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":71.7},{"place":442,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":71.5},{"place":443,"model":"deepseek-r1-0120","company":"deepseek","family":"DeepSeek","version":"0120","score":71.5},{"place":444,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":71.5},{"place":445,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":71.5},{"place":446,"model":"magistral-medium-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":71.46},{"place":447,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":71.46},{"place":448,"model":"pulsar-16b","company":"multiverse","family":"Pulsar","version":"Pulsar","score":71.41},{"place":449,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":71.4},{"place":450,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":71.3},{"place":451,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":71.2},{"place":452,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":71.2},{"place":453,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":71.2},{"place":454,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":71.2},{"place":455,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":71.2},{"place":456,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.1},{"place":457,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":71.08},{"place":458,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":71.08},{"place":459,"model":"gemini-2.5-flash-lite-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":71},{"place":460,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":71},{"place":461,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":71},{"place":462,"model":"magistral-medium-1.0","company":"mistral","family":"Magistral","version":"Magistral 1.0","score":70.83},{"place":463,"model":"magistral-medium","company":"magistral","family":"Magistral","version":"Magistral","score":70.8},{"place":464,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":70.8},{"place":465,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.7},{"place":466,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":70.61},{"place":467,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.6},{"place":468,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":70.56},{"place":469,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":470,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.2},{"place":471,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":70.2},{"place":472,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":70.2},{"place":473,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":70.2},{"place":474,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.1},{"place":475,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":70.07},{"place":476,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":70},{"place":477,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":70},{"place":478,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":70},{"place":479,"model":"midm-k-2.5-pro","company":"kt","family":"Mi:dm","version":"Mi:dm K 2.5","score":70},{"place":480,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":69.89},{"place":481,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":69.8},{"place":482,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":69.8},{"place":483,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":69.6},{"place":484,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":69.49},{"place":485,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":69.4},{"place":486,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":69.3},{"place":487,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":69.2},{"place":488,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":69.2},{"place":489,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":69.2},{"place":490,"model":"nemotron-labs-dory1.0-4b-1loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":69.19},{"place":491,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":68.99},{"place":492,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":68.9},{"place":493,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.7},{"place":494,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":68.69},{"place":495,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":68.4},{"place":496,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.4},{"place":497,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":68.4},{"place":498,"model":"ring-mini-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":68.24},{"place":499,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.2},{"place":500,"model":"magistral-small-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":68.2},{"place":501,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":68.2},{"place":502,"model":"magistral-small-1.0","company":"mistral","family":"Magistral","version":"Magistral 1.0","score":68.18},{"place":503,"model":"hy-1.8b","company":"tencent","family":"HY","version":"HY","score":68.18},{"place":504,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":68.1},{"place":505,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":68.1},{"place":506,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":67.9},{"place":507,"model":"golongrl-4b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":67.7},{"place":508,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":67.68},{"place":509,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":67.4},{"place":510,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":67.3},{"place":511,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.3},{"place":512,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":67.2},{"place":513,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.2},{"place":514,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.2},{"place":515,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":67.1},{"place":516,"model":"phi-4-reasoning","company":"microsoft","family":"Phi","version":"Phi 4","score":67.1},{"place":517,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.1},{"place":518,"model":"claude-4.5-haiku-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67},{"place":519,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":66.8},{"place":520,"model":"ministral-3-8b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":66.8},{"place":521,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":66.79},{"place":522,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":66.78},{"place":523,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":66.7},{"place":524,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.7},{"place":525,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":66.7},{"place":526,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":66.7},{"place":527,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.7},{"place":528,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":66.7},{"place":529,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":66.5},{"place":530,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":66.5},{"place":531,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.5},{"place":532,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":66.3},{"place":533,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":66.3},{"place":534,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":66.3},{"place":535,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":66.24},{"place":536,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":66.2},{"place":537,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":66.16},{"place":538,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":66},{"place":539,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":66},{"place":540,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":66},{"place":541,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.8},{"place":542,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.8},{"place":543,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.8},{"place":544,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.8},{"place":545,"model":"magistral-small-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":65.78},{"place":546,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":65.7},{"place":547,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":65.7},{"place":548,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":65.6},{"place":549,"model":"hy-1.8b-int4gptq","company":"tencent","family":"HY","version":"HY","score":65.56},{"place":550,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":65.53},{"place":551,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":65.45},{"place":552,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":65.4},{"place":553,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.4},{"place":554,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":65.2},{"place":555,"model":"deepseek-r1-distill-llama-70b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":65.2},{"place":556,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":65.2},{"place":557,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":65.2},{"place":558,"model":"hy-1.8b-2bit","company":"tencent","family":"HY","version":"HY","score":65.15},{"place":559,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65},{"place":560,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":65},{"place":561,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":65},{"place":562,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":64.7},{"place":563,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":64.6},{"place":564,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":64.6},{"place":565,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64.6},{"place":566,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":64.4},{"place":567,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":64.1},{"place":568,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":64.1},{"place":569,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64},{"place":570,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":64},{"place":571,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":64},{"place":572,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63.63},{"place":573,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":63.6},{"place":574,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":63.6},{"place":575,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":63.6},{"place":576,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.6},{"place":577,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":63.6},{"place":578,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.38},{"place":579,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":63.3},{"place":580,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":63.1},{"place":581,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":63.1},{"place":582,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.9},{"place":583,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.6},{"place":584,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":62.6},{"place":585,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":62},{"place":586,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":62},{"place":587,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":62},{"place":588,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":61.7},{"place":589,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":61.4},{"place":590,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":61.3},{"place":591,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":61.3},{"place":592,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.2},{"place":593,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":61.2},{"place":594,"model":"ring-lite","company":"antgroup","family":"Ring","version":"Ring Lite","score":61.1},{"place":595,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":61.1},{"place":596,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":61.1},{"place":597,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":61.1},{"place":598,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":61.1},{"place":599,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":61.1},{"place":600,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":60.91},{"place":601,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":60.6},{"place":602,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":60.6},{"place":603,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":60.6},{"place":604,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":60.6},{"place":605,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60.26},{"place":606,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":60.1},{"place":607,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.1},{"place":608,"model":"openpangu-embedded-7b-v1.1","company":"huawei","family":"openPangu-Embedded","version":"openPangu-Embedded-V1.1","score":60.1},{"place":609,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":60},{"place":610,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60},{"place":611,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.8},{"place":612,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":59.6},{"place":613,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":59.3},{"place":614,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":59.1},{"place":615,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":59.1},{"place":616,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.1},{"place":617,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":59.1},{"place":618,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.6},{"place":619,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":58.6},{"place":620,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.59},{"place":621,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":58.55},{"place":622,"model":"deepseek-r1-lite-preview","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":58.5},{"place":623,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":58.3},{"place":624,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":58.1},{"place":625,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":58},{"place":626,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":57.8},{"place":627,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.6},{"place":628,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":57.6},{"place":629,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":57.6},{"place":630,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":57.5},{"place":631,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":57.4},{"place":632,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.4},{"place":633,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":57.2},{"place":634,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":57.2},{"place":635,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":57.1},{"place":636,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":57.1},{"place":637,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":56.9},{"place":638,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":56.9},{"place":639,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":56.8},{"place":640,"model":"aquif-3-moe-17b-a2.8b","company":"aquif","family":"Aquif","version":"Aquif 3","score":56.7},{"place":641,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56.6},{"place":642,"model":"magistral-small-2509","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":56.5},{"place":643,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":56.45},{"place":644,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":56.3},{"place":645,"model":"phi-4-14b","company":"microsoft","family":"Phi","version":"Phi 4","score":56.1},{"place":646,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":56.1},{"place":647,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":55.9},{"place":648,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":55.8},{"place":649,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.2},{"place":650,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":55.1},{"place":651,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":55.1},{"place":652,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":55.1},{"place":653,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.9},{"place":654,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.8},{"place":655,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.8},{"place":656,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.71},{"place":657,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.6},{"place":658,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54.55},{"place":659,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.5},{"place":660,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":54.5},{"place":661,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":54.4},{"place":662,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":54.3},{"place":663,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":54.1},{"place":664,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":54},{"place":665,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":54},{"place":666,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":53.6},{"place":667,"model":"ministral-3-3b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":53.4},{"place":668,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.1},{"place":669,"model":"aquif-3.6-1b","company":"aquif","family":"Aquif","version":"Aquif 3.6","score":52.8},{"place":670,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":52.53},{"place":671,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":52},{"place":672,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":52},{"place":673,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":52},{"place":674,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":52},{"place":675,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.6},{"place":676,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":51.5},{"place":677,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":51.3},{"place":678,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":51.3},{"place":679,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":51.3},{"place":680,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":51.1},{"place":681,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":51},{"place":682,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":51},{"place":683,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":51},{"place":684,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":51},{"place":685,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.8},{"place":686,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":50.6},{"place":687,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.51},{"place":688,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":50.5},{"place":689,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.5},{"place":690,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":50.3},{"place":691,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":50.3},{"place":692,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":50.3},{"place":693,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":50},{"place":694,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":49.9},{"place":695,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":49.9},{"place":696,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.8},{"place":697,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":49.66},{"place":698,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":49.5},{"place":699,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.49},{"place":700,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":49},{"place":701,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49},{"place":702,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":49},{"place":703,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":48.5},{"place":704,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":48.5},{"place":705,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":48.36},{"place":706,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":48.1},{"place":707,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":48},{"place":708,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":48},{"place":709,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":48},{"place":710,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":48},{"place":711,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":47.76},{"place":712,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":47.64},{"place":713,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":47.6},{"place":714,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":47.5},{"place":715,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":47.47},{"place":716,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":47.47},{"place":717,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":47.4},{"place":718,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":47},{"place":719,"model":"hy-0.5b","company":"tencent","family":"HY","version":"HY","score":46.97},{"place":720,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":46.8},{"place":721,"model":"vibethinker-1.5b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":46.7},{"place":722,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":46.7},{"place":723,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":46.63},{"place":724,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":46.4},{"place":725,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":46.2},{"place":726,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":46},{"place":727,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":46},{"place":728,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.6},{"place":729,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":45.5},{"place":730,"model":"seed1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":45.25},{"place":731,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":44.95},{"place":732,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":44.95},{"place":733,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":44.9},{"place":734,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":44.9},{"place":735,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":44.9},{"place":736,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":44.8},{"place":737,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.6},{"place":738,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":44.41},{"place":739,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":44.4},{"place":740,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":43.94},{"place":741,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":43.94},{"place":742,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":43.9},{"place":743,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":43.9},{"place":744,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":43.9},{"place":745,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":43.8},{"place":746,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":43.8},{"place":747,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.8},{"place":748,"model":"g9v3-3b","company":"ai9stars","family":"G9","version":"G9v3","score":43.8},{"place":749,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":43.43},{"place":750,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.4},{"place":751,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":43.3},{"place":752,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.3},{"place":753,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":43.1},{"place":754,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":43},{"place":755,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":42.93},{"place":756,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":42.92},{"place":757,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.9},{"place":758,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":42.42},{"place":759,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":42.4},{"place":760,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":42.4},{"place":761,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":42.4},{"place":762,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":42.4},{"place":763,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":42.4},{"place":764,"model":"aquif-3.5-nano-1b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":42},{"place":765,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":41.92},{"place":766,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":41.7},{"place":767,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":41.41},{"place":768,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":41.4},{"place":769,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":41.3},{"place":770,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":41.3},{"place":771,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":41.06},{"place":772,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":40.91},{"place":773,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":40.9},{"place":774,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":40.9},{"place":775,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":40.9},{"place":776,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":40.9},{"place":777,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":40.9},{"place":778,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":40.9},{"place":779,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":40.8},{"place":780,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":40.74},{"place":781,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":40.57},{"place":782,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":40.4},{"place":783,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.1},{"place":784,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":40.1},{"place":785,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":39.9},{"place":786,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":39.9},{"place":787,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.8},{"place":788,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":39.8},{"place":789,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":39.7},{"place":790,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.3},{"place":791,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":39.3},{"place":792,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":38.9},{"place":793,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":38.89},{"place":794,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":38.8},{"place":795,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":38.72},{"place":796,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":38.6},{"place":797,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":38.4},{"place":798,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":37.86},{"place":799,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":37.4},{"place":800,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":37.21},{"place":801,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":36.93},{"place":802,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.9},{"place":803,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":36.38},{"place":804,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":36.38},{"place":805,"model":"aquif-3-3.2b","company":"aquif","family":"Aquif","version":"Aquif 3","score":36.1},{"place":806,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":36},{"place":807,"model":"aquif-3.5-2.7b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":35.8},{"place":808,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":35.78},{"place":809,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":35.7},{"place":810,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":35.3},{"place":811,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":35.26},{"place":812,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":35.2},{"place":813,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":35.2},{"place":814,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":35.19},{"place":815,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.9},{"place":816,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":34.85},{"place":817,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":34.85},{"place":818,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":34.68},{"place":819,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":34.38},{"place":820,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":34.3},{"place":821,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":34.2},{"place":822,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":33.6},{"place":823,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":33.5},{"place":824,"model":"midm-2.0-base-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":33.5},{"place":825,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":33.33},{"place":826,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":33.3},{"place":827,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":33.2},{"place":828,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":33.2},{"place":829,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":33.1},{"place":830,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":33},{"place":831,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":32.66},{"place":832,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":32.6},{"place":833,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.2},{"place":834,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":32.2},{"place":835,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":32.1},{"place":836,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":31.9},{"place":837,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":31.8},{"place":838,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":31.8},{"place":839,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":31.6},{"place":840,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":31.6},{"place":841,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":31.31},{"place":842,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":31.31},{"place":843,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":31.3},{"place":844,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.98},{"place":845,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":30.8},{"place":846,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":30.8},{"place":847,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":30.64},{"place":848,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":30.3},{"place":849,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":30.3},{"place":850,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":29.97},{"place":851,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.59},{"place":852,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":29.5},{"place":853,"model":"llama-3.1-3b","company":"meta","family":"Llama","version":"Llama 3.1","score":29.4},{"place":854,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":29.3},{"place":855,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":29.3},{"place":856,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":29.29},{"place":857,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":28.8},{"place":858,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":28.6},{"place":859,"model":"apriel-5b-instruct","company":"servicenow","family":"Apriel","version":"Apriel","score":28.4},{"place":860,"model":"exaone-3.5-2.4b","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":28.4},{"place":861,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":28.3},{"place":862,"model":"littlelamb-0.3b","company":"multiverse","family":"LittleLamb","version":"LittleLamb","score":28.18},{"place":863,"model":"exaone-3.5-2.4b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":28.1},{"place":864,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":28.1},{"place":865,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":28.1},{"place":866,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":28},{"place":867,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":27.95},{"place":868,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.9},{"place":869,"model":"afm-4.5b","company":"arcee","family":"AFM","version":"AFM","score":27.8},{"place":870,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.78},{"place":871,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.77},{"place":872,"model":"qwen3-6b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.7},{"place":873,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":27.6},{"place":874,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":27.6},{"place":875,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":27.58},{"place":876,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.5},{"place":877,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.41},{"place":878,"model":"lfm2-350m-math","company":"liquidai","family":"LFM","version":"LFM2","score":27.4},{"place":879,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":27.3},{"place":880,"model":"k2-horizon-0.9b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":27.3},{"place":881,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":26.77},{"place":882,"model":"midm-2.0-mini-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":26.6},{"place":883,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":26.3},{"place":884,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":26.3},{"place":885,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":26.26},{"place":886,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":25.91},{"place":887,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":25.59},{"place":888,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":25.5},{"place":889,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":25.5},{"place":890,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.42},{"place":891,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":25.41},{"place":892,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":25.4},{"place":893,"model":"phi-4-mini-3.8b","company":"microsoft","family":"Phi","version":"Phi 4 mini","score":25.2},{"place":894,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":25.08},{"place":895,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.08},{"place":896,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":24.7},{"place":897,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":24.7},{"place":898,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":24.34},{"place":899,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":24.3},{"place":900,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.24},{"place":901,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":24.24},{"place":902,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":24.24},{"place":903,"model":"littlelamb-0.3b","company":"multiverse","family":"LittleLamb","version":"LittleLamb","score":24.04},{"place":904,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":23.89},{"place":905,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":23.7},{"place":906,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":23.2},{"place":907,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":22.7},{"place":908,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":22.32},{"place":909,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":22.2},{"place":910,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":21.9},{"place":911,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":21.6},{"place":912,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":21.4},{"place":913,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":21.38},{"place":914,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":21.21},{"place":915,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":21.2},{"place":916,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":21},{"place":917,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":20.2},{"place":918,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":19.7},{"place":919,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":19.29},{"place":920,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":19.2},{"place":921,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":19.2},{"place":922,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":16.57},{"place":923,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":11.9},{"place":924,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":11.9}]},{"id":"gqa","name":"GQA","topic":"Visual reasoning VQA","description":"Compositional question answering over real-world images (scene-graph based); test-dev balanced accuracy.","url":"https://cs.stanford.edu/people/dorarad/gqa/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1902.09506","metric":"percent","stars":"","top_model":"Qwen-VL","top_percent":59.3,"top_model_id":"qwen-vl","top_generation":"Qwen-VL","top_model_base":"Qwen-VL","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":59.3},{"place":2,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":57.5},{"place":3,"model":"instructblip-vicuna-13b","company":"salesforce","family":"BLIP","version":"InstructBLIP","score":49.5},{"place":4,"model":"blip-2-vicuna-13b","company":"salesforce","family":"BLIP","version":"BLIP-2","score":32.3}]},{"id":"graphwalks-bfs","name":"GraphWalks BFS","topic":"Long-context reasoning","description":"Graph traversal/GraphWalks benchmark (BFS variant) for long-context reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":99.7,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":99.7},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":98.7},{"place":3,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":98},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":94},{"place":5,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":93.1},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":93},{"place":7,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92},{"place":8,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":91.4},{"place":9,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":90.6},{"place":10,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":85.5},{"place":11,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":84.2},{"place":12,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":82.5},{"place":13,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.5},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":79.9},{"place":15,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":76.3},{"place":16,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":73.4},{"place":17,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":73.4},{"place":18,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":72},{"place":19,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":68.9},{"place":20,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.1}]},{"id":"graphwalks-bfs-1m","name":"GraphWalks BFS 1M","topic":"Long-context reasoning","description":"GraphWalks BFS long-context graph traversal at 1M context (F1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Mythos 5","top_percent":79.4,"top_model_id":"claude-mythos-5","top_generation":"Claude 5","top_model_base":"Claude Mythos 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":79.4},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.1},{"place":3,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":74.3},{"place":4,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":71.2},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":68.1},{"place":6,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":51.2},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":45.4},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":41.2},{"place":9,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":37},{"place":10,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":34.2},{"place":11,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.3},{"place":12,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15.8},{"place":13,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":9.4},{"place":14,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":2.5},{"place":15,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":0}]},{"id":"graphwalks-bfs-256k","name":"GraphWalks BFS 256K","topic":"Long-context reasoning","description":"GraphWalks BFS long-context graph traversal at 256K context (F1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Spark-X2.6-4B","top_percent":92.2,"top_model_id":"spark-x2.6-4b","top_generation":"Spark X2.6","top_model_base":"Spark-X2.6-4B","top_model_family":"Spark","top_company":"iflytek","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":92.2},{"place":2,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":91.1},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":90.7},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.4},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":85.9},{"place":6,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":85.7},{"place":7,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":81.3},{"place":8,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79},{"place":9,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":77},{"place":10,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":76.9},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":76.9},{"place":12,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":73.7},{"place":13,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.6},{"place":14,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":62.5},{"place":15,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.8},{"place":16,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":47.1},{"place":17,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":44}]},{"id":"graphwalks-bfs-256k-1m","name":"GraphWalks BFS 256K-1M","topic":"Long-context reasoning","description":"GraphWalks BFS long-context graph traversal at 256K-1M context (F1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":84.2,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":84.2},{"place":2,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":80},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":71.8},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":66.8},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":65},{"place":6,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":38.7},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":21.4}]},{"id":"graphwalks-parents","name":"GraphWalks Parents","topic":"Long-context reasoning","description":"Graph traversal/GraphWalks benchmark (Parents variant) for long-context reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Lite","top_percent":100,"top_model_id":"seed2.0-lite","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Lite","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":100},{"place":2,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":99.7},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":99.7},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":99.7},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":99},{"place":6,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":97.6},{"place":7,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":96.6},{"place":8,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":96.2},{"place":9,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":93},{"place":10,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":89.8},{"place":11,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":89},{"place":12,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":71.5},{"place":13,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":64.3},{"place":14,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":50.8}]},{"id":"graphwalks-parents-1m","name":"GraphWalks Parents 1M","topic":"Long-context reasoning","description":"GraphWalks Parents long-context graph task at 1M context (F1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":72,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":72},{"place":2,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":62},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.5},{"place":4,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":44.4},{"place":5,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":0}]},{"id":"graphwalks-parents-256k","name":"GraphWalks Parents 256K","topic":"Long-context reasoning","description":"GraphWalks Parents long-context graph traversal at 256K context (F1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Mythos 5","top_percent":99.96,"top_model_id":"claude-mythos-5","top_generation":"Claude 5","top_model_base":"Claude Mythos 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":99.96},{"place":2,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":99.9},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":99.3},{"place":4,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":97},{"place":5,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":93.6},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":90.1},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":82.8},{"place":8,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":35}]},{"id":"gre-math-maj16","name":"GRE Math maj@16","topic":"Math (standardized tests)","description":"GRE quantitative section evaluated via majority voting over 16 samples.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen2 7B","top_percent":58.5,"top_model_id":"qwen2-7b","top_generation":"Qwen2","top_model_base":"Qwen2 7B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":58.5},{"place":2,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":56.9},{"place":3,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":52.3},{"place":4,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":46.2},{"place":5,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":44.6},{"place":6,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":26.2}]},{"id":"ground-ui-1k","name":"Ground-UI-1K","topic":"GUI grounding","description":"Accuracy on the Ground-UI-1K grounding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Holo2-235B-A22B","top_percent":85.5,"top_model_id":"holo2-235b-a22b","top_generation":"Holo2","top_model_base":"Holo2","top_model_family":"Holo","top_company":"hcompany","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"holo2-235b-a22b","company":"hcompany","family":"Holo","version":"Holo2","score":85.5},{"place":2,"model":"holo2-30b-a3b","company":"hcompany","family":"Holo","version":"Holo2","score":85.5},{"place":3,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":85.4},{"place":4,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.2},{"place":5,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":84.5},{"place":6,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":84.2},{"place":7,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.2},{"place":8,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.1},{"place":9,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":84},{"place":10,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":84},{"place":11,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":83.8},{"place":12,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.6},{"place":13,"model":"holo2-4b","company":"hcompany","family":"Holo","version":"Holo2","score":83.3},{"place":14,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":83.2},{"place":15,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":82.3},{"place":16,"model":"holotron-12b","company":"hcompany","family":"Holotron","version":"Holotron","score":82},{"place":17,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":80.7},{"place":18,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":78.5},{"place":19,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":76.4},{"place":20,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":75.5},{"place":21,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":74.75},{"place":22,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":33.5}]},{"id":"gsm-infinite-hard-128k","name":"GSM-Infinite Hard (128K)","topic":"Math reasoning","description":"GSM-Infinite Hard benchmark at 128K context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiMo V2 Flash Base","top_percent":29,"top_model_id":"mimo-v2-flash-base","top_generation":"MiMo V2","top_model_base":"MiMo V2 Flash Base","top_model_family":"MiMo","top_company":"xiaomi","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":29},{"place":2,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":28.7},{"place":3,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":25.7},{"place":4,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":8.8}]},{"id":"gsm-infinite-hard-16k","name":"GSM-Infinite Hard (16K)","topic":"Math reasoning","description":"GSM-Infinite Hard benchmark at 16K context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V3.2-Exp","top_percent":50.4,"top_model_id":"deepseek-v3.2-exp","top_generation":"DeepSeek V3.2","top_model_base":"DeepSeek V3.2-Exp","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":50.4},{"place":2,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":41.5},{"place":3,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":37.7},{"place":4,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":34.6}]},{"id":"gsm-infinite-hard-32k","name":"GSM-Infinite Hard (32K)","topic":"Math reasoning","description":"GSM-Infinite Hard benchmark at 32K context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V3.2-Exp","top_percent":45.2,"top_model_id":"deepseek-v3.2-exp","top_generation":"DeepSeek V3.2","top_model_base":"DeepSeek V3.2-Exp","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":45.2},{"place":2,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":38.8},{"place":3,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":33.7},{"place":4,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":26.1}]},{"id":"gsm-infinite-hard-64k","name":"GSM-Infinite Hard (64K)","topic":"Math reasoning","description":"GSM-Infinite Hard benchmark at 64K context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V3.1","top_percent":34.7,"top_model_id":"deepseek-v3.1","top_generation":"DeepSeek V3.1","top_model_base":"DeepSeek V3.1","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":34.7},{"place":2,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":32.6},{"place":3,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":31.5},{"place":4,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":16}]},{"id":"gsm-plus","name":"GSM-Plus","topic":"Math (grade-school, enhanced)","description":"Enhanced GSM-style grade-school math benchmark variant.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-9B","top_percent":91.4,"top_model_id":"qwen3.5-9b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 9B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":47,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.4},{"place":2,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.7},{"place":3,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":89.74},{"place":4,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":89.71},{"place":5,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":89.69},{"place":6,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.41},{"place":7,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.3},{"place":8,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":89.23},{"place":9,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":88.3},{"place":10,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":88.1},{"place":11,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.9},{"place":12,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.4},{"place":13,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":87.18},{"place":14,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":87.1},{"place":15,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":87},{"place":16,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":86.6},{"place":17,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":86.55},{"place":18,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86.5},{"place":19,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":86.5},{"place":20,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":85.88},{"place":21,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.8},{"place":22,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.56},{"place":23,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.2},{"place":24,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.1},{"place":25,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":80.5},{"place":26,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.1},{"place":27,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":73},{"place":28,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":72.8},{"place":29,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":68.38},{"place":30,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.3},{"place":31,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":64.76},{"place":32,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.1},{"place":33,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":62.6},{"place":34,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.29},{"place":35,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":61.17},{"place":36,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":60.75},{"place":37,"model":"llama-3.1-3b","company":"meta","family":"Llama","version":"Llama 3.1","score":59.2},{"place":38,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":59.14},{"place":39,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":58.91},{"place":40,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":58.27},{"place":41,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":56.16},{"place":42,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":50.4},{"place":43,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":49.7},{"place":44,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":42.6},{"place":45,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.4},{"place":46,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":38.68},{"place":47,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":28.9},{"place":48,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":28.1},{"place":49,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":26.6},{"place":50,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.5},{"place":51,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":25.1},{"place":52,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":17},{"place":53,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":4.6},{"place":54,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":4.3}]},{"id":"gsm-symbolic","name":"GSM-Symbolic","topic":"Math reasoning","description":"Symbolic reasoning variant of GSM that tests algebraic manipulation and arithmetic with structured problems.","url":"https://github.com/kosukearai/gsm-symbolic","leaderboard":"","github":"https://github.com/kosukearai/gsm-symbolic","paper":"","metric":"percent","stars":"","top_model":"Granite-4.0-H-Small","top_percent":87.38,"top_model_id":"granite-4.0-h-small","top_generation":"Granite 4.0","top_model_base":"Granite 4.0 H Small","top_model_family":"Granite","top_company":"IBM","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":87.38},{"place":2,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":83.7},{"place":3,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":82.27},{"place":4,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":81.45},{"place":5,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":81.32},{"place":6,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":79.82},{"place":7,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":75.7}]},{"id":"gsm8k","name":"GSM8K","topic":"Math (grade-school)","description":"Grade-school math word problems requiring multi-step reasoning.","url":"https://huggingface.co/datasets/openai/gsm8k","leaderboard":"https://llm-stats.com/benchmarks/gsm8k","github":"https://github.com/openai/grade-school-math","paper":"","metric":"percent","stars":"1322","top_model":"MiMo V2.5 Pro Base","top_percent":99.6,"top_model_id":"mimo-v2.5-pro-base","top_generation":"MiMo V2.5","top_model_base":"MiMo V2.5 Pro Base","top_model_family":"MiMo","top_company":"xiaomi","top_open_source":1,"lower_is_better":false,"bench_models":705,"total_models":3854,"placements":[{"place":1,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":99.6},{"place":2,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":99.6},{"place":3,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":97.3},{"place":4,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":97.19},{"place":5,"model":"o1","company":"openai","family":"o1","version":"o1","score":97.1},{"place":6,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":97.1},{"place":7,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":97},{"place":8,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":96.8},{"place":9,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":96.8},{"place":10,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":96.8},{"place":11,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":96.7},{"place":12,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":96.7},{"place":13,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":96.66},{"place":14,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":96.66},{"place":15,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":96.66},{"place":16,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":96.6},{"place":17,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":96.4},{"place":18,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":96.4},{"place":19,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":96.4},{"place":20,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":96.4},{"place":21,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":96.36},{"place":22,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":96.36},{"place":23,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":96.3},{"place":24,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":96.3},{"place":25,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":96.3},{"place":26,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":96.26},{"place":27,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":96.21},{"place":28,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":96.13},{"place":29,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":96.1},{"place":30,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":96.1},{"place":31,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":96.1},{"place":32,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":96.06},{"place":33,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":96.06},{"place":34,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":96},{"place":35,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":95.98},{"place":36,"model":"llama-3.1-405b-instruct-bf16","company":"meta","family":"Llama","version":"Llama 3.1","score":95.98},{"place":37,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":95.91},{"place":38,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":95.9},{"place":39,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.9},{"place":40,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":95.9},{"place":41,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":95.9},{"place":42,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":95.83},{"place":43,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.8},{"place":44,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":95.8},{"place":45,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.8},{"place":46,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":95.8},{"place":47,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":95.7},{"place":48,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":95.7},{"place":49,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":95.6},{"place":50,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":95.6},{"place":51,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":95.6},{"place":52,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":95.53},{"place":53,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":95.53},{"place":54,"model":"mistral-large-2407","company":"mistral","family":"Mistral","version":"Mistral","score":95.53},{"place":55,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":95.5},{"place":56,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":95.45},{"place":57,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":95.4},{"place":58,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":95.4},{"place":59,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":95.38},{"place":60,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":95.37},{"place":61,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.22},{"place":62,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":95.2},{"place":63,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":95.1},{"place":64,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":95.1},{"place":65,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":95.1},{"place":66,"model":"gemini-1.5-flash-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":95.01},{"place":67,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":95},{"place":68,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":95},{"place":69,"model":"gemini-1.5-pro-exp-0801","company":"google","family":"Gemini","version":"Gemini 1.0","score":95},{"place":70,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":94.92},{"place":71,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":94.9},{"place":72,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":94.9},{"place":73,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":94.8},{"place":74,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94.8},{"place":75,"model":"nova-pro","company":"amazon","family":"Nova","version":"Nova","score":94.8},{"place":76,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":94.8},{"place":77,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":94.5},{"place":78,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":94.5},{"place":79,"model":"nova-lite","company":"amazon","family":"Nova","version":"Nova","score":94.5},{"place":80,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":94.5},{"place":81,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":94.47},{"place":82,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":94.4},{"place":83,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":94.4},{"place":84,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":94.4},{"place":85,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":94.39},{"place":86,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":94.39},{"place":87,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":94.24},{"place":88,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":94.2},{"place":89,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":94.2},{"place":90,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":94.2},{"place":91,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":94.16},{"place":92,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":94.16},{"place":93,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":94.1},{"place":94,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":94.1},{"place":95,"model":"step-2","company":"stepfun","family":"Step","version":"Step 2","score":94},{"place":96,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":93.93},{"place":97,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":93.93},{"place":98,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":93.93},{"place":99,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":93.85},{"place":100,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":93.8},{"place":101,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":93.78},{"place":102,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":93.71},{"place":103,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":93.7},{"place":104,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":93.7},{"place":105,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":93.7},{"place":106,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":93.6},{"place":107,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.6},{"place":108,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":93.6},{"place":109,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.56},{"place":110,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":93.5},{"place":111,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":93.5},{"place":112,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":93.5},{"place":113,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":93.46},{"place":114,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.4},{"place":115,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":93.4},{"place":116,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":93.4},{"place":117,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.33},{"place":118,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":93.3},{"place":119,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":93.3},{"place":120,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":93.2},{"place":121,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":93.2},{"place":122,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":93.2},{"place":123,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":93.1},{"place":124,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":93.1},{"place":125,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":93.1},{"place":126,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":93.03},{"place":127,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":93},{"place":128,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":93},{"place":129,"model":"mistral-large-2407","company":"mistral","family":"Mistral","version":"Mistral","score":93},{"place":130,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":93},{"place":131,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":93},{"place":132,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":92.9},{"place":133,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":92.9},{"place":134,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":92.9},{"place":135,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":92.8},{"place":136,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":92.7},{"place":137,"model":"yuan2.0-m32","company":"yuanlab","family":"Yuan","version":"Yuan2.0-M32","score":92.7},{"place":138,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":92.7},{"place":139,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":92.65},{"place":140,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":92.6},{"place":141,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":92.5},{"place":142,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":92.49},{"place":143,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":92.49},{"place":144,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.49},{"place":145,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":92.49},{"place":146,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":92.47},{"place":147,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":92.4},{"place":148,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.34},{"place":149,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":92.3},{"place":150,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":92.3},{"place":151,"model":"nova-micro","company":"amazon","family":"Nova","version":"Nova","score":92.3},{"place":152,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":92.3},{"place":153,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":92.27},{"place":154,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":92.2},{"place":155,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":92.2},{"place":156,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":92.12},{"place":157,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":92.1},{"place":158,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":92},{"place":159,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":92},{"place":160,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":92},{"place":161,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":91.9},{"place":162,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":91.9},{"place":163,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":91.89},{"place":164,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":91.89},{"place":165,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":91.89},{"place":166,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":91.81},{"place":167,"model":"internlm2-math-plus-mixtral8x22b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":91.8},{"place":168,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":91.74},{"place":169,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":91.7},{"place":170,"model":"abab6.5","company":"minimax","family":"abab","version":"abab6.5","score":91.7},{"place":171,"model":"midm-2.0-base-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":91.6},{"place":172,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":91.6},{"place":173,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":91.6},{"place":174,"model":"qwen2.5-math-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":91.6},{"place":175,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":91.58},{"place":176,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":91.51},{"place":177,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":91.51},{"place":178,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":91.51},{"place":179,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":91.5},{"place":180,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.43},{"place":181,"model":"llama-3.1-nemotron-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":91.43},{"place":182,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":91.4},{"place":183,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":91.4},{"place":184,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":91.4},{"place":185,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":91.4},{"place":186,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":91.36},{"place":187,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":91.36},{"place":188,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":91.3},{"place":189,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":91.28},{"place":190,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":91.21},{"place":191,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":91.2},{"place":192,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":91.1},{"place":193,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":91.1},{"place":194,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":91.1},{"place":195,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":91.1},{"place":196,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":91.1},{"place":197,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":91.1},{"place":198,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":91.1},{"place":199,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":91.05},{"place":200,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":91},{"place":201,"model":"palm-2","company":"google","family":"PaLM","version":"PaLM 2","score":91},{"place":202,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":91},{"place":203,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":90.9},{"place":204,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.8},{"place":205,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":90.8},{"place":206,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":90.8},{"place":207,"model":"qwen2.5-math-72b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":90.8},{"place":208,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":90.8},{"place":209,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":90.75},{"place":210,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.67},{"place":211,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":90.6},{"place":212,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":90.4},{"place":213,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":90.4},{"place":214,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":90.37},{"place":215,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":90.37},{"place":216,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":90.3},{"place":217,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":90.22},{"place":218,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":90.2},{"place":219,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.2},{"place":220,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":90.14},{"place":221,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.07},{"place":222,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":90.06},{"place":223,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":90},{"place":224,"model":"grok-1.5","company":"xai","family":"Grok","version":"Grok 1.5","score":90},{"place":225,"model":"seed1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.99},{"place":226,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":89.99},{"place":227,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":89.92},{"place":228,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":89.91},{"place":229,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":89.9},{"place":230,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":89.9},{"place":231,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":89.9},{"place":232,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":89.8},{"place":233,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":89.8},{"place":234,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":89.7},{"place":235,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":89.69},{"place":236,"model":"phi-3-small-8k-instruct","company":"microsoft","family":"Phi","version":"Phi-3","score":89.6},{"place":237,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.5},{"place":238,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":89.5},{"place":239,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.5},{"place":240,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":89.5},{"place":241,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":89.5},{"place":242,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":89.31},{"place":243,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.3},{"place":244,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89.3},{"place":245,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":89.2},{"place":246,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":89.1},{"place":247,"model":"qwen2-math-72b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":89.1},{"place":248,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":89.01},{"place":249,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":89.01},{"place":250,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":89},{"place":251,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":89},{"place":252,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":88.9},{"place":253,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":88.9},{"place":254,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":88.9},{"place":255,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.78},{"place":256,"model":"joyai-llm-flash-base","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":88.78},{"place":257,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":88.78},{"place":258,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":88.7},{"place":259,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":88.7},{"place":260,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":88.7},{"place":261,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.6},{"place":262,"model":"phi-4-mini","company":"microsoft","family":"Phi","version":"Phi 4","score":88.6},{"place":263,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":88.5},{"place":264,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":88.4},{"place":265,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.3},{"place":266,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":88.2},{"place":267,"model":"baichuan-3","company":"baichuan","family":"Baichuan","version":"Baichuan 3","score":88.2},{"place":268,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":88.2},{"place":269,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":88.15},{"place":270,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.1},{"place":271,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88.1},{"place":272,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":88.1},{"place":273,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":88},{"place":274,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":87.9},{"place":275,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":87.9},{"place":276,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":87.72},{"place":277,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":87.7},{"place":278,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":87.7},{"place":279,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.6},{"place":280,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":87.6},{"place":281,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":87.6},{"place":282,"model":"glm-4-0116","company":"zai","family":"GLM","version":"GLM 4","score":87.6},{"place":283,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":87.6},{"place":284,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.57},{"place":285,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87.5},{"place":286,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":87.49},{"place":287,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":87.41},{"place":288,"model":"reka-core-20240501","company":"reka","family":"Reka","version":"Reka Core","score":87.41},{"place":289,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":87.3},{"place":290,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":87.27},{"place":291,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":87.2},{"place":292,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":87},{"place":293,"model":"jamba-1.5-large","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":87},{"place":294,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":86.92},{"place":295,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":86.88},{"place":296,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":86.8},{"place":297,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":86.7},{"place":298,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.7},{"place":299,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.7},{"place":300,"model":"athene-70b","company":"nvidia","family":"Athene","version":"Athene V2","score":86.66},{"place":301,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":86.5},{"place":302,"model":"apertus-v1.5-70b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":86.4},{"place":303,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":86.4},{"place":304,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":86.3},{"place":305,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.3},{"place":306,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":86.2},{"place":307,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":86.2},{"place":308,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":86},{"place":309,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":86},{"place":310,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.8},{"place":311,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":85.8},{"place":312,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":85.8},{"place":313,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":85.75},{"place":314,"model":"apertus-v1.5-8b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":85.7},{"place":315,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":85.7},{"place":316,"model":"bielik-11b-v3.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":85.6},{"place":317,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":85.6},{"place":318,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.6},{"place":319,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":85.6},{"place":320,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":85.54},{"place":321,"model":"bielik-11b-v2.5-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.5","score":85.52},{"place":322,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":85.5},{"place":323,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.5},{"place":324,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":85.45},{"place":325,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":85.4},{"place":326,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":85.4},{"place":327,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.4},{"place":328,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":85.37},{"place":329,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":85.3},{"place":330,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":85.3},{"place":331,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.2},{"place":332,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":85.14},{"place":333,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":85.1},{"place":334,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":85.06},{"place":335,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":85},{"place":336,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":84.91},{"place":337,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84.9},{"place":338,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":84.9},{"place":339,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":84.8},{"place":340,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":84.8},{"place":341,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":84.76},{"place":342,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":84.76},{"place":343,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":84.7},{"place":344,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":84.69},{"place":345,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":84.6},{"place":346,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":84.5},{"place":347,"model":"hrm-text-1b","company":"sapient","family":"HRM","version":"HRM-Text","score":84.5},{"place":348,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84.5},{"place":349,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":84.5},{"place":350,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.4},{"place":351,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":84.38},{"place":352,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":84.38},{"place":353,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":84.3},{"place":354,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":84.2},{"place":355,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":84.1},{"place":356,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":84.1},{"place":357,"model":"math-shepherd-mistral-7b","company":"pku","family":"Math-Shepherd","version":"Math-Shepherd","score":84.1},{"place":358,"model":"hy-1.8b","company":"tencent","family":"HY","version":"HY","score":84.08},{"place":359,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":84.08},{"place":360,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84},{"place":361,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":84},{"place":362,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":84},{"place":363,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":84},{"place":364,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":83.9},{"place":365,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.9},{"place":366,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":83.9},{"place":367,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83.9},{"place":368,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.8},{"place":369,"model":"bielik-11b-v2.6-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.6","score":83.78},{"place":370,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":83.7},{"place":371,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":83.7},{"place":372,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":83.7},{"place":373,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":83.62},{"place":374,"model":"gairmath-abel-70b","company":"gair","family":"Abel","version":"GAIRMath-Abel","score":83.6},{"place":375,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83.6},{"place":376,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":83.5},{"place":377,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":83.5},{"place":378,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":83.4},{"place":379,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":83.3},{"place":380,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":83.2},{"place":381,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.2},{"place":382,"model":"wizardmath-7b-v1.1","company":"microsoft","family":"WizardMath","version":"WizardMath V1.1","score":83.2},{"place":383,"model":"midm-2.0-mini-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":83.1},{"place":384,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.09},{"place":385,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":83.02},{"place":386,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":83},{"place":387,"model":"deepseek-math-7b-instruct","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":82.9},{"place":388,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":82.9},{"place":389,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":82.9},{"place":390,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":82.8},{"place":391,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":82.79},{"place":392,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":82.71},{"place":393,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":82.71},{"place":394,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":82.7},{"place":395,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":82.7},{"place":396,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":82.7},{"place":397,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":82.7},{"place":398,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":82.64},{"place":399,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":82.64},{"place":400,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":82.6},{"place":401,"model":"mobilellm-r1.5-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":82.6},{"place":402,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":82.6},{"place":403,"model":"internlm2-math-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":82.6},{"place":404,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":82.6},{"place":405,"model":"exaone-3.5-2.4b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":82.5},{"place":406,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":82.5},{"place":407,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":82.49},{"place":408,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":82.41},{"place":409,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":82.4},{"place":410,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":82.34},{"place":411,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":82.3},{"place":412,"model":"metamath-70b","company":"meta-math","family":"MetaMath","version":"MetaMath","score":82.3},{"place":413,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":82.3},{"place":414,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":82.26},{"place":415,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":82.03},{"place":416,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":82},{"place":417,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":82},{"place":418,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":81.9},{"place":419,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":81.88},{"place":420,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":81.7},{"place":421,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":81.7},{"place":422,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":81.65},{"place":423,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":81.65},{"place":424,"model":"wizardmath-70b-v1.0","company":"microsoft","family":"WizardMath","version":"WizardMath V1.0","score":81.6},{"place":425,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":81.6},{"place":426,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":81.58},{"place":427,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.5},{"place":428,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":81.5},{"place":429,"model":"inflection-2","company":"inflection","family":"Inflection","version":"Inflection-2","score":81.4},{"place":430,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":81.4},{"place":431,"model":"bielik-11b-v2.3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.3","score":81.27},{"place":432,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":81.2},{"place":433,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":81.2},{"place":434,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":81.12},{"place":435,"model":"bielik-11b-v2.2-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.2","score":81.12},{"place":436,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":81.1},{"place":437,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":81.1},{"place":438,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.1},{"place":439,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":81.1},{"place":440,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":81.1},{"place":441,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":81.05},{"place":442,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":81},{"place":443,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":80.89},{"place":444,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":80.8},{"place":445,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":80.8},{"place":446,"model":"mistral-small-3-24b-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":80.73},{"place":447,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":80.7},{"place":448,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":80.7},{"place":449,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":80.7},{"place":450,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":80.6},{"place":451,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":80.6},{"place":452,"model":"bielik-11b-v2.1-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.1","score":80.59},{"place":453,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":80.5},{"place":454,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.44},{"place":455,"model":"qwen2-math-7b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":80.4},{"place":456,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":80.36},{"place":457,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":80.36},{"place":458,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":80.3},{"place":459,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":80.2},{"place":460,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":80.14},{"place":461,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":80.1},{"place":462,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":80.06},{"place":463,"model":"yi-large","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":80.06},{"place":464,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":80.04},{"place":465,"model":"rnd1-base-0910","company":"radicalnumerics","family":"RND1","version":"RND1","score":80},{"place":466,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":80},{"place":467,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":80},{"place":468,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":79.9},{"place":469,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":79.83},{"place":470,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":79.7},{"place":471,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.7},{"place":472,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":79.6},{"place":473,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":79.6},{"place":474,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":79.6},{"place":475,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":79.6},{"place":476,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":79.5},{"place":477,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":79.5},{"place":478,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":79.45},{"place":479,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":79.4},{"place":480,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":79.38},{"place":481,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":79.23},{"place":482,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.2},{"place":483,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":79.2},{"place":484,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":79.2},{"place":485,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":79.15},{"place":486,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.1},{"place":487,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":79},{"place":488,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.92},{"place":489,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":78.92},{"place":490,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":78.9},{"place":491,"model":"qwen-72b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":78.9},{"place":492,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":78.9},{"place":493,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":78.77},{"place":494,"model":"hy-1.8b-int4gptq","company":"tencent","family":"HY","version":"HY","score":78.7},{"place":495,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":78.6},{"place":496,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":78.6},{"place":497,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":78.5},{"place":498,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":78.5},{"place":499,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":78.47},{"place":500,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":78.47},{"place":501,"model":"seallm-7b-v2","company":"damo","family":"SeaLLM","version":"SeaLLM v2","score":78.2},{"place":502,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":78.2},{"place":503,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":78.2},{"place":504,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":78.17},{"place":505,"model":"internlm2-math-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":78.1},{"place":506,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.9},{"place":507,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":77.9},{"place":508,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":77.8},{"place":509,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":77.79},{"place":510,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":77.7},{"place":511,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":77.7},{"place":512,"model":"metamath-mistral-7b","company":"metamath","family":"MetaMath","version":"MetaMath","score":77.7},{"place":513,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":77.6},{"place":514,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.41},{"place":515,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":77.4},{"place":516,"model":"hy-1.8b-2bit","company":"tencent","family":"HY","version":"HY","score":77.33},{"place":517,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":77.3},{"place":518,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":77.26},{"place":519,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":77.2},{"place":520,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":77.2},{"place":521,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.18},{"place":522,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":77.1},{"place":523,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":77.1},{"place":524,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":77.03},{"place":525,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":76.8},{"place":526,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":76.8},{"place":527,"model":"qwen2.5-math-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":76.8},{"place":528,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":76.7},{"place":529,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":76.7},{"place":530,"model":"yuan2.0-102b","company":"yuanlab","family":"Yuan","version":"Yuan2.0","score":76.6},{"place":531,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":76.6},{"place":532,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":76.57},{"place":533,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":76.42},{"place":534,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":76.4},{"place":535,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":76.4},{"place":536,"model":"yuan2.0-51b","company":"yuanlab","family":"Yuan","version":"Yuan2.0","score":76.3},{"place":537,"model":"bielik-11b-v2.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.0","score":76.27},{"place":538,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":76.2},{"place":539,"model":"skywork-moe-base","company":"skywork","family":"Skywork","version":"Skywork-MoE","score":76.1},{"place":540,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":76.1},{"place":541,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":76},{"place":542,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":75.97},{"place":543,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":75.97},{"place":544,"model":"jamba-1.5-mini","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":75.8},{"place":545,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":75.74},{"place":546,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":75.74},{"place":547,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":75.7},{"place":548,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":75.7},{"place":549,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":75.6},{"place":550,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":75.51},{"place":551,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.5},{"place":552,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":75.4},{"place":553,"model":"numinamath-7b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":75.4},{"place":554,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.3},{"place":555,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":75.3},{"place":556,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":75.21},{"place":557,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":75.1},{"place":558,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":74.98},{"place":559,"model":"internlm2.5-7b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":74.8},{"place":560,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":74.68},{"place":561,"model":"reka-flash-21b-20240226","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226","score":74.68},{"place":562,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.6},{"place":563,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.6},{"place":564,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.5},{"place":565,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":74.4},{"place":566,"model":"bielik-11b-v3.0","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":74.15},{"place":567,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":74},{"place":568,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":74},{"place":569,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":73.8},{"place":570,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":73.7},{"place":571,"model":"bielik-4.5b-v3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":73.69},{"place":572,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":73.42},{"place":573,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.2},{"place":574,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":73.16},{"place":575,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":73.1},{"place":576,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":72.9},{"place":577,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.86},{"place":578,"model":"openchat-3.5-0106-gemma","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":72.86},{"place":579,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":72.6},{"place":580,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":72.6},{"place":581,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":72.48},{"place":582,"model":"skywork-13b-math","company":"skywork","family":"Skywork","version":"Skywork","score":72.33},{"place":583,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":72.3},{"place":584,"model":"metamath-13b","company":"metamath","family":"MetaMath","version":"MetaMath","score":72.3},{"place":585,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":72.3},{"place":586,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":72.18},{"place":587,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":72.02},{"place":588,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":72},{"place":589,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.95},{"place":590,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":71.8},{"place":591,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":71.7},{"place":592,"model":"acegpt-v2-32b-chat","company":"freedomintelligence","family":"AceGPT","version":"AceGPT-v2","score":71.5},{"place":593,"model":"qwen2-math-1.5b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":71.3},{"place":594,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":71.1},{"place":595,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":71},{"place":596,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":70.9},{"place":597,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":70.8},{"place":598,"model":"command-r-plus-08-2024","company":"cohere","family":"Command","version":"Command","score":70.7},{"place":599,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":70.7},{"place":600,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":70.7},{"place":601,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":70.7},{"place":602,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":70.7},{"place":603,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":70.7},{"place":604,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.28},{"place":605,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":70.13},{"place":606,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":70.1},{"place":607,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":70.1},{"place":608,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":70.1},{"place":609,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":70.05},{"place":610,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70},{"place":611,"model":"math-qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":69.8},{"place":612,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":69.7},{"place":613,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":69.7},{"place":614,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.6},{"place":615,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":69.6},{"place":616,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":69.6},{"place":617,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":69.5},{"place":618,"model":"metamath-llemma-7b","company":"metamath","family":"MetaMath","version":"MetaMath","score":69.2},{"place":619,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":69.1},{"place":620,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":68.8},{"place":621,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":68.69},{"place":622,"model":"meta-llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":68.69},{"place":623,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":68.6},{"place":624,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":68.6},{"place":625,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.5},{"place":626,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":68.46},{"place":627,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":68.39},{"place":628,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":68.3},{"place":629,"model":"internlm2-math-base-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":68.2},{"place":630,"model":"yi-coder-9b","company":"01ai","family":"Yi","version":"Yi-Coder","score":68.1},{"place":631,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":68},{"place":632,"model":"bolmo-7b","company":"allenai","family":"Bolmo","version":"Bolmo 7B","score":68},{"place":633,"model":"bielik-11b-v2","company":"SpeakLeash","family":"Bielik","version":"Bielik v2","score":67.78},{"place":634,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":67.63},{"place":635,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":67.6},{"place":636,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":67.55},{"place":637,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":67.5},{"place":638,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":67.2},{"place":639,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.2},{"place":640,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":67.2},{"place":641,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":67.1},{"place":642,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":67.02},{"place":643,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":66.9},{"place":644,"model":"yuan2.0-2b","company":"yuanlab","family":"Yuan","version":"Yuan2.0","score":66.6},{"place":645,"model":"metamath-7b","company":"metamath","family":"MetaMath","version":"MetaMath","score":66.5},{"place":646,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":66.41},{"place":647,"model":"gair-abel-13b","company":"sjtu","family":"Abel","version":"Abel","score":66.41},{"place":648,"model":"gairmath-abel-13b","company":"gair","family":"Abel","version":"GAIRMath-Abel","score":66.4},{"place":649,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":66},{"place":650,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":65.8},{"place":651,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":65.7},{"place":652,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":65.7},{"place":653,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":65.7},{"place":654,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":65.66},{"place":655,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":65.13},{"place":656,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":64.75},{"place":657,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":64.7},{"place":658,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":64.52},{"place":659,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":64.2},{"place":660,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":64.1},{"place":661,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":63.99},{"place":662,"model":"wizardmath-13b-v1.0","company":"microsoft","family":"WizardMath","version":"WizardMath V1.0","score":63.9},{"place":663,"model":"internlm2-math-base-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":63.7},{"place":664,"model":"bielik-4.5b-v3","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":63.61},{"place":665,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":63.4},{"place":666,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":63.31},{"place":667,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":63.3},{"place":668,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":63.2},{"place":669,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":63},{"place":670,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":62.9},{"place":671,"model":"grok-1","company":"xai","family":"Grok","version":"Grok 1","score":62.9},{"place":672,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":62.9},{"place":673,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":62.9},{"place":674,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":62.85},{"place":675,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":62.8},{"place":676,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":62.8},{"place":677,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":62.7},{"place":678,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":62.7},{"place":679,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":62.6},{"place":680,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":62.6},{"place":681,"model":"math-qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":62.5},{"place":682,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":62.5},{"place":683,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":62.5},{"place":684,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":62.4},{"place":685,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":62.3},{"place":686,"model":"audio-flamingo-3","company":"nvidia","family":"Audio Flamingo","version":"Audio Flamingo 3","score":62.2},{"place":687,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":62.2},{"place":688,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":62.2},{"place":689,"model":"x-omni","company":"tencent","family":"X-Omni","version":"X-Omni","score":61.7},{"place":690,"model":"mobilellm-r1-950m-base","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":61.6},{"place":691,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":61.6},{"place":692,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":61.6},{"place":693,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":61.56},{"place":694,"model":"minicpm-moe-8x2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":61.56},{"place":695,"model":"qwen1.5-moe-a2.7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":61.5},{"place":696,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":61.3},{"place":697,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.3},{"place":698,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":61.3},{"place":699,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":61.2},{"place":700,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":61.2},{"place":701,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":61.18},{"place":702,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":61.03},{"place":703,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":61},{"place":704,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":60.9},{"place":705,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":60.9},{"place":706,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.73},{"place":707,"model":"tfree-hat-pretrained-7b-base","company":"alephalpha","family":"TFree","version":"TFree Hat","score":60.7},{"place":708,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":60.7},{"place":709,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.7},{"place":710,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":60.3},{"place":711,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":60.3},{"place":712,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":60.2},{"place":713,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":60.1},{"place":714,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":60.1},{"place":715,"model":"jamba-v0.1","company":"ai21","family":"Jamba","version":"Jamba","score":59.9},{"place":716,"model":"gairmath-abel-7b","company":"gair","family":"Abel","version":"GAIRMath-Abel","score":59.7},{"place":717,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":59.59},{"place":718,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":59.3},{"place":719,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":59.3},{"place":720,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":59},{"place":721,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":58.98},{"place":722,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":58.91},{"place":723,"model":"minerva-540b","company":"google","family":"Minerva","version":"Minerva","score":58.8},{"place":724,"model":"internlm2-math-plus-1.8b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":58.8},{"place":725,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":58.7},{"place":726,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":58.68},{"place":727,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":58.5},{"place":728,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":58.4},{"place":729,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":58.4},{"place":730,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":58.4},{"place":731,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":58.4},{"place":732,"model":"lfm2-1.2b","company":"liquidai","family":"LFM","version":"LFM2","score":58.3},{"place":733,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":58.2},{"place":734,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":57.77},{"place":735,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":57.7},{"place":736,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":57.7},{"place":737,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":57.54},{"place":738,"model":"llama-3-instruct-8b-simpo-v0.2","company":"princeton-nlp","family":"Llama","version":"Llama 3","score":57.54},{"place":739,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":57.5},{"place":740,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":57.47},{"place":741,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":57.2},{"place":742,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":57.2},{"place":743,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":57.16},{"place":744,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":57.1},{"place":745,"model":"qwen1.5-4b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":57},{"place":746,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":56.8},{"place":747,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":56.8},{"place":748,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":56.7},{"place":749,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":56.7},{"place":750,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":56.6},{"place":751,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":56.6},{"place":752,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":56.5},{"place":753,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":56.4},{"place":754,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":56},{"place":755,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":56},{"place":756,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":55.8},{"place":757,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":55.7},{"place":758,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":55.3},{"place":759,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":55.3},{"place":760,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":55.1},{"place":761,"model":"hy-0.5b","company":"tencent","family":"HY","version":"HY","score":55.04},{"place":762,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":55},{"place":763,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":54.9},{"place":764,"model":"wizardmath-7b-v1.0","company":"microsoft","family":"WizardMath","version":"WizardMath V1.0","score":54.9},{"place":765,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":54.74},{"place":766,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":54.7},{"place":767,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":54.7},{"place":768,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":54.7},{"place":769,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54.62},{"place":770,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":54.6},{"place":771,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":54.44},{"place":772,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":54.4},{"place":773,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":54.4},{"place":774,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":54.4},{"place":775,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":54.3},{"place":776,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":54.3},{"place":777,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":54.3},{"place":778,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":54.1},{"place":779,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":54.1},{"place":780,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":54},{"place":781,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":54},{"place":782,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":53.83},{"place":783,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":53.8},{"place":784,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":53.8},{"place":785,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":53.68},{"place":786,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":53.6},{"place":787,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":53.37},{"place":788,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":53.3},{"place":789,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53},{"place":790,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":52.99},{"place":791,"model":"mobilellm-r1.5-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":52.8},{"place":792,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":52.8},{"place":793,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":52.77},{"place":794,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":52.77},{"place":795,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":52.7},{"place":796,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":52.7},{"place":797,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":52.62},{"place":798,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":52.62},{"place":799,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":52.6},{"place":800,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":52.6},{"place":801,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":52.54},{"place":802,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":52.5},{"place":803,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":52.5},{"place":804,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":52.4},{"place":805,"model":"minerva-62b","company":"google","family":"Minerva","version":"Minerva","score":52.4},{"place":806,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":52.3},{"place":807,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":52.3},{"place":808,"model":"kwaiyii-13b-chat","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":52.2},{"place":809,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":52.2},{"place":810,"model":"aquif-3-0.4b","company":"aquif","family":"Aquif","version":"Aquif 3","score":52.1},{"place":811,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":52.1},{"place":812,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":52.08},{"place":813,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":51.93},{"place":814,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":51.9},{"place":815,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":51.9},{"place":816,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":51.7},{"place":817,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":51.7},{"place":818,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":51.63},{"place":819,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":51.6},{"place":820,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":51.5},{"place":821,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.4},{"place":822,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":51.25},{"place":823,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":51.2},{"place":824,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":51},{"place":825,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":50.9},{"place":826,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":50.9},{"place":827,"model":"aquif-3.5-a0.6b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":50.7},{"place":828,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":50.3},{"place":829,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":50},{"place":830,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.6},{"place":831,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":49.2},{"place":832,"model":"internlm2-math-base-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":49.2},{"place":833,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":49.1},{"place":834,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":48.8},{"place":835,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":48.52},{"place":836,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":48.5},{"place":837,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":48.45},{"place":838,"model":"kwaiyii-13b-base","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":48.4},{"place":839,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":48.3},{"place":840,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":48.2},{"place":841,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.1},{"place":842,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":48.1},{"place":843,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":47.5},{"place":844,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":47.5},{"place":845,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":47.46},{"place":846,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":47.31},{"place":847,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":46.9},{"place":848,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":46.9},{"place":849,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":46.4},{"place":850,"model":"lfm2-700m","company":"liquidai","family":"LFM","version":"LFM2","score":46.4},{"place":851,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":46.4},{"place":852,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":46.1},{"place":853,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":45.8},{"place":854,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.7},{"place":855,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":45.19},{"place":856,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":44.9},{"place":857,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":44.9},{"place":858,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":44.88},{"place":859,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":44.88},{"place":860,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":44.1},{"place":861,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":44.1},{"place":862,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":44.05},{"place":863,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":44},{"place":864,"model":"chinchilla-70b","company":"google","family":"Chinchilla","version":"Chinchilla","score":43.7},{"place":865,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":43.5},{"place":866,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":43.5},{"place":867,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":43.44},{"place":868,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":43.4},{"place":869,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":43.37},{"place":870,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":43.2},{"place":871,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":43.1},{"place":872,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":43.1},{"place":873,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.8},{"place":874,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":42.7},{"place":875,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":42.3},{"place":876,"model":"granite-swash-2b","company":"IBM","family":"Granite","version":"Granite SWASH","score":42.23},{"place":877,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":42.23},{"place":878,"model":"llama-2-34b","company":"meta","family":"Llama","version":"Llama 2","score":42.2},{"place":879,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":42.15},{"place":880,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":41.8},{"place":881,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":41.6},{"place":882,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":41.24},{"place":883,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":41.1},{"place":884,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":41},{"place":885,"model":"chatglm2-12b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":40.94},{"place":886,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":40.7},{"place":887,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":40.49},{"place":888,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":40.3},{"place":889,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":40.1},{"place":890,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":40.03},{"place":891,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":40},{"place":892,"model":"olmo-2-0425-1b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":39.8},{"place":893,"model":"granite-swash-3b-a600m","company":"IBM","family":"Granite","version":"Granite SWASH","score":39.58},{"place":894,"model":"qwen2-audio-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Audio","score":39.5},{"place":895,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":39.42},{"place":896,"model":"mobilellm-r1-360m-base","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":39.4},{"place":897,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":39.04},{"place":898,"model":"baguettotron-321m","company":"pleias","family":"Baguettotron","version":"Baguettotron","score":39},{"place":899,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":39},{"place":900,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":38.9},{"place":901,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":38.8},{"place":902,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":38.51},{"place":903,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":38.4},{"place":904,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":38.4},{"place":905,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":38.4},{"place":906,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":38.36},{"place":907,"model":"chatglm2-12b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":38.13},{"place":908,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":37.83},{"place":909,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":37.7},{"place":910,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":37.4},{"place":911,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":37.1},{"place":912,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":36.8},{"place":913,"model":"evabyte-6.5b","company":"hku","family":"EvaByte","version":"EvaByte 6.5B","score":36.7},{"place":914,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":36.7},{"place":915,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":36.54},{"place":916,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.5},{"place":917,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":36.5},{"place":918,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":36.5},{"place":919,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":36.5},{"place":920,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.47},{"place":921,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":36.4},{"place":922,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":36.4},{"place":923,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":36.2},{"place":924,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":36},{"place":925,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":35.86},{"place":926,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":35.71},{"place":927,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":35.6},{"place":928,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":35.4},{"place":929,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":35.4},{"place":930,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":35.3},{"place":931,"model":"mistral-7b-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":34.72},{"place":932,"model":"huginn-3.5b","company":"tomg-umd","family":"Huginn","version":"Huginn","score":34.6},{"place":933,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":34.6},{"place":934,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":34.5},{"place":935,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":34.5},{"place":936,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":34.3},{"place":937,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":34},{"place":938,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":34},{"place":939,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":33.66},{"place":940,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":33.13},{"place":941,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":33},{"place":942,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":32.8},{"place":943,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":32.7},{"place":944,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":32.7},{"place":945,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":32.5},{"place":946,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":32.4},{"place":947,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":32.4},{"place":948,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":32.4},{"place":949,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":32.37},{"place":950,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":32.37},{"place":951,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":31.8},{"place":952,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":31.8},{"place":953,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":31.77},{"place":954,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":31.2},{"place":955,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":31.2},{"place":956,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":31},{"place":957,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":31},{"place":958,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":30.63},{"place":959,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":30.3},{"place":960,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":30.2},{"place":961,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":30.1},{"place":962,"model":"bielik-7b-instruct-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":29.95},{"place":963,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":29.6},{"place":964,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":29.6},{"place":965,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":29.57},{"place":966,"model":"bielik-7b-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":29.49},{"place":967,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":29.2},{"place":968,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":28.89},{"place":969,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":28.89},{"place":970,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":28.81},{"place":971,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":28.8},{"place":972,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":28.73},{"place":973,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":28.7},{"place":974,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":28.43},{"place":975,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":28.4},{"place":976,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":28.13},{"place":977,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":28.05},{"place":978,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":27.8},{"place":979,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":27.2},{"place":980,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":26.8},{"place":981,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":26.76},{"place":982,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":26.6},{"place":983,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":26.3},{"place":984,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":26.16},{"place":985,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":26},{"place":986,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":25.9},{"place":987,"model":"yi-coder-1.5b","company":"01ai","family":"Yi","version":"Yi-Coder","score":25.5},{"place":988,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":25.25},{"place":989,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":25.2},{"place":990,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":24.6},{"place":991,"model":"mobilellm-r1-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":24.5},{"place":992,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":24.5},{"place":993,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":24.49},{"place":994,"model":"blt-7b","company":"meta","family":"BLT","version":"BLT 7B","score":24.2},{"place":995,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":24},{"place":996,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":23.4},{"place":997,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":23.3},{"place":998,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":23.28},{"place":999,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":22.8},{"place":1000,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":22.74},{"place":1001,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":22.44},{"place":1002,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":22.44},{"place":1003,"model":"codegeex2-6b","company":"zai","family":"CodeGeeX","version":"CodeGeeX2","score":22.2},{"place":1004,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":22.1},{"place":1005,"model":"qwen1.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":22},{"place":1006,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":21.6},{"place":1007,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":21.3},{"place":1008,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":21.2},{"place":1009,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":21.15},{"place":1010,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":21.15},{"place":1011,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":20.8},{"place":1012,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":20.55},{"place":1013,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":20.32},{"place":1014,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":20.3},{"place":1015,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":19.6},{"place":1016,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":19.5},{"place":1017,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":19.3},{"place":1018,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":19.26},{"place":1019,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":18.8},{"place":1020,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":18.4},{"place":1021,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":18.2},{"place":1022,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":18},{"place":1023,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":17.8},{"place":1024,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":17.7},{"place":1025,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":17.7},{"place":1026,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":17.4},{"place":1027,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":16.83},{"place":1028,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":16.7},{"place":1029,"model":"mobilellm-r1-140m-base","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":16.3},{"place":1030,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":16.22},{"place":1031,"model":"minerva-8b","company":"google","family":"Minerva","version":"Minerva","score":16.2},{"place":1032,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":16.2},{"place":1033,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":16},{"place":1034,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":15.85},{"place":1035,"model":"codeshell-7b","company":"wisdomshell","family":"CodeShell","version":"CodeShell","score":15.8},{"place":1036,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":15.5},{"place":1037,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":15.3},{"place":1038,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":15.2},{"place":1039,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":14.6},{"place":1040,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":14.6},{"place":1041,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":14.25},{"place":1042,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":13.57},{"place":1043,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":13.57},{"place":1044,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":13.5},{"place":1045,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":12.4},{"place":1046,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":11.98},{"place":1047,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":11.3},{"place":1048,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":11},{"place":1049,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":11},{"place":1050,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":10.31},{"place":1051,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":10.1},{"place":1052,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":10},{"place":1053,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":9.78},{"place":1054,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":9.7},{"place":1055,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":9.17},{"place":1056,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":9.1},{"place":1057,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":9.1},{"place":1058,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":8.64},{"place":1059,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":8.4},{"place":1060,"model":"mobilellm-r1.5-140m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":8.3},{"place":1061,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":8.1},{"place":1062,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":7.59},{"place":1063,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":7.2},{"place":1064,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":7.05},{"place":1065,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":6.8},{"place":1066,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":6.8},{"place":1067,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":6.8},{"place":1068,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":6},{"place":1069,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":5.84},{"place":1070,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":5.8},{"place":1071,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":5.5},{"place":1072,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":5.46},{"place":1073,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":5},{"place":1074,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":4.82},{"place":1075,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":4.62},{"place":1076,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":4.4},{"place":1077,"model":"mobilellm-r1-140m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":4.1},{"place":1078,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":3.94},{"place":1079,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":3.64},{"place":1080,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":3.41},{"place":1081,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":3},{"place":1082,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":3},{"place":1083,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":2.73},{"place":1084,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":2.7},{"place":1085,"model":"trlm-135m","company":"loka","family":"TRLM","version":"TRLM","score":2.59},{"place":1086,"model":"gemma-3-pt-1b","company":"google","family":"Gemma","version":"Gemma 3","score":2.4},{"place":1087,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":2.4},{"place":1088,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":2.3},{"place":1089,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":2.27},{"place":1090,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":2.05},{"place":1091,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":1.7},{"place":1092,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1.6},{"place":1093,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":1.5},{"place":1094,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1.4},{"place":1095,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1.4},{"place":1096,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":1.1}]},{"id":"gsm8k-de","name":"GSM8K (DE)","topic":"Math (grade-school, German)","description":"German translation of the GSM8K grade-school math word problems.","url":"","leaderboard":"","github":"","paper":"","metric":"comp_acc","stars":"","top_model":"Llama-3_1-70B-TFree-HAT-SFT","top_percent":0.63,"top_model_id":"llama-3_1-70b-tfree-hat-sft","top_generation":"Llama TFree HAT","top_model_base":"Llama 3.1 70B TFree HAT","top_model_family":"Llama TFree HAT","top_company":"alephalpha","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.63},{"place":2,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.139}]},{"id":"gsm8k-decision","name":"GSM8K (decision)","topic":"Math (grade-school)","description":"GSM8K posed as choices among candidate answers; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://huggingface.co/datasets/openai/gsm8k","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"vLLM-SR d3","top_percent":85.2,"top_model_id":"vllm-sr-d3","top_generation":"d3","top_model_base":"d3","top_model_family":"vLLM-SR d3","top_company":"vllm-sr","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":85.2},{"place":2,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":83.7},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":80.8},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":79.9},{"place":5,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":79},{"place":6,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":76.4},{"place":7,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":73},{"place":8,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":72.8},{"place":9,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":69.6},{"place":10,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":67.6},{"place":11,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":67.6},{"place":12,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":67.3},{"place":13,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":65},{"place":14,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":61.6},{"place":15,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59.4},{"place":16,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":59},{"place":17,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":58.1},{"place":18,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":51.8},{"place":19,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":50.3},{"place":20,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":48.9},{"place":21,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":48.7},{"place":22,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":46.2},{"place":23,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":43.3},{"place":24,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":41.6},{"place":25,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":36.5},{"place":26,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":34.9},{"place":27,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":32.7},{"place":28,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":29.5},{"place":29,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":25.6},{"place":30,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":25.2},{"place":31,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":24.7},{"place":32,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":22},{"place":33,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":21.6},{"place":34,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":20.7},{"place":35,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":19.9},{"place":36,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":18.6},{"place":37,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":18.4},{"place":38,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":17.3}]},{"id":"gsm8k-ja","name":"GSM8K (Japanese)","topic":"Math (grade-school, Japanese)","description":"Japanese translation of GSM8K grade-school math.","url":"https://huggingface.co/datasets/SakanaAI/gsm8k-ja-test_250-1319","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 1.2B JP 202606","top_percent":62.2,"top_model_id":"lfm2.5-1.2b-jp-202606","top_generation":"LFM2.5","top_model_base":"LFM2.5 1.2B JP","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":62.2},{"place":2,"model":"lfm2.5-1.2b-jp","company":"liquidai","family":"LFM","version":"LFM2.5","score":56},{"place":3,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":52.8},{"place":4,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":50.2},{"place":5,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":47.2},{"place":6,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":46.8},{"place":7,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":46},{"place":8,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":44.4},{"place":9,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":42.8},{"place":10,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":42.8},{"place":11,"model":"gemma-2-llama-swallow-2b-it-v0.1","company":"tokyotech","family":"Swallow","version":"Gemma-2-Llama Swallow","score":34.4},{"place":12,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":33.6},{"place":13,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":25.2},{"place":14,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":24.8}]},{"id":"gsm8k-ko","name":"GSM8K-Ko","topic":"Math (grade-school, Korean)","description":"Korean translation of the GSM8K grade-school math word problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-30B-A3B","top_percent":88.1,"top_model_id":"qwen3-30b-a3b","top_generation":"Qwen3","top_model_base":"Qwen3 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.1},{"place":2,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":88.1},{"place":3,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":81.43},{"place":4,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":77.48},{"place":5,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":77.48},{"place":6,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":70.43}]},{"id":"gsm8k-platinum","name":"GSM8K Platinum","topic":"Math (grade-school, hard)","description":"Harder subset/setting of GSM8K grade-school math problems.","url":"https://github.com/openai/grade-school-math","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-Linear-Base","top_percent":89.6,"top_model_id":"kimi-linear-base","top_generation":"Kimi Linear","top_model_base":"Kimi Linear","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":89.6},{"place":2,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":89.5},{"place":3,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":79.4}]},{"id":"gso-benchmark","name":"GSO Benchmark","topic":"Code generation","description":"LiveCodeBench GSO benchmark.","url":"https://livecodebench.github.io/gso.html","leaderboard":"https://gso-bench.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5.1","top_percent":88.24,"top_model_id":"claude-fable-5.1","top_generation":"Claude 5.1","top_model_base":"Claude Fable 5.1","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":88.24},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":79.41},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":78.43},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":76.47},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":47.06},{"place":6,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":44.12},{"place":7,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":41.18},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":40.2},{"place":9,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":37.25},{"place":10,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":31.37},{"place":11,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":27.45},{"place":12,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":26.47},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":22.55},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":18.63},{"place":15,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":14.71},{"place":16,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":13.73},{"place":17,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":9.8},{"place":18,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":8.82},{"place":19,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":8.8},{"place":20,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":6.9},{"place":21,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":6.9},{"place":22,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":6.86},{"place":23,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":6.86},{"place":24,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":4.9},{"place":25,"model":"qwen3-coder-480b-a35b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.9},{"place":26,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":4.9},{"place":27,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":4.9},{"place":28,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":4.6},{"place":29,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.92},{"place":30,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":3.8},{"place":31,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":3.6},{"place":32,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":2.94},{"place":33,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":2.9},{"place":34,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":1.3},{"place":35,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0}]},{"id":"habermas-machine-decision","name":"Habermas Machine (decision)","topic":"Deliberation / preference","description":"Predict group preference among candidate consensus statements; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/google-deepmind/habermas_machine","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef-Flash","top_percent":71.8,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":71.8},{"place":2,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":68.7},{"place":3,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":67.8},{"place":4,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":61.6},{"place":5,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":60.8},{"place":6,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":59.8},{"place":7,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":58.9},{"place":8,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":58.8},{"place":9,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":45.9},{"place":10,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":45.7},{"place":11,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":45.5},{"place":12,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":45.1},{"place":13,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":45},{"place":14,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":44.6},{"place":15,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":44.6},{"place":16,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":43.3},{"place":17,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":42.5},{"place":18,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":41.6},{"place":19,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":41.6},{"place":20,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":41.2},{"place":21,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":41.1},{"place":22,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":41.1},{"place":23,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":40.4},{"place":24,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":40.4},{"place":25,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":40},{"place":26,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":39.4},{"place":27,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":39.4},{"place":28,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":38.1},{"place":29,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":38},{"place":30,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":38},{"place":31,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":38},{"place":32,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":37.4},{"place":33,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":36.7},{"place":34,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":36.3},{"place":35,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":36.3},{"place":36,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":36.2},{"place":37,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":34.1},{"place":38,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":33.4}]},{"id":"hae-rae-bench","name":"HAE-RAE Bench","topic":"Korean language understanding","description":"Korean language understanding benchmark evaluating knowledge and reasoning.","url":"https://huggingface.co/datasets/HAERAE-HUB/HAE_RAE_BENCH","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kanana-1.5-32.5B-Base","top_percent":90.65,"top_model_id":"kanana-1.5-32.5b-base","top_generation":"Kanana 1.5","top_model_base":"Kanana 1.5 32.5B","top_model_family":"Kanana","top_company":"kakao","top_open_source":1,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":90.65},{"place":2,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":88.91},{"place":3,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":88.73},{"place":4,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":88.73},{"place":5,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":80.66},{"place":6,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.57},{"place":7,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.57},{"place":8,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.34},{"place":9,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":75.3},{"place":10,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.04},{"place":11,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":72.04},{"place":12,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":65.34},{"place":13,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":59.9},{"place":14,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":57.39},{"place":15,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":55.54},{"place":16,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":53.41},{"place":17,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":51},{"place":18,"model":"audio-flamingo-3","company":"nvidia","family":"Audio Flamingo","version":"Audio Flamingo 3","score":46},{"place":19,"model":"qwen2-audio-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Audio","score":40.8},{"place":20,"model":"x-omni","company":"tencent","family":"X-Omni","version":"X-Omni","score":21.3},{"place":21,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":20},{"place":22,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":14.9}]},{"id":"hallusionbench","name":"HallusionBench","topic":"Multimodal hallucination","description":"Benchmark for evaluating hallucination tendencies in multimodal LLMs.","url":"https://hallusionbench.github.io/","leaderboard":"","github":"https://github.com/FuxiaoLiu/HallusionBench","paper":"https://arxiv.org/abs/2310.14566","metric":"percent","stars":"","top_model":"Qwen3-VL 32B Thinking","top_percent":76.6,"top_model_id":"qwen3-vl-32b-thinking","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 32B Thinking","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":163,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.6},{"place":2,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.9},{"place":3,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.1},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":73.48},{"place":5,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.4},{"place":7,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":70.6},{"place":8,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":69.9},{"place":10,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":69.8},{"place":11,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":69.8},{"place":12,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.3},{"place":13,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":68.9},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68.6},{"place":15,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":68},{"place":16,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.9},{"place":17,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.6},{"place":18,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":67.4},{"place":19,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.4},{"place":20,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.3},{"place":21,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.7},{"place":22,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.7},{"place":23,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":66.58},{"place":24,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":66.14},{"place":25,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":66.1},{"place":26,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66},{"place":27,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":65.8},{"place":28,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":29,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.5},{"place":30,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":65.4},{"place":31,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.4},{"place":32,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":65.3},{"place":33,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":65.3},{"place":34,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":65.2},{"place":35,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":65.2},{"place":36,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":65.2},{"place":37,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65.2},{"place":38,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65},{"place":39,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":64.83},{"place":40,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.8},{"place":41,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.5},{"place":42,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":64.4},{"place":43,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":64.2},{"place":44,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.1},{"place":45,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.1},{"place":46,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.1},{"place":47,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.01},{"place":48,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":63.9},{"place":49,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":63.9},{"place":50,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":63.87},{"place":51,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":63.83},{"place":52,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.8},{"place":53,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.7},{"place":54,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":63.7},{"place":55,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.5},{"place":56,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":63.49},{"place":57,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":63.2},{"place":58,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":63.2},{"place":59,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":63.2},{"place":60,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":63.2},{"place":61,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":63.2},{"place":62,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.07},{"place":63,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":62.8},{"place":64,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":62.6},{"place":65,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.56},{"place":66,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":62.5},{"place":67,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62.35},{"place":68,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62.06},{"place":69,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.65},{"place":70,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.5},{"place":71,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":61.5},{"place":72,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.1},{"place":73,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":61.1},{"place":74,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":60.98},{"place":75,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":60.4},{"place":76,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":60.4},{"place":77,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":60.3},{"place":78,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":60.3},{"place":79,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":60.1},{"place":80,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":60},{"place":81,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.9},{"place":82,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":59.8},{"place":83,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":59.8},{"place":84,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":59.7},{"place":85,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":59.1},{"place":86,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":59.1},{"place":87,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.1},{"place":88,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":58.5},{"place":89,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":58.4},{"place":90,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":58.4},{"place":91,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":58.1},{"place":92,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":58.1},{"place":93,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":58.1},{"place":94,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":58.1},{"place":95,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58},{"place":96,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":57.85},{"place":97,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.6},{"place":98,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":57.4},{"place":99,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":57.2},{"place":100,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":57},{"place":101,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":57},{"place":102,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":56.9},{"place":103,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":56.8},{"place":104,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":56.5},{"place":105,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":56.4},{"place":106,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":56.4},{"place":107,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":56},{"place":108,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":55.9},{"place":109,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":55.5},{"place":110,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":55.2},{"place":111,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":55.1},{"place":112,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":55},{"place":113,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":55},{"place":114,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":55},{"place":115,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.9},{"place":116,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":54.5},{"place":117,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":54.5},{"place":118,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":53.6},{"place":119,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":53.6},{"place":120,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.1},{"place":121,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.1},{"place":122,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":52.5},{"place":123,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":52.14},{"place":124,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":52.1},{"place":125,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":51.9},{"place":126,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.7},{"place":127,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.4},{"place":128,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":51.1},{"place":129,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":50.7},{"place":130,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":50.6},{"place":131,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":50.6},{"place":132,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":50.3},{"place":133,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":50.2},{"place":134,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":50.1},{"place":135,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":49.9},{"place":136,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":49.9},{"place":137,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":49.8},{"place":138,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":49.8},{"place":139,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":49.8},{"place":140,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.3},{"place":141,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":49.3},{"place":142,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":49},{"place":143,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":48.4},{"place":144,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":48.1},{"place":145,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":47.8},{"place":146,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":47.7},{"place":147,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":47.6},{"place":148,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":47.6},{"place":149,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":47.4},{"place":150,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":47.4},{"place":151,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":47.2},{"place":152,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.7},{"place":153,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":46.7},{"place":154,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":46.6},{"place":155,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":46.5},{"place":156,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":46.5},{"place":157,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":46.4},{"place":158,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":46.3},{"place":159,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":46.1},{"place":160,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":46.1},{"place":161,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":46.1},{"place":162,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":46.02},{"place":163,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":45.87},{"place":164,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":45.8},{"place":165,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":45.7},{"place":166,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.6},{"place":167,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":45.6},{"place":168,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":45.2},{"place":169,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":45.2},{"place":170,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":45.2},{"place":171,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":45},{"place":172,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":45},{"place":173,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":44.8},{"place":174,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":44.8},{"place":175,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.1},{"place":176,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":44.1},{"place":177,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":43.9},{"place":178,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":43.9},{"place":179,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":42.6},{"place":180,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":42.5},{"place":181,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":42.4},{"place":182,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":42.4},{"place":183,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":42},{"place":184,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":41.9},{"place":185,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.8},{"place":186,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":41.7},{"place":187,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":41.7},{"place":188,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":41.6},{"place":189,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":41.6},{"place":190,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":41.6},{"place":191,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":41.3},{"place":192,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":41.2},{"place":193,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":41},{"place":194,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":40.9},{"place":195,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":40.6},{"place":196,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":40.5},{"place":197,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":39.7},{"place":198,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":39.3},{"place":199,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":39.2},{"place":200,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":39.2},{"place":201,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":39},{"place":202,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":37.9},{"place":203,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":37.8},{"place":204,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":34.8},{"place":205,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":34},{"place":206,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":32.9},{"place":207,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":27.9}]},{"id":"harbor-index","name":"Harbor-Index","topic":"Agentic coding","description":"Aggregate index of agentic terminal/coding tasks run through the Harbor evaluation framework.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":56.9,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.9},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.3},{"place":3,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":42.5},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":41},{"place":5,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":39.6},{"place":6,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":38.8},{"place":7,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":36.9},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":35.8},{"place":9,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":25.8},{"place":10,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":24.3},{"place":11,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":20},{"place":12,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":17.3},{"place":13,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":17.3},{"place":14,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":17},{"place":15,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":15.6}]},{"id":"hardmultiqa","name":"HardMultiQA","topic":"Russian factual knowledge","description":"Yandex 5-shot benchmark of hard multi-answer factual questions in Russian.","url":"https://huggingface.co/datasets/yandex/HardMultiQA","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":67.9,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":67.9},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":65.4},{"place":3,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":54.5},{"place":4,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":48.6},{"place":5,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.2}]},{"id":"harmbench","name":"HarmBench","topic":"Safety","description":"Harmfulness and safety compliance benchmark across a variety of risky prompts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-realtime-1.5","top_percent":100,"top_model_id":"gpt-realtime-1.5","top_generation":"GPT-realtime-1.5","top_model_base":"GPT-realtime","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":100},{"place":2,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":100},{"place":3,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":99.5},{"place":4,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":99.5},{"place":5,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":99},{"place":6,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":99},{"place":7,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":98},{"place":8,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":94.8},{"place":9,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":94.2},{"place":10,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":57.3},{"place":11,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":56},{"place":12,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.5}]},{"id":"harmfulq","name":"HarmfulQA","topic":"Safety","description":"Harmful question set testing models' ability to avoid unsafe answers.","url":"https://huggingface.co/datasets/d-llm/HarmfulQA","leaderboard":"","github":"https://github.com/declare-lab/red-instruct","paper":"https://arxiv.org/abs/2308.09662","metric":"percent","stars":"104","top_model":"K2-THINK","top_percent":99,"top_model_id":"k2-think","top_generation":"K2-THINK","top_model_base":"K2-THINK","top_model_family":"K2","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":99},{"place":2,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":79.4},{"place":3,"model":"chatgpt","company":"openai","family":"GPT","version":"ChatGPT","score":74.3}]},{"id":"healthbench","name":"HealthBench","topic":"Medical QA","description":"Comprehensive medical knowledge and clinical reasoning benchmark across specialties and tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":67.2,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":57,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":67.2},{"place":2,"model":"gpt-5-thinking-high","company":"openai","family":"GPT","version":"GPT-5","score":67.2},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":67.1},{"place":4,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":66.7},{"place":5,"model":"baichuan-m3-235b","company":"baichuan","family":"Baichuan-M","version":"Baichuan-M3","score":65.1},{"place":6,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":63.3},{"place":7,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":62.7},{"place":8,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":62.5},{"place":9,"model":"antangelmed","company":"antgroup","family":"AntAngelMed","version":"AntAngelMed","score":62.5},{"place":10,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":61.1},{"place":11,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":60.2},{"place":12,"model":"baichuan-m2-32b","company":"baichuan","family":"Baichuan","version":"Baichuan-M2","score":60.1},{"place":13,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":59.82},{"place":14,"model":"o3","company":"openai","family":"o3","version":"o3","score":59.8},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59.3},{"place":16,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":58.5},{"place":17,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":58.3},{"place":18,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":58},{"place":19,"model":"ring-1t","company":"antgroup","family":"Ring","version":"Ring","score":57.93},{"place":20,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":57.7},{"place":21,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":57},{"place":22,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":57},{"place":23,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":56.5},{"place":24,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":55.8},{"place":25,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":55.56},{"place":26,"model":"gpt-5.2-instant","company":"openai","family":"GPT","version":"GPT-5.2","score":55.4},{"place":27,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":55.3},{"place":28,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":55.2},{"place":29,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":55.1},{"place":30,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":55},{"place":31,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":54.99},{"place":32,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":54.5},{"place":33,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":54.5},{"place":34,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":54.44},{"place":35,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":54.1},{"place":36,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":53.3},{"place":37,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":53.2},{"place":38,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":53},{"place":39,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":52.4},{"place":40,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":52.1},{"place":41,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":51.6},{"place":42,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":51.6},{"place":43,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":51.4},{"place":44,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":51.2},{"place":45,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":50.4},{"place":46,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":50.19},{"place":47,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.57},{"place":48,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.39},{"place":49,"model":"ring-flash-linear-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":49.1},{"place":50,"model":"qwen3-32b-thinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":47.61},{"place":51,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":46.9},{"place":52,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":46.61},{"place":53,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":46.2},{"place":54,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.2},{"place":55,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":43.8},{"place":56,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.9},{"place":57,"model":"medgemma-27b-text-it","company":"google","family":"Gemma","version":"MedGemma","score":37.4},{"place":58,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":36.3},{"place":59,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":32},{"place":60,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":30},{"place":61,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":28.7}]},{"id":"healthbench-consensus","name":"HealthBench Consensus","topic":"Medical","description":"HealthBench consensus subset (criteria validated by multiple physicians); length-adjusted score.","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":96.2,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":96.2},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":96},{"place":3,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":95.9},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95.6},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":95.5},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":95.5},{"place":7,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":95.5},{"place":8,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":95.1},{"place":9,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":95.1},{"place":10,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":95.1},{"place":11,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":95},{"place":12,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":94.8},{"place":13,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":94.7},{"place":14,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":93.8}]},{"id":"healthbench-hard","name":"HealthBench-Hard","topic":"Medical QA (hard)","description":"Challenging subset of HealthBench focusing on complex, ambiguous clinical cases.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":46.2,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":46.2},{"place":2,"model":"baichuan-m3-235b","company":"baichuan","family":"Baichuan-M","version":"Baichuan-M3","score":44.4},{"place":3,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":42.8},{"place":4,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":42},{"place":5,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":40.1},{"place":6,"model":"antangelmed","company":"antgroup","family":"AntAngelMed","version":"AntAngelMed","score":39.6},{"place":7,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":38.6},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":36.6},{"place":9,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":36.2},{"place":10,"model":"baichuan-m2-32b","company":"baichuan","family":"Baichuan","version":"Baichuan-M2","score":34.7},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":33.1},{"place":12,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":32.7},{"place":13,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":32},{"place":14,"model":"o3","company":"openai","family":"o3","version":"o3","score":31.6},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":31.5},{"place":16,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":31.4},{"place":17,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":31.4},{"place":18,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":31.4},{"place":19,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":30.1},{"place":20,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":29.1},{"place":21,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":28.7},{"place":22,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":27.8},{"place":23,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":27.2},{"place":24,"model":"gpt-5.2-instant","company":"openai","family":"GPT","version":"GPT-5.2","score":26.8},{"place":25,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":25.9},{"place":26,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":25.9},{"place":27,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":22.9},{"place":28,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":21.7},{"place":29,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":21.5},{"place":30,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":20.6},{"place":31,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":20.3},{"place":32,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":20},{"place":33,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":15.3},{"place":34,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":15.2},{"place":35,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":15},{"place":36,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":14.8},{"place":37,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":11},{"place":38,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":10.9},{"place":39,"model":"medgemma-27b-text-it","company":"google","family":"Gemma","version":"MedGemma","score":8.5}]},{"id":"healthbench-hard-hallucinations","name":"HealthBench-Hard Hallucinations","topic":"Medical hallucination safety","description":"Measures hallucination and unsafe medical advice under hard clinical scenarios.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":1.6,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":1.6},{"place":2,"model":"o3","company":"openai","family":"o3","version":"o3","score":12.9},{"place":3,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":15.8}]},{"id":"healthbench-professional","name":"HealthBench Professional","topic":"Medical QA","description":"525 physician-authored clinical conversations (consults, documentation, research) graded against rubric criteria.","url":"https://arxiv.org/abs/2604.27470","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OpenEvidence Darwin","top_percent":82.7,"top_model_id":"openevidence-darwin","top_generation":"OpenEvidence 2026","top_model_base":"OpenEvidence Darwin","top_model_family":"OpenEvidence","top_company":"openevidence","top_open_source":0,"lower_is_better":false,"bench_models":37,"total_models":3854,"placements":[{"place":1,"model":"openevidence-darwin","company":"openevidence","family":"OpenEvidence","version":"OpenEvidence 2026","score":82.7},{"place":2,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":69.2},{"place":3,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":66},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":65.6},{"place":5,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":65.35},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":65.3},{"place":7,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":64.8},{"place":8,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":64.7},{"place":9,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":64.7},{"place":10,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":64.2},{"place":11,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":63.4},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.3},{"place":13,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":62.7},{"place":14,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":62.3},{"place":15,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":62.1},{"place":16,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":60.9},{"place":17,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":60.8},{"place":18,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":60.8},{"place":19,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":60.76},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":60.5},{"place":21,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":60.5},{"place":22,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":59.8},{"place":23,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":58.1},{"place":24,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57.8},{"place":25,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":57.7},{"place":26,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":57.4},{"place":27,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":56.9},{"place":28,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":56.7},{"place":29,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.4},{"place":30,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":55.8},{"place":31,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":55.7},{"place":32,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":55.2},{"place":33,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":54},{"place":34,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":53},{"place":35,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":52.1},{"place":36,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":51.8},{"place":37,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":50.37},{"place":38,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":49.56},{"place":39,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":49.56},{"place":40,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":49.5},{"place":41,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":49.07},{"place":42,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":48.5},{"place":43,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":48.2},{"place":44,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":44.2},{"place":45,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":44.1},{"place":46,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":38.4},{"place":47,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32.2}]},{"id":"hellaswag","name":"HellaSwag","topic":"Commonsense reasoning","description":"Adversarial commonsense sentence completion.","url":"https://github.com/rowanz/hellaswag","leaderboard":"","github":"","paper":"","metric":"percent","stars":"220","top_model":"Clef-Omni","top_percent":99.1,"top_model_id":"clef-omni","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":415,"total_models":3854,"placements":[{"place":1,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":99.1},{"place":2,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":98.6},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":98.2},{"place":4,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":98.2},{"place":5,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":97.2},{"place":6,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":97},{"place":7,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":96.6},{"place":8,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":96.4},{"place":9,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":96.4},{"place":10,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":96.2},{"place":11,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":96},{"place":12,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":95.9},{"place":13,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":95.8},{"place":14,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":95},{"place":15,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":94.9},{"place":16,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":94.8},{"place":17,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":94.6},{"place":18,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":94.5},{"place":19,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":94.3},{"place":20,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":94.1},{"place":21,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":94.1},{"place":22,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":93.8},{"place":23,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":93.4},{"place":24,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.1},{"place":25,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":92.5},{"place":26,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":92.3},{"place":27,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":91.79},{"place":28,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":91.4},{"place":29,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":91},{"place":30,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":91},{"place":31,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":90.92},{"place":32,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":90.6},{"place":33,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.51},{"place":34,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":90.3},{"place":35,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":90.3},{"place":36,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":90.2},{"place":37,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":90.17},{"place":38,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":90.11},{"place":39,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.1},{"place":40,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.9},{"place":41,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":89.9},{"place":42,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":89.8},{"place":43,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":89.44},{"place":44,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":89.4},{"place":45,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":89.4},{"place":46,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":89.2},{"place":47,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":89.2},{"place":48,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":89.2},{"place":49,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":89.2},{"place":50,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":89},{"place":51,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88.97},{"place":52,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":88.96},{"place":53,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":88.9},{"place":54,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":88.88},{"place":55,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88.8},{"place":56,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":88.8},{"place":57,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":88.7},{"place":58,"model":"command-r-plus-08-2024","company":"cohere","family":"Command","version":"Command","score":88.6},{"place":59,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":88.6},{"place":60,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":88.5},{"place":61,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":88.5},{"place":62,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":88.5},{"place":63,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":88.5},{"place":64,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":88.3},{"place":65,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.3},{"place":66,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.29},{"place":67,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":88.2},{"place":68,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":88.16},{"place":69,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":88.13},{"place":70,"model":"glm-5-base","company":"zai","family":"GLM","version":"GLM 5","score":88.1},{"place":71,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":88},{"place":72,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88},{"place":73,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":88},{"place":74,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":87.9},{"place":75,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":87.9},{"place":76,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":87.8},{"place":77,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":87.8},{"place":78,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":87.8},{"place":79,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":87.8},{"place":80,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":87.7},{"place":81,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":87.6},{"place":82,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.6},{"place":83,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":87.6},{"place":84,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":87.5},{"place":85,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":87.5},{"place":86,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.48},{"place":87,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":87.3},{"place":88,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":87.3},{"place":89,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":87.3},{"place":90,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":87.2},{"place":91,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":87.2},{"place":92,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":87.1},{"place":93,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":87.1},{"place":94,"model":"glm-5.3-flash-base","company":"zai","family":"GLM","version":"GLM 5.3","score":87.1},{"place":95,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":87.1},{"place":96,"model":"jamba-v0.1","company":"ai21","family":"Jamba","version":"Jamba","score":87.1},{"place":97,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":87},{"place":98,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":86.9},{"place":99,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":86.8},{"place":100,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":86.6},{"place":101,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":86.6},{"place":102,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":86.6},{"place":103,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":86.51},{"place":104,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":86.5},{"place":105,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":86.42},{"place":106,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":86.4},{"place":107,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":86.4},{"place":108,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":86.36},{"place":109,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.31},{"place":110,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.3},{"place":111,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":86.3},{"place":112,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":86.1},{"place":113,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":86.1},{"place":114,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":86.02},{"place":115,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86},{"place":116,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86},{"place":117,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":86},{"place":118,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":86},{"place":119,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":86},{"place":120,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":85.97},{"place":121,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":85.9},{"place":122,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":85.9},{"place":123,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":85.9},{"place":124,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":85.8},{"place":125,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":85.8},{"place":126,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":85.76},{"place":127,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.7},{"place":128,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":85.68},{"place":129,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.61},{"place":130,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":85.6},{"place":131,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":85.6},{"place":132,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.56},{"place":133,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.55},{"place":134,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":85.55},{"place":135,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":85.5},{"place":136,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":85.49},{"place":137,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":85.4},{"place":138,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.4},{"place":139,"model":"qwen-72b","company":"qwen","family":"Qwen","version":"Qwen","score":85.4},{"place":140,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":85.31},{"place":141,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.3},{"place":142,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.3},{"place":143,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":85.3},{"place":144,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":85.3},{"place":145,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":85.26},{"place":146,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":85.2},{"place":147,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.2},{"place":148,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.1},{"place":149,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.1},{"place":150,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":85},{"place":151,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":85},{"place":152,"model":"marin-32b-base","company":"marin","family":"Marin","version":"Marin 32B","score":85},{"place":153,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":85},{"place":154,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":85},{"place":155,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":84.97},{"place":156,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":84.9},{"place":157,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":84.88},{"place":158,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":84.8},{"place":159,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":84.8},{"place":160,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":84.8},{"place":161,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.8},{"place":162,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":84.7},{"place":163,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":84.69},{"place":164,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":84.55},{"place":165,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":84.4},{"place":166,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":84.4},{"place":167,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.3},{"place":168,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":84.2},{"place":169,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":84.2},{"place":170,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":84.2},{"place":171,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.1},{"place":172,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":84.1},{"place":173,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":84},{"place":174,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":84},{"place":175,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":84},{"place":176,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":84},{"place":177,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":83.99},{"place":178,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":83.76},{"place":179,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":83.7},{"place":180,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":83.7},{"place":181,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":83.68},{"place":182,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":83.6},{"place":183,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":83.5},{"place":184,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":83.5},{"place":185,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":83.4},{"place":186,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":83.31},{"place":187,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":83.3},{"place":188,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":83.3},{"place":189,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":83.26},{"place":190,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":83.2},{"place":191,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":83.2},{"place":192,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":83.1},{"place":193,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":83.1},{"place":194,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":83.1},{"place":195,"model":"mistral-7b-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":83.08},{"place":196,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":83},{"place":197,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":83},{"place":198,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":83},{"place":199,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":83},{"place":200,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":82.8},{"place":201,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":82.7},{"place":202,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":82.6},{"place":203,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":82.59},{"place":204,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":82.51},{"place":205,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":82.5},{"place":206,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":82.47},{"place":207,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":82.4},{"place":208,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":82.27},{"place":209,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":82.23},{"place":210,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":82.2},{"place":211,"model":"apertus-v1.5-70b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":82.2},{"place":212,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":82.2},{"place":213,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":82.1},{"place":214,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":82.1},{"place":215,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":82.1},{"place":216,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":82},{"place":217,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":81.97},{"place":218,"model":"bielik-11b-v3.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":81.96},{"place":219,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":81.94},{"place":220,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":81.9},{"place":221,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":81.9},{"place":222,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":81.9},{"place":223,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":81.9},{"place":224,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":81.84},{"place":225,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":81.8},{"place":226,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":81.8},{"place":227,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":81.6},{"place":228,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":81.6},{"place":229,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":81.59},{"place":230,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":81.5},{"place":231,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.5},{"place":232,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":81.5},{"place":233,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":81.4},{"place":234,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":81.4},{"place":235,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":81.4},{"place":236,"model":"bielik-11b-v3.0","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":81.38},{"place":237,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":81.3},{"place":238,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":81.2},{"place":239,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":81.08},{"place":240,"model":"openchat-3.5-0106-gemma","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":81.08},{"place":241,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":81},{"place":242,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81},{"place":243,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":81},{"place":244,"model":"chinchilla-70b","company":"google","family":"Chinchilla","version":"Chinchilla","score":80.8},{"place":245,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":80.8},{"place":246,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":80.8},{"place":247,"model":"bielik-11b-v2.5-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.5","score":80.71},{"place":248,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":80.7},{"place":249,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":80.7},{"place":250,"model":"palm-cont-62b","company":"google","family":"PaLM","version":"PaLM","score":80.6},{"place":251,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":80.6},{"place":252,"model":"bielik-11b-v2.6-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.6","score":80.56},{"place":253,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":80.5},{"place":254,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":80.43},{"place":255,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":80.3},{"place":256,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":80.3},{"place":257,"model":"bielik-11b-v2.1-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.1","score":80.2},{"place":258,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":80.2},{"place":259,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.2},{"place":260,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":80.2},{"place":261,"model":"bielik-11b-v2.2-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.2","score":80.16},{"place":262,"model":"bielik-11b-v2.3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.3","score":80.11},{"place":263,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":80.11},{"place":264,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":80.1},{"place":265,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":80.08},{"place":266,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.98},{"place":267,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":79.9},{"place":268,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":79.9},{"place":269,"model":"bielik-11b-v2","company":"SpeakLeash","family":"Bielik","version":"Bielik v2","score":79.84},{"place":270,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":79.72},{"place":271,"model":"palm-62b","company":"google","family":"PaLM","version":"PaLM","score":79.7},{"place":272,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":79.7},{"place":273,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":79.7},{"place":274,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":79.7},{"place":275,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":79.69},{"place":276,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.6},{"place":277,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79.56},{"place":278,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.51},{"place":279,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":79.47},{"place":280,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":79.46},{"place":281,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":79.3},{"place":282,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.3},{"place":283,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":79.3},{"place":284,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":79.23},{"place":285,"model":"gopher-280b","company":"google","family":"Gopher","version":"Gopher","score":79.2},{"place":286,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":79.2},{"place":287,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":79.2},{"place":288,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":79.2},{"place":289,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":79.2},{"place":290,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":79.1},{"place":291,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":79.01},{"place":292,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":79},{"place":293,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":79},{"place":294,"model":"eurollm-22b-base","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":79},{"place":295,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.96},{"place":296,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":78.9},{"place":297,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":78.9},{"place":298,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":78.8},{"place":299,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":78.8},{"place":300,"model":"bielik-11b-v2.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.0","score":78.65},{"place":301,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":78.62},{"place":302,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":78.56},{"place":303,"model":"meta-llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":78.55},{"place":304,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":78.5},{"place":305,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":78.5},{"place":306,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":78.37},{"place":307,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":78.2},{"place":308,"model":"apertus-v1.5-8b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":78.1},{"place":309,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":78.1},{"place":310,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":78.1},{"place":311,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":77.8},{"place":312,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.7},{"place":313,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":77.63},{"place":314,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":77.5},{"place":315,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":77.5},{"place":316,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":77.4},{"place":317,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":77.4},{"place":318,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":77.4},{"place":319,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":77.2},{"place":320,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":77.2},{"place":321,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":77.2},{"place":322,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":77.1},{"place":323,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.1},{"place":324,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":77.1},{"place":325,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":77},{"place":326,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":76.8},{"place":327,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":76.7},{"place":328,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":76.68},{"place":329,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":76.68},{"place":330,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":76.5},{"place":331,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":76.49},{"place":332,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":76.4},{"place":333,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":76.4},{"place":334,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":76.4},{"place":335,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":76.3},{"place":336,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":76.2},{"place":337,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":76.19},{"place":338,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":76.1},{"place":339,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":76.1},{"place":340,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":76.1},{"place":341,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":76.1},{"place":342,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":76},{"place":343,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":75.92},{"place":344,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":75.71},{"place":345,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":75.7},{"place":346,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.66},{"place":347,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":75.65},{"place":348,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":75.63},{"place":349,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":75.62},{"place":350,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":75.6},{"place":351,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":75.58},{"place":352,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":75.57},{"place":353,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":75.45},{"place":354,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":75.4},{"place":355,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":75.32},{"place":356,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":75.18},{"place":357,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":75.1},{"place":358,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":75},{"place":359,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":74.96},{"place":360,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":74.71},{"place":361,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":74.6},{"place":362,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.6},{"place":363,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":74.6},{"place":364,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.6},{"place":365,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.54},{"place":366,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":74.52},{"place":367,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":74.52},{"place":368,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":74.4},{"place":369,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":74.35},{"place":370,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":74.3},{"place":371,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":74.29},{"place":372,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":74.2},{"place":373,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.1},{"place":374,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":74.1},{"place":375,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":74.1},{"place":376,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":74},{"place":377,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.95},{"place":378,"model":"bielik-4.5b-v3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":73.9},{"place":379,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":73.8},{"place":380,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":73.7},{"place":381,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":73.7},{"place":382,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":73.54},{"place":383,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":73.47},{"place":384,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":73.1},{"place":385,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":73.1},{"place":386,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":73.09},{"place":387,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":73.07},{"place":388,"model":"bielik-4.5b-v3","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":73.01},{"place":389,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":72.9},{"place":390,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":72.7},{"place":391,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":72.64},{"place":392,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":72.37},{"place":393,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":72.2},{"place":394,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":72.2},{"place":395,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":71.87},{"place":396,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":71.81},{"place":397,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":71.7},{"place":398,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":71.5},{"place":399,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":71.5},{"place":400,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":71.4},{"place":401,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":71.4},{"place":402,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":71.39},{"place":403,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":71.32},{"place":404,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":71.28},{"place":405,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":71.27},{"place":406,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":71},{"place":407,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":70.9},{"place":408,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":70.8},{"place":409,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":70.74},{"place":410,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":70.63},{"place":411,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":70.6},{"place":412,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":70.39},{"place":413,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":70.32},{"place":414,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":70.3},{"place":415,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":70.24},{"place":416,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":70.24},{"place":417,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":70.2},{"place":418,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":69.9},{"place":419,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":69.85},{"place":420,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":69.51},{"place":421,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":69.23},{"place":422,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":69.2},{"place":423,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":69.02},{"place":424,"model":"bielik-7b-instruct-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":68.91},{"place":425,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.89},{"place":426,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":68.8},{"place":427,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.79},{"place":428,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":68.7},{"place":429,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":68.7},{"place":430,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":68.5},{"place":431,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":68.5},{"place":432,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.4},{"place":433,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":68.4},{"place":434,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":68.3},{"place":435,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":68.25},{"place":436,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":68.2},{"place":437,"model":"bielik-7b-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":67.92},{"place":438,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.9},{"place":439,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":67.9},{"place":440,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":67.84},{"place":441,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.73},{"place":442,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":67.5},{"place":443,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":67.3},{"place":444,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":67.11},{"place":445,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.09},{"place":446,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":67},{"place":447,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":67},{"place":448,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":66.9},{"place":449,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":66.76},{"place":450,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":66.7},{"place":451,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":66.6},{"place":452,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.4},{"place":453,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":66.1},{"place":454,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":65.69},{"place":455,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":65.67},{"place":456,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":65.54},{"place":457,"model":"huginn-3.5b","company":"tomg-umd","family":"Huginn","version":"Huginn","score":65.2},{"place":458,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":65.2},{"place":459,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":65.03},{"place":460,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":64.8},{"place":461,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.6},{"place":462,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":64.5},{"place":463,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":64.24},{"place":464,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":64.21},{"place":465,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":64.1},{"place":466,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":64.1},{"place":467,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":63.74},{"place":468,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":63.7},{"place":469,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.4},{"place":470,"model":"hrm-text-1b","company":"sapient","family":"HRM","version":"HRM-Text","score":63.4},{"place":471,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":63.33},{"place":472,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":63.3},{"place":473,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":63.04},{"place":474,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":62.9},{"place":475,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":62.9},{"place":476,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":62.9},{"place":477,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":62.7},{"place":478,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":62.3},{"place":479,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.23},{"place":480,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.2},{"place":481,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":61.9},{"place":482,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":61.8},{"place":483,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":61.74},{"place":484,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":61.6},{"place":485,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":61.4},{"place":486,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":61.22},{"place":487,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":61.2},{"place":488,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.9},{"place":489,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":60.84},{"place":490,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.56},{"place":491,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":60.4},{"place":492,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.2},{"place":493,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":60},{"place":494,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":59.9},{"place":495,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":59.6},{"place":496,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":59.39},{"place":497,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":59.35},{"place":498,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":59.28},{"place":499,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":59},{"place":500,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":58.53},{"place":501,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":58.48},{"place":502,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":58.4},{"place":503,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":58.33},{"place":504,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":57.9},{"place":505,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":57.4},{"place":506,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":57.25},{"place":507,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":57},{"place":508,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":57},{"place":509,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":57},{"place":510,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":56.9},{"place":511,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":56.7},{"place":512,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":56.12},{"place":513,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":56.1},{"place":514,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":56.1},{"place":515,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":56},{"place":516,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":56},{"place":517,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":55.63},{"place":518,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":55.5},{"place":519,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.31},{"place":520,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":55.3},{"place":521,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":55},{"place":522,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":54.81},{"place":523,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":54.72},{"place":524,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":54.56},{"place":525,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":53.8},{"place":526,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":53.7},{"place":527,"model":"apertus-v1.1-4b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":53.51},{"place":528,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":53.38},{"place":529,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":52.9},{"place":530,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":52.4},{"place":531,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52.38},{"place":532,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":52.2},{"place":533,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52.1},{"place":534,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":51.93},{"place":535,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.7},{"place":536,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":49.5},{"place":537,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":49.36},{"place":538,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":49.3},{"place":539,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.27},{"place":540,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":49.1},{"place":541,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":48.4},{"place":542,"model":"apertus-v1.1-1.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":48.31},{"place":543,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":48.1},{"place":544,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":47.68},{"place":545,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":47.5},{"place":546,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":47.1},{"place":547,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":44.8},{"place":548,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":44.5},{"place":549,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":44.29},{"place":550,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":43.7},{"place":551,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":43.6},{"place":552,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":42.24},{"place":553,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":42.17},{"place":554,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":42.1},{"place":555,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":42.1},{"place":556,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":41.2},{"place":557,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":41.1},{"place":558,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":41.01},{"place":559,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":40.9},{"place":560,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":40.9},{"place":561,"model":"apertus-v1.1-0.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":40.42},{"place":562,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.5},{"place":563,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":39.4},{"place":564,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":37.7},{"place":565,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":36.7},{"place":566,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":36.4},{"place":567,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":34.4},{"place":568,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":33.1},{"place":569,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":32.2},{"place":570,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":30.4},{"place":571,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":29.6},{"place":572,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.809},{"place":573,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.665}]},{"id":"hellaswag-de","name":"HellaSwag (DE)","topic":"Commonsense reasoning (German)","description":"German translation of the HellaSwag commonsense benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"norm_log_acc","stars":"","top_model":"Llama-3_1-70B-TFree-HAT-SFT","top_percent":0.727,"top_model_id":"llama-3_1-70b-tfree-hat-sft","top_generation":"Llama TFree HAT","top_model_base":"Llama 3.1 70B TFree HAT","top_model_family":"Llama TFree HAT","top_company":"alephalpha","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.727},{"place":2,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.707}]},{"id":"helmet-longqa","name":"HELMET LongQA","topic":"Long-context QA","description":"Long-context subset of the HELMET benchmark focusing on grounded question answering.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Jamba Mini 1.6","top_percent":46.9,"top_model_id":"jamba-mini-1.6","top_generation":"Jamba Mini","top_model_base":"Jamba Mini 1.6","top_model_family":"Jamba","top_company":"ai21","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":46.9},{"place":2,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":33},{"place":3,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":29.2},{"place":4,"model":"command-r7b","company":"cohere","family":"Command","version":"Command","score":9.6}]},{"id":"helpsteer2","name":"HelpSteer2","topic":"Response quality rating","description":"NVIDIA HelpSteer2 helpfulness/attribute rating, posed as decisions.","url":"https://huggingface.co/datasets/nvidia/HelpSteer2","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Decider 4B (Mapika)","top_percent":42,"top_model_id":"mapika-decider-4b","top_generation":"Decider","top_model_base":"Decider","top_model_family":"Decider","top_company":"mapika","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"mapika-decider-4b","company":"mapika","family":"Decider","version":"Decider","score":42},{"place":2,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":36.7},{"place":3,"model":"mapika-decider-2b","company":"mapika","family":"Decider","version":"Decider","score":32}]},{"id":"herobench","name":"HeroBench","topic":"Long-horizon planning","description":"Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/pdf/2508.12782","metric":"percent","stars":"","top_model":"Grok 4","top_percent":91.7,"top_model_id":"grok-4","top_generation":"Grok 4","top_model_base":"Grok 4","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":91.7},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":83.9},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.9},{"place":4,"model":"o3","company":"openai","family":"o3","version":"o3","score":60.6},{"place":5,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":44.4},{"place":6,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":35},{"place":7,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":35},{"place":8,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":31.7},{"place":9,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":26.1},{"place":10,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":24.4},{"place":11,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":21.7},{"place":12,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":17.2},{"place":13,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":16.1},{"place":14,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.3},{"place":15,"model":"deepseek-r1-70b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":11.2},{"place":16,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":10},{"place":17,"model":"magistral-medium","company":"magistral","family":"Magistral","version":"Magistral","score":9.4},{"place":18,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":8.9},{"place":19,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":8.3},{"place":20,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":7.2},{"place":21,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":3.9},{"place":22,"model":"gigachat-2-max","company":"gigachat","family":"GigaChat","version":"GigaChat 2","score":2.8},{"place":23,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":1.7},{"place":24,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":0}]},{"id":"hhem-v2.1","name":"HHEM v2.1","topic":"Hallucination detection","description":"Hughes Hallucination Evaluation Model (Vectara) — lower is better.","url":"","leaderboard":"https://github.com/vectara/hallucination-leaderboard","github":"https://github.com/vectara/hallucination-leaderboard","paper":"","metric":"percent","stars":"","top_model":"AntGroup Finix_S1_32b","top_percent":0.6,"top_model_id":"antgroup-finix-s1-32b","top_generation":"Finix S1","top_model_base":"Finix S1","top_model_family":"Finix","top_company":"antgroup","top_open_source":1,"lower_is_better":true,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"antgroup-finix-s1-32b","company":"antgroup","family":"Finix","version":"Finix S1","score":0.6},{"place":2,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":0.7},{"place":3,"model":"gemini-2.0-pro-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":0.8},{"place":4,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":0.8},{"place":5,"model":"vectara-mockingbird-2-echo","company":"vectara","family":"Mockingbird","version":"Mockingbird 2 Echo","score":0.9},{"place":6,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1.1},{"place":7,"model":"gemini-2.0-flash-lite-preview","company":"google","family":"Gemini","version":"Gemini 2.0","score":1.2},{"place":8,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":1.2},{"place":9,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":1.3},{"place":10,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.2},{"place":11,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":2.9},{"place":12,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":3.2},{"place":13,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":3.3},{"place":14,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":3.5},{"place":15,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":3.6},{"place":16,"model":"deepseek-tng-r1t2-chimera","company":"tng","family":"DeepSeek-TNG","version":"DeepSeek-TNG R1T2","score":5.5},{"place":17,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.5},{"place":18,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":5.5},{"place":19,"model":"deepseek-v3-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":7.7},{"place":20,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":11.1},{"place":21,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":14.3}]},{"id":"hiddenmath","name":"HiddenMath","topic":"Math reasoning","description":"Mathematical reasoning benchmark referenced in recent model cards.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.0 Pro","top_percent":65.2,"top_model_id":"gemini-2.0-pro","top_generation":"Gemini 2.0","top_model_base":"Gemini 2.0 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":65.2},{"place":2,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":63.5},{"place":3,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":60.3},{"place":4,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":54.5},{"place":5,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":52},{"place":6,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":47.2},{"place":7,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":43},{"place":8,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":15.8},{"place":9,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":14.8},{"place":10,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":10.4},{"place":11,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":1.8}]},{"id":"hiertext-f1","name":"HierText (F1)","topic":"OCR","description":"HierText text grounding and recognition, F1 mean.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":39,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":39},{"place":2,"model":"pp-ocrv5","company":"paddlepaddle","family":"PP-OCR","version":"PP-OCRv5","score":30.5},{"place":3,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":30.5},{"place":4,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":29.4},{"place":5,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":28},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":25.7}]},{"id":"hipho","name":"HiPhO","topic":"Physics olympiad (multimodal)","description":"High-school physics olympiad problems with diagrams for evaluating multimodal physics reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":90,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":86.8},{"place":3,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":86.8},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":86.6},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.4},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":84.3},{"place":7,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":84.1},{"place":8,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":83.8},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82},{"place":10,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":81.6},{"place":11,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.4},{"place":12,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.4},{"place":13,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":78.6},{"place":14,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":15,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":76},{"place":16,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":74.8},{"place":17,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":74.1},{"place":18,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":72.9},{"place":19,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":72.5},{"place":20,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.3},{"place":21,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":65},{"place":22,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":46.4},{"place":23,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":43.3},{"place":24,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":41.1},{"place":25,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40.8},{"place":26,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.7},{"place":27,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":38.5},{"place":28,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":38.3},{"place":29,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37.7},{"place":30,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37}]},{"id":"hitab","name":"HiTab","topic":"Table QA","description":"Hierarchical table QA (MMTab subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.1","top_percent":77.8,"top_model_id":"gpt-5.1","top_generation":"GPT-5.1","top_model_base":"GPT-5.1","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":77.8},{"place":2,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":67.6},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.9},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":48.3},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":44.1},{"place":6,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":15.8}]},{"id":"hle","name":"HLE","topic":"Multi-domain reasoning","description":"Challenging LLMs at the frontier of human knowledge.","url":"https://github.com/centerforaisafety/hle","leaderboard":"https://agi.safe.ai/","github":"","paper":"","metric":"avg@3","stars":"1085","top_model":"Claude Opus 5.5","top_percent":64.4,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":258,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":64.4},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":60.9},{"place":3,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":59},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57.8},{"place":5,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":56.9},{"place":6,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":56.8},{"place":7,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.6},{"place":8,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.5},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.3},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":55.6},{"place":11,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.9},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.3},{"place":13,"model":"muse-spark-contemplating","company":"meta","family":"Muse","version":"Muse Spark","score":50.2},{"place":14,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":50},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":49.8},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":49.5},{"place":17,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":48.4},{"place":18,"model":"gemini-3.1-deep-think","company":"google","family":"Gemini","version":"Gemini 3.1","score":48.4},{"place":19,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":47.2},{"place":20,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":47.2},{"place":21,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":46.9},{"place":22,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":46.9},{"place":23,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":45.9},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.8},{"place":25,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":45.7},{"place":26,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":45.4},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":45},{"place":28,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.9},{"place":29,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":44.6},{"place":30,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":44.5},{"place":31,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":44.4},{"place":32,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":43.9},{"place":33,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":43.9},{"place":34,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":43.6},{"place":35,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":43.5},{"place":36,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":43.4},{"place":37,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":43.2},{"place":38,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":43.1},{"place":39,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":43.1},{"place":40,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":42.8},{"place":41,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":42.8},{"place":42,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":42.7},{"place":43,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":42.7},{"place":44,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":42.7},{"place":45,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":42.6},{"place":46,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":42.3},{"place":47,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":41.7},{"place":48,"model":"chatgpt-agent","company":"openai","family":"GPT","version":"ChatGPT","score":41.6},{"place":49,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":41.4},{"place":50,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":41.4},{"place":51,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":40.9},{"place":52,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.8},{"place":53,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.8},{"place":54,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":40.5},{"place":55,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":40.2},{"place":56,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40},{"place":57,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40},{"place":58,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":39.9},{"place":59,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":39.8},{"place":60,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":39.2},{"place":61,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":39.2},{"place":62,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":38.8},{"place":63,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":38.3},{"place":64,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.8},{"place":65,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":37.7},{"place":66,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.7},{"place":67,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.7},{"place":68,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":37.68},{"place":69,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.5},{"place":70,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.5},{"place":71,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.5},{"place":72,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":37.44},{"place":73,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":37.2},{"place":74,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.2},{"place":75,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":37},{"place":76,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":36.8},{"place":77,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":36.7},{"place":78,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":36.6},{"place":79,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":36.6},{"place":80,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":36.6},{"place":81,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":36.6},{"place":82,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":36.5},{"place":83,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":36.4},{"place":84,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":35.9},{"place":85,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":35.5},{"place":86,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":35.5},{"place":87,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":35.4},{"place":88,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":35.2},{"place":89,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":35.1},{"place":90,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35},{"place":91,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":34.8},{"place":92,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":34.7},{"place":93,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":34.7},{"place":94,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":34.7},{"place":95,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":34.7},{"place":96,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":34.6},{"place":97,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":34.5},{"place":98,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":34.5},{"place":99,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":34.5},{"place":100,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":34.5},{"place":101,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":34.16},{"place":102,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":34},{"place":103,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":33.8},{"place":104,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":33.7},{"place":105,"model":"kat-coder-pro-v1","company":"kuaishou","family":"KAT","version":"KAT-Coder Pro v1","score":33.4},{"place":106,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":33.2},{"place":107,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":32.9},{"place":108,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32},{"place":109,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32},{"place":110,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":31.8},{"place":111,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":31.79},{"place":112,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":31.6},{"place":113,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":31.6},{"place":114,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":31.5},{"place":115,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":31.4},{"place":116,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":31.4},{"place":117,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":31},{"place":118,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":31},{"place":119,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":30.8},{"place":120,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":30.8},{"place":121,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":30.8},{"place":122,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":30.8},{"place":123,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":30.8},{"place":124,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":30.7},{"place":125,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":30.6},{"place":126,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":30.5},{"place":127,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":30.2},{"place":128,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":30.2},{"place":129,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":30.2},{"place":130,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":30.1},{"place":131,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":30.1},{"place":132,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":30},{"place":133,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":29.9},{"place":134,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":29.4},{"place":135,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":29.32},{"place":136,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":29.2},{"place":137,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":28.8},{"place":138,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.7},{"place":139,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":28.4},{"place":140,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":28.4},{"place":141,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":28.4},{"place":142,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":28.2},{"place":143,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":28.1},{"place":144,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":28},{"place":145,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":28},{"place":146,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":27.2},{"place":147,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":27.2},{"place":148,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":27.2},{"place":149,"model":"gemini-deepresearch","company":"google","family":"Gemini","version":"Gemini DeepResearch","score":26.9},{"place":150,"model":"kimi-researcher","company":"moonshotai","family":"Kimi","version":"Kimi Researcher","score":26.9},{"place":151,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":26.9},{"place":152,"model":"openai-deepresearch","company":"openai","family":"DeepResearch","version":"DeepResearch","score":26.6},{"place":153,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":26.3},{"place":154,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":25.81},{"place":155,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":25.8},{"place":156,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":25.7},{"place":157,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":25.6},{"place":158,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":25.3},{"place":159,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":25.1},{"place":160,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":25.1},{"place":161,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":25.1},{"place":162,"model":"o3","company":"openai","family":"o3","version":"o3","score":24.9},{"place":163,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":24.8},{"place":164,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":24.8},{"place":165,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":24.5},{"place":166,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":24.5},{"place":167,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.4},{"place":168,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":24.3},{"place":169,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.3},{"place":170,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":24},{"place":171,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":23.9},{"place":172,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":23.9},{"place":173,"model":"gpt-5-codex-high","company":"openai","family":"GPT","version":"GPT-5","score":23.4},{"place":174,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":22.7},{"place":175,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.4},{"place":176,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":22.34},{"place":177,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":22.2},{"place":178,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":22.2},{"place":179,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":22.1},{"place":180,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":22},{"place":181,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":21.7},{"place":182,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.6},{"place":183,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.6},{"place":184,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":21.4},{"place":185,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":21.4},{"place":186,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":21.2},{"place":187,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":21.2},{"place":188,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.1},{"place":189,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":21.1},{"place":190,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":20.8},{"place":191,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":20.6},{"place":192,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":20.3},{"place":193,"model":"o3","company":"openai","family":"o3","version":"o3","score":20.3},{"place":194,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":20.3},{"place":195,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":20.2},{"place":196,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":20},{"place":197,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":19.93},{"place":198,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":19.9},{"place":199,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":19.8},{"place":200,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":19.7},{"place":201,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":19.5},{"place":202,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":19.4},{"place":203,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":19.11},{"place":204,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":18.58},{"place":205,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":18.5},{"place":206,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":18.5},{"place":207,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":18.4},{"place":208,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":18.4},{"place":209,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":18.3},{"place":210,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":18.3},{"place":211,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":18.3},{"place":212,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":18.1},{"place":213,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":18.07},{"place":214,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":17.9},{"place":215,"model":"mirothinker-v0.2-32b","company":"miromind","family":"MiroThinker","version":"MiroThinker v0.2","score":17.8},{"place":216,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":17.7},{"place":217,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":17.7},{"place":218,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.7},{"place":219,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.7},{"place":220,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":17.6},{"place":221,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":17.6},{"place":222,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.3},{"place":223,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":17.3},{"place":224,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.3},{"place":225,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.3},{"place":226,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":17.2},{"place":227,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":17.04},{"place":228,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":17},{"place":229,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":16.8},{"place":230,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":16.7},{"place":231,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":16.7},{"place":232,"model":"cogito-671b-v2.1","company":"deepcogito","family":"Cogito","version":"Cogito 671B v2.1","score":16.66},{"place":233,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":16},{"place":234,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":16},{"place":235,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":15.9},{"place":236,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":15.9},{"place":237,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15.7},{"place":238,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":15.5},{"place":239,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":15.2},{"place":240,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":15.15},{"place":241,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":15},{"place":242,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":15},{"place":243,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":14.9},{"place":244,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.9},{"place":245,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":14.8},{"place":246,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":14.74},{"place":247,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.7},{"place":248,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":14.6},{"place":249,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":14.4},{"place":250,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.3},{"place":251,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":14.23},{"place":252,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":14.1},{"place":253,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.7},{"place":254,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.7},{"place":255,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.7},{"place":256,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":13.3},{"place":257,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":13.3},{"place":258,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":13.1},{"place":259,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":12.92},{"place":260,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":12.5},{"place":261,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":12.5},{"place":262,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":12.3},{"place":263,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":12.3},{"place":264,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":12.26},{"place":265,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":12.2},{"place":266,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":12.1},{"place":267,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":12},{"place":268,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":12},{"place":269,"model":"openreasoning-nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":11.9},{"place":270,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":11.9},{"place":271,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":11.7},{"place":272,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":11.26},{"place":273,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":11.23},{"place":274,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":11.1},{"place":275,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":11.1},{"place":276,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":11.1},{"place":277,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":11},{"place":278,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":11},{"place":279,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":11},{"place":280,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":10.9},{"place":281,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":10.8},{"place":282,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":10.75},{"place":283,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":10.7},{"place":284,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":10.63},{"place":285,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":10.6},{"place":286,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":10.6},{"place":287,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":10.5},{"place":288,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":10.5},{"place":289,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":10.47},{"place":290,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":10.2},{"place":291,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":10.2},{"place":292,"model":"openreasoning-nemotron-14b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":10.1},{"place":293,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":10.06},{"place":294,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":10},{"place":295,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":9.98},{"place":296,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":9.95},{"place":297,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.9},{"place":298,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":9.8},{"place":299,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":9.8},{"place":300,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":9.8},{"place":301,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":9.8},{"place":302,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":9.8},{"place":303,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":9.7},{"place":304,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":9.6},{"place":305,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":9.6},{"place":306,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":9.37},{"place":307,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":9.3},{"place":308,"model":"nova-pro","company":"amazon","family":"Nova","version":"Nova","score":8.9},{"place":309,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":8.9},{"place":310,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.7},{"place":311,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":8.6},{"place":312,"model":"nova-lite","company":"amazon","family":"Nova","version":"Nova","score":8.6},{"place":313,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.6},{"place":314,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.57},{"place":315,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":8.5},{"place":316,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":8.5},{"place":317,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":8.4},{"place":318,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":8.4},{"place":319,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":8.3},{"place":320,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":8.3},{"place":321,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":8.2},{"place":322,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":8.2},{"place":323,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":8.2},{"place":324,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":8.1},{"place":325,"model":"o1","company":"openai","family":"o1","version":"o1","score":8},{"place":326,"model":"midm-k-2.5-pro","company":"kt","family":"Mi:dm","version":"Mi:dm K 2.5","score":7.7},{"place":327,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":7.7},{"place":328,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":7.69},{"place":329,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":7.6},{"place":330,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":7.4},{"place":331,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":7.3},{"place":332,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":7.23},{"place":333,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":7.2},{"place":334,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":7.1},{"place":335,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":7.09},{"place":336,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":6.9},{"place":337,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":6.9},{"place":338,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":6.85},{"place":339,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":6.8},{"place":340,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":6.8},{"place":341,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":6.7},{"place":342,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":6.6},{"place":343,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":6.5},{"place":344,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":6.3},{"place":345,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":6.3},{"place":346,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":6.3},{"place":347,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":6.2},{"place":348,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":6.14},{"place":349,"model":"littlelamb-0.3b","company":"multiverse","family":"LittleLamb","version":"LittleLamb","score":6.12},{"place":350,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":6.1},{"place":351,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":6},{"place":352,"model":"jamba-reasoning-3b","company":"ai21","family":"Jamba","version":"Jamba Reasoning","score":6},{"place":353,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":5.9},{"place":354,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":5.9},{"place":355,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":5.9},{"place":356,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":5.8},{"place":357,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.7},{"place":358,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":5.65},{"place":359,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.65},{"place":360,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":5.61},{"place":361,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":5.6},{"place":362,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":5.6},{"place":363,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":5.52},{"place":364,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":5.5},{"place":365,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":5.5},{"place":366,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":5.4},{"place":367,"model":"littlelamb-0.3b","company":"multiverse","family":"LittleLamb","version":"LittleLamb","score":5.37},{"place":368,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":5.2},{"place":369,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":5.2},{"place":370,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":5.2},{"place":371,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":5.2},{"place":372,"model":"ernie-4.5-21b-a3b-pt","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":5.1},{"place":373,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":5.1},{"place":374,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.1},{"place":375,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":4.9},{"place":376,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.8},{"place":377,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":4.8},{"place":378,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.8},{"place":379,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":4.7},{"place":380,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":4.6},{"place":381,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":4.59},{"place":382,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.54},{"place":383,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.4},{"place":384,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":4.4},{"place":385,"model":"phi-4-mini","company":"microsoft","family":"Phi","version":"Phi 4","score":4.2},{"place":386,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.2},{"place":387,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":4.1},{"place":388,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":4.1},{"place":389,"model":"qwen3-8b-nothinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":4},{"place":390,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":4},{"place":391,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.9},{"place":392,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.8},{"place":393,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":3.7},{"place":394,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":3.3},{"place":395,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":3.3},{"place":396,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":2.7},{"place":397,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.6},{"place":398,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":2.5},{"place":399,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.1}]},{"id":"hle-diamond","name":"HLE-Diamond","topic":"Multidisciplinary reasoning","description":"Hard 'Diamond' subset of Humanity's Last Exam, evaluated without tools.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Spark Open","top_percent":26.1,"top_model_id":"muse-spark-open","top_generation":"Muse Spark Open","top_model_base":"Muse Spark Open","top_model_family":"Muse","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":26.1},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":22.2},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":17.3},{"place":4,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":16.4},{"place":5,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":11.2},{"place":6,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":8.9}]},{"id":"hle-multichoice","name":"HLE-MultiChoice","topic":"Advanced reasoning","description":"The 513 text-only original multiple-choice questions of Humanity's Last Exam, posed as one choice among the lettered answers.","url":"https://artificialanalysis.ai/evaluations/hle-multichoice","leaderboard":"https://artificialanalysis.ai/evaluations/hle-multichoice","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5 (max)","top_percent":70.2,"top_model_id":"claude-opus-5.5-max","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":58,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":70.2},{"place":2,"model":"claude-opus-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":59.8},{"place":3,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":58.9},{"place":4,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":55.4},{"place":5,"model":"claude-haiku-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":37.4},{"place":6,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":35.3},{"place":7,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":32.4},{"place":8,"model":"claude-haiku-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":30.2},{"place":9,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":29},{"place":10,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":26.7},{"place":11,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25.7},{"place":12,"model":"claude-haiku-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":23.6},{"place":13,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":23.2},{"place":14,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":22.2},{"place":15,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":20.9},{"place":16,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":18.9},{"place":17,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":16.8},{"place":18,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":16.8},{"place":19,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":16},{"place":20,"model":"pplx-decider-v1.1-27b","company":"perplexity","family":"pplx-decider","version":"v1.1","score":15.4},{"place":21,"model":"d1-ultra","company":"liquidai","family":"d1","version":"d1","score":15},{"place":22,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":14.9},{"place":23,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":14.8},{"place":24,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":14.4},{"place":25,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":14.2},{"place":26,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":14},{"place":27,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":14},{"place":28,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":14},{"place":29,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":13.6},{"place":30,"model":"celeris-1-decision","company":"celeris","family":"Celeris","version":"Celeris-1","score":13.3},{"place":31,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":12.8},{"place":32,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":12.8},{"place":33,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":12.6},{"place":34,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":12.6},{"place":35,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":12.3},{"place":36,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":12},{"place":37,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":12},{"place":38,"model":"gpt-6-luna-decisions","company":"openai","family":"GPT","version":"GPT-6","score":11.7},{"place":39,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":11.7},{"place":40,"model":"d1","company":"liquidai","family":"d1","version":"d1","score":11.5},{"place":41,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":11.4},{"place":42,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":11.4},{"place":43,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":11.4},{"place":44,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":11.1},{"place":45,"model":"microsoft-decision-1","company":"microsoft","family":"Microsoft-Decision","version":"Microsoft-Decision-1","score":10.9},{"place":46,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":10.8},{"place":47,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":10.8},{"place":48,"model":"glide","company":"fastino","family":"GLiDE","version":"GLiDE","score":10.5},{"place":49,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":10.3},{"place":50,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":10.2},{"place":51,"model":"mercury-decide","company":"inception","family":"Mercury","version":"Mercury Decide","score":10.1},{"place":52,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":9.4},{"place":53,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":9},{"place":54,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":8.6},{"place":55,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":8.6},{"place":56,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":7.6},{"place":57,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":7},{"place":58,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":7}]},{"id":"hle-overconfidence","name":"HLE Overconfidence","topic":"Overconfidence / safety","description":"Overconfidence rate derived from Humanity's Last Exam evaluations.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2","top_percent":43.7,"top_model_id":"gpt-5.2","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":43.7},{"place":2,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":47.8},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":55.1},{"place":4,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":56.4},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.9},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":57.2},{"place":7,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":58.8},{"place":8,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60.5},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.1},{"place":10,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":65},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72},{"place":12,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":72.1},{"place":13,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":80},{"place":14,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":80},{"place":15,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.4}]},{"id":"hle-text-only","name":"HLE (Text Only)","topic":"Advanced reasoning","description":"Humanity's Last Exam benchmark restricted to text-only inputs.","url":"https://github.com/centerforaisafety/hle","leaderboard":"https://agi.safe.ai/","github":"","paper":"","metric":"percent","stars":"1085","top_model":"Claude Fable 5","top_percent":53.3,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":206,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.3},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":49.8},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":47.2},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":46.9},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":46.9},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.8},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":45},{"place":8,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.9},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":44.7},{"place":10,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":44},{"place":11,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":43.6},{"place":12,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":43.4},{"place":13,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":42.7},{"place":14,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":42.3},{"place":15,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":42},{"place":16,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":41.7},{"place":17,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":41.7},{"place":18,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":41.4},{"place":19,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":41.3},{"place":20,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":41.1},{"place":21,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":41},{"place":22,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":40.9},{"place":23,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":40.5},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":40.3},{"place":25,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":40.1},{"place":26,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40},{"place":27,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":39.9},{"place":28,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":39.6},{"place":29,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":39.5},{"place":30,"model":"iquest-q1","company":"iquest","family":"IQuest","version":"IQuest Q1","score":39.2},{"place":31,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":39.1},{"place":32,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":39},{"place":33,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.6},{"place":34,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":38.5},{"place":35,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.8},{"place":36,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.7},{"place":37,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.7},{"place":38,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.5},{"place":39,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":37.5},{"place":40,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.5},{"place":41,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":37},{"place":42,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":37},{"place":43,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":36.6},{"place":44,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":36.47},{"place":45,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":36.4},{"place":46,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":36.2},{"place":47,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":36},{"place":48,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":35.9},{"place":49,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35.9},{"place":50,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":35.9},{"place":51,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35.8},{"place":52,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":35.6},{"place":53,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":35.6},{"place":54,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":34.8},{"place":55,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":34.8},{"place":56,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":34.5},{"place":57,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":34.4},{"place":58,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":33.9},{"place":59,"model":"mirothinker-v1.0-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker-v1.0","score":33.4},{"place":60,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":33.3},{"place":61,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":33.3},{"place":62,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":33.2},{"place":63,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":32.4},{"place":64,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":32.3},{"place":65,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":32.2},{"place":66,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":32.1},{"place":67,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32},{"place":68,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32},{"place":69,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32},{"place":70,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":32},{"place":71,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":31.9},{"place":72,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":31.79},{"place":73,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":31.7},{"place":74,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":31.6},{"place":75,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":31.5},{"place":76,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":31},{"place":77,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":30.8},{"place":78,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":30.5},{"place":79,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":30.1},{"place":80,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":30},{"place":81,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":29.9},{"place":82,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":29.7},{"place":83,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":29.4},{"place":84,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":29.2},{"place":85,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":28.8},{"place":86,"model":"nemotron-3.5-bolt-74b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":28.73},{"place":87,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.7},{"place":88,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":28.59},{"place":89,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.5},{"place":90,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":28.4},{"place":91,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":28.2},{"place":92,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":28.2},{"place":93,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":28.1},{"place":94,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":28},{"place":95,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":27.94},{"place":96,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":27.8},{"place":97,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.3},{"place":98,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":27.2},{"place":99,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":27.1},{"place":100,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":26.9},{"place":101,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":26.7},{"place":102,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":26.6},{"place":103,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":26.5},{"place":104,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":26.32},{"place":105,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":26.3},{"place":106,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":26},{"place":107,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":25.8},{"place":108,"model":"solar-mini-4","company":"upstage","family":"Solar","version":"Solar Mini 4","score":25.8},{"place":109,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":25.7},{"place":110,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":25.35},{"place":111,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.3},{"place":112,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":25.2},{"place":113,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":25.2},{"place":114,"model":"k2-horizon-32b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":25.2},{"place":115,"model":"k2-horizon-mova-36b-a4b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":25.2},{"place":116,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":25.16},{"place":117,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":25.1},{"place":118,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":24.51},{"place":119,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":24.4},{"place":120,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.3},{"place":121,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":24.3},{"place":122,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.2},{"place":123,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":24.1},{"place":124,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":23.9},{"place":125,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":23.7},{"place":126,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":23.6},{"place":127,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":23.1},{"place":128,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":23.1},{"place":129,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":23.04},{"place":130,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.4},{"place":131,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":22.2},{"place":132,"model":"re-trac-4b","company":"microsoft","family":"RE-TRAC","version":"RE-TRAC","score":22.2},{"place":133,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":22.1},{"place":134,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":22.06},{"place":135,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":22},{"place":136,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":21.94},{"place":137,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":21.7},{"place":138,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.6},{"place":139,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":21.5},{"place":140,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":21.5},{"place":141,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":21.42},{"place":142,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":21.1},{"place":143,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":20.8},{"place":144,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":20.6},{"place":145,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":20.57},{"place":146,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.4},{"place":147,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":20.3},{"place":148,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":20.3},{"place":149,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":20.3},{"place":150,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":19.87},{"place":151,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":19.8},{"place":152,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":19.78},{"place":153,"model":"gpt-5-mini-2025-08","company":"openai","family":"GPT","version":"GPT-5","score":19.74},{"place":154,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":19.56},{"place":155,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":19.5},{"place":156,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":19.41},{"place":157,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":19.4},{"place":158,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":19.4},{"place":159,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":19.3},{"place":160,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":19.2},{"place":161,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":19.2},{"place":162,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":19.18},{"place":163,"model":"o4-mini-2025-04-16-high","company":"openai","family":"o4","version":"o4","score":18.9},{"place":164,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":18.5},{"place":165,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":18.38},{"place":166,"model":"gemini-2.5-pro-preview-05-06","company":"google","family":"Gemini","version":"Gemini 2.5","score":18.38},{"place":167,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":18.3},{"place":168,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":18.3},{"place":169,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":18.26},{"place":170,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":18.2},{"place":171,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":18.2},{"place":172,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":18},{"place":173,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":17.8},{"place":174,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":17.8},{"place":175,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":17.79},{"place":176,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.7},{"place":177,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":17.7},{"place":178,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":17.6},{"place":179,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":17.5},{"place":180,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":17.5},{"place":181,"model":"g9v3-39a5b","company":"ai9stars","family":"G9","version":"G9v3","score":17.5},{"place":182,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":17.42},{"place":183,"model":"webexplorer-8b","company":"hkust","family":"WebExplorer","version":"WebExplorer","score":17.3},{"place":184,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":17.2},{"place":185,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":16.5},{"place":186,"model":"pacore-8b","company":"stepfun","family":"Step","version":"PaCoRe","score":16.2},{"place":187,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15.7},{"place":188,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":15.48},{"place":189,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":15.43},{"place":190,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15.43},{"place":191,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":15.4},{"place":192,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":14.9},{"place":193,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":14.9},{"place":194,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.9},{"place":195,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":14.8},{"place":196,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":14.53},{"place":197,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":14.5},{"place":198,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":14.09},{"place":199,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":14.04},{"place":200,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":14},{"place":201,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":13.76},{"place":202,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.7},{"place":203,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":13.6},{"place":204,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":13.37},{"place":205,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":13.3},{"place":206,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":12.92},{"place":207,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":12.88},{"place":208,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":12.8},{"place":209,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":12.6},{"place":210,"model":"gemini-2.5-flash-04-17","company":"google","family":"Gemini","version":"Gemini 2.5","score":12.58},{"place":211,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12.5},{"place":212,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":12.1},{"place":213,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":11.77},{"place":214,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.75},{"place":215,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":11.72},{"place":216,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":11.6},{"place":217,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":11.5},{"place":218,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":11.4},{"place":219,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":11.33},{"place":220,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":11.31},{"place":221,"model":"claude-opus-4-1-20250805-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":11.26},{"place":222,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":11.2},{"place":223,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":10.98},{"place":224,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":10.89},{"place":225,"model":"nemotron-labs-dory1.0-4b","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":10.89},{"place":226,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":10.8},{"place":227,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":10.72},{"place":228,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":10.6},{"place":229,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":10.6},{"place":230,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":10.47},{"place":231,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":10.47},{"place":232,"model":"nemotron-labs-dory1.0-4b-4loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":10.43},{"place":233,"model":"o3-mini-2025-01-31-med","company":"openai","family":"o3","version":"o3","score":10.31},{"place":234,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.9},{"place":235,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":9.73},{"place":236,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":9.7},{"place":237,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":9.7},{"place":238,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":9.7},{"place":239,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":9.64},{"place":240,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":9.5},{"place":241,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":9.5},{"place":242,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":9.41},{"place":243,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":9.4},{"place":244,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.31},{"place":245,"model":"rlvr-8b-0926","company":"stepfun","family":"Step","version":"PaCoRe","score":9.3},{"place":246,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":9},{"place":247,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.7},{"place":248,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":8.7},{"place":249,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":8.62},{"place":250,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":8.54},{"place":251,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":8.5},{"place":252,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":8.3},{"place":253,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":8.26},{"place":254,"model":"nemotron-labs-dory1.0-4b-1loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":8.25},{"place":255,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":7.89},{"place":256,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":7.75},{"place":257,"model":"o1-pro","company":"openai","family":"o1","version":"o1","score":7.71},{"place":258,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":7.65},{"place":259,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":7.6},{"place":260,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":7.37},{"place":261,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":7},{"place":262,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":6.92},{"place":263,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.8},{"place":264,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":6.72},{"place":265,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":6.6},{"place":266,"model":"gemini-2.0-flash-thinking-01-21","company":"google","family":"Gemini","version":"Gemini 2.0","score":6.55},{"place":267,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":6.26},{"place":268,"model":"gpt-4.5-preview","company":"openai","family":"GPT","version":"GPT-4.5","score":5.8},{"place":269,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":5.42},{"place":270,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":5.34},{"place":271,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.28},{"place":272,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":5.2},{"place":273,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":4.97},{"place":274,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":4.9},{"place":275,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":4.68},{"place":276,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":4.55},{"place":277,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":4.55},{"place":278,"model":"g9v3-3b","company":"ai9stars","family":"G9","version":"G9v3","score":4.5},{"place":279,"model":"nova-micro","company":"amazon","family":"Nova","version":"Nova","score":4.41},{"place":280,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":4.36},{"place":281,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":4.32},{"place":282,"model":"nova-pro","company":"amazon","family":"Nova","version":"Nova","score":4.32},{"place":283,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4},{"place":284,"model":"nova-lite","company":"amazon","family":"Nova","version":"Nova","score":3.76},{"place":285,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":2.32}]},{"id":"hle-verified","name":"HLE-Verified","topic":"Multi-domain reasoning","description":"Verified and revised version of Humanity's Last Exam (HLE) with component-wise verification protocol.","url":"https://huggingface.co/datasets/skylenage/HLE-Verified","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.8 Flash","top_percent":54.9,"top_model_id":"gemini-3.8-flash","top_generation":"Gemini 3.8","top_model_base":"Gemini 3.8 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":54.9},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":54.5},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.4},{"place":4,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":53.6},{"place":5,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":51.2},{"place":6,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":51.1},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":50.4},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":48.2},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":48},{"place":10,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":46.9},{"place":11,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":43.3},{"place":12,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":42.9},{"place":13,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":42.4},{"place":14,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.8},{"place":15,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.6},{"place":16,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.6},{"place":17,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":31}]},{"id":"hle-vl","name":"HLE-VL","topic":"Holistic language evaluation (vision-language)","description":"Vision-language HLE benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":36,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":36},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":31.5},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":19}]},{"id":"hle-with-tools","name":"HLE (With Tools)","topic":"Tool-augmented reasoning","description":"Humanity's Last Exam benchmark evaluated with tool access.","url":"https://github.com/centerforaisafety/hle","leaderboard":"https://agi.safe.ai/","github":"","paper":"","metric":"avg@3","stars":"1085","top_model":"Kimi-K3.1 Pro","top_percent":70,"top_model_id":"kimi-k3.1-pro","top_generation":"Kimi K3.1","top_model_base":"Kimi K3.1 Pro","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":0,"lower_is_better":false,"bench_models":153,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":70},{"place":2,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":67.7},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":65.6},{"place":4,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":65},{"place":5,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":64.7},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":64.7},{"place":7,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":64.5},{"place":8,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":64.5},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.5},{"place":10,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":64.5},{"place":11,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.9},{"place":12,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":63.9},{"place":13,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.8},{"place":14,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.6},{"place":15,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63},{"place":16,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":62.5},{"place":17,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":62.1},{"place":18,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":61},{"place":19,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":60.9},{"place":20,"model":"apodex-h1","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":60.8},{"place":21,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":60.2},{"place":22,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":60},{"place":23,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":59.8},{"place":24,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":58.8},{"place":25,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":58.7},{"place":26,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":58.7},{"place":27,"model":"muse-spark-contemplating","company":"meta","family":"Muse","version":"Muse Spark","score":58.4},{"place":28,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":58},{"place":29,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":57.9},{"place":30,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57.4},{"place":31,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":57.4},{"place":32,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":57.2},{"place":33,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":57.2},{"place":34,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":57},{"place":35,"model":"iris-pro","company":"allspark","family":"Iris","version":"Iris","score":56.4},{"place":36,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":56.2},{"place":37,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":56.1},{"place":38,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":56.1},{"place":39,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":56},{"place":40,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":55.7},{"place":41,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":55.5},{"place":42,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":55.4},{"place":43,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":55.3},{"place":44,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.1},{"place":45,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":55.1},{"place":46,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":55},{"place":47,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.9},{"place":48,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":54.7},{"place":49,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":54.7},{"place":50,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":54.6},{"place":51,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":54.2},{"place":52,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":54},{"place":53,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":54},{"place":54,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":53.5},{"place":55,"model":"gemini-3.1-deep-think","company":"google","family":"Gemini","version":"Gemini 3.1","score":53.4},{"place":56,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53.3},{"place":57,"model":"xyz-aquila-pro","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":53.3},{"place":58,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":53.2},{"place":59,"model":"apodex-1.1","company":"apodex","family":"Apodex","version":"Apodex 1.1","score":53.2},{"place":60,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53.1},{"place":61,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53.1},{"place":62,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53},{"place":63,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":52.6},{"place":64,"model":"arex-2","company":"baai","family":"AREX","version":"AREX-2","score":52.6},{"place":65,"model":"arex-base","company":"baai","family":"AREX","version":"AREX","score":52.4},{"place":66,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":52.3},{"place":67,"model":"iris-mini","company":"allspark","family":"Iris","version":"Iris","score":52.3},{"place":68,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":52.2},{"place":69,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":52.1},{"place":70,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":52},{"place":71,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":51.9},{"place":72,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":51.8},{"place":73,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":51.6},{"place":74,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.5},{"place":75,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":51.4},{"place":76,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":51.2},{"place":77,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":51.1},{"place":78,"model":"xyz-aquila-mini","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":51.1},{"place":79,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.8},{"place":80,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":50.6},{"place":81,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":50.4},{"place":82,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":50.4},{"place":83,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":50.4},{"place":84,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":50.3},{"place":85,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":50.2},{"place":86,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":50.2},{"place":87,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":50.2},{"place":88,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.1},{"place":89,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":50},{"place":90,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":50},{"place":91,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":50},{"place":92,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":50},{"place":93,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":49.8},{"place":94,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":49.8},{"place":95,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":49},{"place":96,"model":"apodex-1.0","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":49},{"place":97,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":48.9},{"place":98,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.5},{"place":99,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.3},{"place":100,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":48.2},{"place":101,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":48.2},{"place":102,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":48},{"place":103,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":48},{"place":104,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":47.8},{"place":105,"model":"mirothinker-h1","company":"miromind","family":"MiroThinker","version":"MiroThinker H1","score":47.7},{"place":106,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":47.6},{"place":107,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.5},{"place":108,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":47.5},{"place":109,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.4},{"place":110,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":47.2},{"place":111,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":46.9},{"place":112,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":46.8},{"place":113,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":46.8},{"place":114,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":46.3},{"place":115,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":46},{"place":116,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.8},{"place":117,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.8},{"place":118,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.8},{"place":119,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":45.5},{"place":120,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":45.5},{"place":121,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":45.5},{"place":122,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":45.3},{"place":123,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":45.1},{"place":124,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":45.1},{"place":125,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.9},{"place":126,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.7},{"place":127,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.4},{"place":128,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.4},{"place":129,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.2},{"place":130,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.2},{"place":131,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":42.9},{"place":132,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":42.8},{"place":133,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":42.7},{"place":134,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":42.5},{"place":135,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":41.5},{"place":136,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":40.9},{"place":137,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.8},{"place":138,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.8},{"place":139,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.8},{"place":140,"model":"arex-turbo","company":"baai","family":"AREX","version":"AREX","score":40.6},{"place":141,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40.3},{"place":142,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":40.3},{"place":143,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":40.2},{"place":144,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":40},{"place":145,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":40},{"place":146,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":39.2},{"place":147,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":38.4},{"place":148,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":38},{"place":149,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":37.7},{"place":150,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":37.7},{"place":151,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":37.4},{"place":152,"model":"quest-35b","company":"osunlp","family":"QUEST","version":"QUEST","score":37.2},{"place":153,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":37.1},{"place":154,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":36.9},{"place":155,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":36.4},{"place":156,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":36.2},{"place":157,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":35.8},{"place":158,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":35.7},{"place":159,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":35.4},{"place":160,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":35.2},{"place":161,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":35.2},{"place":162,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33.6},{"place":163,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33.6},{"place":164,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":33.4},{"place":165,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":33.2},{"place":166,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":32.9},{"place":167,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":32.8},{"place":168,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32},{"place":169,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":32},{"place":170,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":31.8},{"place":171,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":31.6},{"place":172,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":31.3},{"place":173,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":31},{"place":174,"model":"websailor-v2-30b-a3b","company":"tongyi","family":"WebSailor","version":"WebSailor-V2","score":30.6},{"place":175,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":30.5},{"place":176,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":30.4},{"place":177,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":30.1},{"place":178,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":28.9},{"place":179,"model":"iterresearch-30b-a3b","company":"tongyi","family":"IterResearch","version":"IterResearch","score":28.8},{"place":180,"model":"kimi-researcher","company":"moonshotai","family":"Kimi","version":"Kimi Researcher","score":26.9},{"place":181,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.5},{"place":182,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":26.4},{"place":183,"model":"toolmind-web-3b","company":"boss","family":"Nanbeige","version":"ToolMind-Web","score":24.8},{"place":184,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":24.5},{"place":185,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.5},{"place":186,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":23.1},{"place":187,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":22.82},{"place":188,"model":"marco-deepresearch-8b","company":"alibaba","family":"Marco","version":"Marco DeepResearch","score":22.5},{"place":189,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":21.8},{"place":190,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":21.5},{"place":191,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.2},{"place":192,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":19.1},{"place":193,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":19.1},{"place":194,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":19},{"place":195,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":19},{"place":196,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":18.7},{"place":197,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":17.9},{"place":198,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.8},{"place":199,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":17.2},{"place":200,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":11.9},{"place":201,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":10.1}]},{"id":"hmmt","name":"HMMT","topic":"Math (competition)","description":"Harvard–MIT Mathematics Tournament problems.","url":"https://hmmt.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 pro","top_percent":100,"top_model_id":"gpt-5-pro","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":100},{"place":2,"model":"o3","company":"openai","family":"o3","version":"o3","score":93.3}]},{"id":"hmmt-2025","name":"HMMT 2025","topic":"Math (competition)","description":"Harvard–MIT Mathematics Tournament 2025 problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":99.8,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":103,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":99.8},{"place":2,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":99.6},{"place":3,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":99.2},{"place":4,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.6},{"place":5,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":98.1},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":97.5},{"place":7,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":97.5},{"place":8,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":95.1},{"place":9,"model":"pacore-8b","company":"stepfun","family":"Step","version":"PaCoRe","score":94.5},{"place":10,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":94.4},{"place":11,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.5},{"place":12,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":93.5},{"place":13,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":93.4},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.33},{"place":15,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":93.3},{"place":16,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":93.3},{"place":17,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":93.3},{"place":18,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.3},{"place":19,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":93.3},{"place":20,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":93.2},{"place":21,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":92.5},{"place":22,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":92.14},{"place":23,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":91.79},{"place":24,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":90.8},{"place":25,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.2},{"place":26,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":90},{"place":27,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":89.7},{"place":28,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.4},{"place":29,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":89.2},{"place":30,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.2},{"place":31,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":88.7},{"place":32,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":88.3},{"place":33,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.7},{"place":34,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":86.67},{"place":35,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":86.5},{"place":36,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":86.1},{"place":37,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":86.1},{"place":38,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":84.79},{"place":39,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":84.53},{"place":40,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.2},{"place":41,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.9},{"place":42,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.9},{"place":43,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.6},{"place":44,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.6},{"place":45,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":83.54},{"place":46,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.5},{"place":47,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.3},{"place":48,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":81.88},{"place":49,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":81.7},{"place":50,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.2},{"place":51,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":80.8},{"place":52,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":79.58},{"place":53,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.2},{"place":54,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":78.18},{"place":55,"model":"rlvr-8b-0926","company":"stepfun","family":"Step","version":"PaCoRe","score":75.4},{"place":56,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74.6},{"place":57,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.18},{"place":58,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":73.9},{"place":59,"model":"openreasoning-nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":73.8},{"place":60,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":73.3},{"place":61,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.4},{"place":62,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.4},{"place":63,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":71.4},{"place":64,"model":"openreasoning-nemotron-14b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":71.2},{"place":65,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":69.38},{"place":66,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.71},{"place":67,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.6},{"place":68,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":67.29},{"place":69,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.7},{"place":70,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":66.46},{"place":71,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.68},{"place":72,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":64.9},{"place":73,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":64.8},{"place":74,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.2},{"place":75,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":63.5},{"place":76,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":63.5},{"place":77,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":61},{"place":78,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":57.29},{"place":79,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":54.3},{"place":80,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":54.1},{"place":81,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":53},{"place":82,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":51.5},{"place":83,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":51.46},{"place":84,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":51.3},{"place":85,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":50.83},{"place":86,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":50.6},{"place":87,"model":"vibethinker-1.5b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":50.4},{"place":88,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.4},{"place":89,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.8},{"place":90,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":47.7},{"place":91,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":47.08},{"place":92,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":45.6},{"place":93,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":44.5},{"place":94,"model":"phi-4-reasoning","company":"microsoft","family":"Phi","version":"Phi 4","score":43.8},{"place":95,"model":"magistral-small-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":43.5},{"place":96,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.3},{"place":97,"model":"acereason-nemotron-1.1","company":"nvidia","family":"AceReason","version":"1.1","score":42.9},{"place":98,"model":"deepseek-r1-0120","company":"deepseek","family":"DeepSeek","version":"0120","score":41.7},{"place":99,"model":"questa-nemotron-1.5b","company":"amazon","family":"Nemotron","version":"QuestA Nemotron","score":41.67},{"place":100,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":41},{"place":101,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":38.8},{"place":102,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":38.8},{"place":103,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":38.3},{"place":104,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":35.8},{"place":105,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":34.7},{"place":106,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":34.2},{"place":107,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":34},{"place":108,"model":"deepseek-r1-distill-32b","company":"deepseek","family":"DeepSeek-R1","version":"32B","score":33},{"place":109,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":32.5},{"place":110,"model":"skywork-or1-7b","company":"skywork","family":"Skywork OR1","version":"Skywork OR1","score":32},{"place":111,"model":"nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":31.56},{"place":112,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":31.5},{"place":113,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":31},{"place":114,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.7},{"place":115,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":29.8},{"place":116,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":27.5},{"place":117,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":27.3},{"place":118,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":26},{"place":119,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":22.19},{"place":120,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.8},{"place":121,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":19.4},{"place":122,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":19},{"place":123,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":15.9},{"place":124,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":15.9},{"place":125,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.9},{"place":126,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":11.8},{"place":127,"model":"qwen3-8b-nothinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":11.5},{"place":128,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":9.8},{"place":129,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.79},{"place":130,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":7},{"place":131,"model":"ernie-4.5-21b-a3b-pt","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":6.9}]},{"id":"hmmt-feb-2025","name":"HMMT Feb 2025","topic":"Math (competition)","description":"Harvard–MIT Mathematics Tournament February 2025 problems.","url":"https://hmmt.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2 (high)","top_percent":100,"top_model_id":"gpt-5.2-high","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":96,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":2,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":100},{"place":3,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":99.4},{"place":4,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":99.4},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":99.4},{"place":6,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":98.4},{"place":7,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":98},{"place":8,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":97.9},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":97.5},{"place":10,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":97.5},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":97.3},{"place":12,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":97.3},{"place":13,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":97.1},{"place":14,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":96.7},{"place":15,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":96.3},{"place":16,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":95.4},{"place":17,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":95.4},{"place":18,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94.8},{"place":19,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":94.6},{"place":20,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":94.2},{"place":21,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":93.8},{"place":22,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":93.7},{"place":23,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":93.67},{"place":24,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":93.4},{"place":25,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":93.3},{"place":26,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.9},{"place":27,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.9},{"place":28,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":92.5},{"place":29,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":92.5},{"place":30,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92},{"place":31,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":91.7},{"place":32,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":91.5},{"place":33,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.4},{"place":34,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90.7},{"place":35,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.2},{"place":36,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":90},{"place":37,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":90},{"place":38,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":90},{"place":39,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":90},{"place":40,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.4},{"place":41,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":89.3},{"place":42,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":89.2},{"place":43,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":89.2},{"place":44,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":89.17},{"place":45,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89},{"place":46,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.7},{"place":47,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":88.3},{"place":48,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":87.7},{"place":49,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":87.5},{"place":50,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":85.8},{"place":51,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.1},{"place":52,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85},{"place":53,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":85},{"place":54,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.6},{"place":55,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":84.4},{"place":56,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":84.2},{"place":57,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.9},{"place":58,"model":"longcat-flash-thinking","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":83.7},{"place":59,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.2},{"place":60,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.5},{"place":61,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":80},{"place":62,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":79.4},{"place":63,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.2},{"place":64,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":78.33},{"place":65,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":78.18},{"place":66,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":77.5},{"place":67,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":76.7},{"place":68,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":76.7},{"place":69,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":75.6},{"place":70,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":74.8},{"place":71,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74},{"place":72,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":73.9},{"place":73,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.8},{"place":74,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":73.7},{"place":75,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":73.3},{"place":76,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":73.3},{"place":77,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.4},{"place":78,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":71},{"place":79,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":70.42},{"place":80,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":70},{"place":81,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":69.2},{"place":82,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":67.1},{"place":83,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":67.1},{"place":84,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":66.7},{"place":85,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":66.67},{"place":86,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.2},{"place":87,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":63.5},{"place":88,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":63.3},{"place":89,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":63.3},{"place":90,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":63.1},{"place":91,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":62.9},{"place":92,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":61.5},{"place":93,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.5},{"place":94,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":55.5},{"place":95,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":52.5},{"place":96,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":51.7},{"place":97,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":50.3},{"place":98,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":48.5},{"place":99,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":45.4},{"place":100,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.89},{"place":101,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.8},{"place":102,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":43.33},{"place":103,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":35.2},{"place":104,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":34},{"place":105,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.7},{"place":106,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":26},{"place":107,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.9},{"place":108,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":10.2}]},{"id":"hmmt-feb-2026","name":"HMMT Feb 2026","topic":"Math (competition)","description":"Harvard–MIT Mathematics Tournament February 2026 problems.","url":"https://hmmt.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Darwin-180B-RSI","top_percent":100,"top_model_id":"darwin-180b-rsi","top_generation":"Darwin","top_model_base":"Darwin 180B RSI","top_model_family":"Darwin","top_company":"finalbench","top_open_source":1,"lower_is_better":false,"bench_models":120,"total_models":3854,"placements":[{"place":1,"model":"darwin-180b-rsi","company":"finalbench","family":"Darwin","version":"Darwin","score":100},{"place":2,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":98.5},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":97.7},{"place":4,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":97.1},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":97.06},{"place":6,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":96.97},{"place":7,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":96.7},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":96.7},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":96.2},{"place":10,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":95.8},{"place":11,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":95.64},{"place":12,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":95.36},{"place":13,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95.2},{"place":14,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95.2},{"place":15,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.8},{"place":16,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.8},{"place":17,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":94.7},{"place":18,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.7},{"place":19,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":94.08},{"place":20,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94},{"place":21,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.9},{"place":22,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":93.9},{"place":23,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":93.56},{"place":24,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":93.5},{"place":25,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":93.47},{"place":26,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":92.9},{"place":27,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":92.7},{"place":28,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":92.7},{"place":29,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":92.5},{"place":30,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.9},{"place":31,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":91.8},{"place":32,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.76},{"place":33,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":91.57},{"place":34,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":90.34},{"place":35,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":90.2},{"place":36,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":89.4},{"place":37,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.9},{"place":38,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":87.9},{"place":39,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.88},{"place":40,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.8},{"place":41,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":87.31},{"place":42,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.3},{"place":43,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.1},{"place":44,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.1},{"place":45,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":87},{"place":46,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":86.4},{"place":47,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":86.4},{"place":48,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.36},{"place":49,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":86.36},{"place":50,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":86.36},{"place":51,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":86.3},{"place":52,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":86.2},{"place":53,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":85.8},{"place":54,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":85.6},{"place":55,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":85.51},{"place":56,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.3},{"place":57,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.9},{"place":58,"model":"mai-thinking-1","company":"microsoft","family":"MAI","version":"MAI-Thinking-1","score":84.9},{"place":59,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.6},{"place":60,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.5},{"place":61,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":84.4},{"place":62,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84.3},{"place":63,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.3},{"place":64,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.3},{"place":65,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":84.1},{"place":66,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":83.9},{"place":67,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.6},{"place":68,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":83.38},{"place":69,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.24},{"place":70,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":82.8},{"place":71,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":82.8},{"place":72,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":82.6},{"place":73,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":82.6},{"place":74,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":81.3},{"place":75,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":81.3},{"place":76,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":81.25},{"place":77,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":81.2},{"place":78,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":80.7},{"place":79,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":79.92},{"place":80,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":79.9},{"place":81,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":79.9},{"place":82,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":79.3},{"place":83,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79},{"place":84,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.8},{"place":85,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.7},{"place":86,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.5},{"place":87,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":78.4},{"place":88,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":77.8},{"place":89,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.2},{"place":90,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":76.5},{"place":91,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":76.23},{"place":92,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75.5},{"place":93,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":75.2},{"place":94,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":74.6},{"place":95,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":73.5},{"place":96,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":73.48},{"place":97,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.48},{"place":98,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.87},{"place":99,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":72.7},{"place":100,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":72.7},{"place":101,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":72.2},{"place":102,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":71.9},{"place":103,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":71.6},{"place":104,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.21},{"place":105,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":71.2},{"place":106,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.8},{"place":107,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":70.6},{"place":108,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":70.31},{"place":109,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.79},{"place":110,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.7},{"place":111,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.6},{"place":112,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":68.9},{"place":113,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":67.95},{"place":114,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":67.8},{"place":115,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.7},{"place":116,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":66.5},{"place":117,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.7},{"place":118,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.6},{"place":119,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64},{"place":120,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":63.8},{"place":121,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":63.64},{"place":122,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":63.6},{"place":123,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.6},{"place":124,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":63.3},{"place":125,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":63.2},{"place":126,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":63.1},{"place":127,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":62.9},{"place":128,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.41},{"place":129,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.6},{"place":130,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":61.4},{"place":131,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":60.8},{"place":132,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60.8},{"place":133,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.6},{"place":134,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":59.48},{"place":135,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":57.2},{"place":136,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":51.52},{"place":137,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.5},{"place":138,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":51.3},{"place":139,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":50.6},{"place":140,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":49.29},{"place":141,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":48.4},{"place":142,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":46.21},{"place":143,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":45.45},{"place":144,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.94},{"place":145,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40.8},{"place":146,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":40.53},{"place":147,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":38.5},{"place":148,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":36.9},{"place":149,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":35.89},{"place":150,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":34.7},{"place":151,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.2},{"place":152,"model":"g9v3-3b","company":"ai9stars","family":"G9","version":"G9v3","score":34.1},{"place":153,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.85},{"place":154,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":33.7},{"place":155,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.7},{"place":156,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.1},{"place":157,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":31.7},{"place":158,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.1},{"place":159,"model":"k2-horizon-0.9b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":25.8},{"place":160,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":25.76},{"place":161,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":24.2},{"place":162,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":23.3},{"place":163,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.7},{"place":164,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":21.73},{"place":165,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.5},{"place":166,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":21.21},{"place":167,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":20.5},{"place":168,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.5},{"place":169,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":17.8},{"place":170,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.85},{"place":171,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.6},{"place":172,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.57}]},{"id":"hmmt-nov-2025","name":"HMMT Nov 2025","topic":"Math (competition)","description":"Harvard–MIT Mathematics Tournament November 2025 problems.","url":"https://hmmt.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2 (high)","top_percent":100,"top_model_id":"gpt-5.2-high","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":81,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":2,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":3,"model":"ring-1t-2.5-heavy-thinking","company":"antgroup","family":"Ring","version":"Ring 2.5","score":98.33},{"place":4,"model":"ring-1t-2.5","company":"antgroup","family":"Ring","version":"Ring 2.5","score":97.34},{"place":5,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":96.9},{"place":6,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":96.7},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":96.7},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":96.5},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":96.5},{"place":10,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":96.3},{"place":11,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":95.8},{"place":12,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":95},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":94.8},{"place":14,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":94.7},{"place":15,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":94.6},{"place":16,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":94.4},{"place":17,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.4},{"place":18,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":94},{"place":19,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":94},{"place":20,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":93.5},{"place":21,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.3},{"place":22,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":93.3},{"place":23,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":93.3},{"place":24,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.7},{"place":25,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":91.51},{"place":26,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":91.1},{"place":27,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":91.1},{"place":28,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":91},{"place":29,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90.7},{"place":30,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.3},{"place":31,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.2},{"place":32,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.2},{"place":33,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":90},{"place":34,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.8},{"place":35,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.5},{"place":36,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.2},{"place":37,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":89.2},{"place":38,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.2},{"place":39,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.1},{"place":40,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.8},{"place":41,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":87.7},{"place":42,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.5},{"place":43,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.5},{"place":44,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":86.8},{"place":45,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":86.7},{"place":46,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":85.8},{"place":47,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":84.9},{"place":48,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":84.4},{"place":49,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":84.4},{"place":50,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":84.2},{"place":51,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.9},{"place":52,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":81.93},{"place":53,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":81.8},{"place":54,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":81.7},{"place":55,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":81.7},{"place":56,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":81.2},{"place":57,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":81},{"place":58,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":80.21},{"place":59,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":80},{"place":60,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80},{"place":61,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":80},{"place":62,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":78.1},{"place":63,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":77.92},{"place":64,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.8},{"place":65,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":75},{"place":66,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75},{"place":67,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":74.3},{"place":68,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":74.2},{"place":69,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.8},{"place":70,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":73.3},{"place":71,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.3},{"place":72,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.25},{"place":73,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":70},{"place":74,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":69.6},{"place":75,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":68.33},{"place":76,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":68.3},{"place":77,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":66.7},{"place":78,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":66.67},{"place":79,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":66.46},{"place":80,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":61.2},{"place":81,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":59},{"place":82,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":58.3},{"place":83,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":57.08},{"place":84,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.67},{"place":85,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":53.44},{"place":86,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":53.18},{"place":87,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.33},{"place":88,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":47.76},{"place":89,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":46.09},{"place":90,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":19.6},{"place":91,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":8.9}]},{"id":"home-appliance-simulator-decision","name":"Home appliance simulator (decision)","topic":"Device control","description":"Multi-step home appliance control decisions; case exact accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://huggingface.co/spaces/multimodalart/jev-decision-index","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Bespoke-Nimble-9B-v3","top_percent":98.9,"top_model_id":"bespoke-nimble-9b-v3","top_generation":"v3","top_model_base":"Bespoke-Nimble-9B","top_model_family":"Bespoke-Nimble","top_company":"bespokelabs","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":98.9},{"place":2,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":97.7},{"place":3,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":92},{"place":4,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":90.9},{"place":5,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":83},{"place":6,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":80.7},{"place":7,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":75},{"place":8,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":69.3},{"place":9,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":65.9},{"place":10,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":63.6},{"place":11,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":53.4},{"place":12,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":52.3},{"place":13,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":52.3},{"place":14,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":50},{"place":15,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":45.5},{"place":16,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":42},{"place":17,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":37.5},{"place":18,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":27.3},{"place":19,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":26.1},{"place":20,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":25},{"place":21,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":21.6},{"place":22,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":18.2},{"place":23,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":14.8},{"place":24,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":12.5},{"place":25,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":12.5},{"place":26,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":11.4},{"place":27,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":2.3},{"place":28,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":1.1},{"place":29,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":1.1},{"place":30,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":0},{"place":31,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":0},{"place":32,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":0},{"place":33,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":0},{"place":34,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":0},{"place":35,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":0},{"place":36,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":0},{"place":37,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":0},{"place":38,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":0}]},{"id":"hotpotqa","name":"HotpotQA","topic":"Multi-hop QA","description":"Explainable multi-hop QA with supporting facts.","url":"https://hotpotqa.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-0.6B","top_percent":64,"top_model_id":"qwen3-0.6b","top_generation":"Qwen3","top_model_base":"Qwen3 0.6B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":64},{"place":2,"model":"baguettotron-321m","company":"pleias","family":"Baguettotron","version":"Baguettotron","score":51},{"place":3,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":25},{"place":4,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":25},{"place":5,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":23},{"place":6,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":21},{"place":7,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":16}]},{"id":"hover","name":"HoVer","topic":"Claim verification","description":"Multi-hop claim verification over Wikipedia introductions; accuracy (Jev Decision Index suite, posed as typed decisions).","url":"https://github.com/hover-nlp/hover","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"AutoTrust JEV-35B","top_percent":88.1,"top_model_id":"autotrust-jev-35b","top_generation":"JEV-35B","top_model_base":"JEV-35B","top_model_family":"JEV","top_company":"autotrust","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":88.1},{"place":2,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":87.9},{"place":3,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":86.2},{"place":4,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":86.2},{"place":5,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":84.9},{"place":6,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":84.4},{"place":7,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":83.5},{"place":8,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":82.6},{"place":9,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":82.2},{"place":10,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":81.8},{"place":11,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":81.5},{"place":12,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":81},{"place":13,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":80.2},{"place":14,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":79.9},{"place":15,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":78.4},{"place":16,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":76.8},{"place":17,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":74.1},{"place":18,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":73.9},{"place":19,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":73.9},{"place":20,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":72.9},{"place":21,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":71.5},{"place":22,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":70.9},{"place":23,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":65.2},{"place":24,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":64.7},{"place":25,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":64.2},{"place":26,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":64.1},{"place":27,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":62.9},{"place":28,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":61.2},{"place":29,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":60.5},{"place":30,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":59.8},{"place":31,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":58.8},{"place":32,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":56.8},{"place":33,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":55.8},{"place":34,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":54},{"place":35,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":53.4},{"place":36,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":53.1},{"place":37,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":52.3},{"place":38,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":50.7}]},{"id":"hrbench4k","name":"HRBench 4K","topic":"Hallucination robustness","description":"Hallucination robustness benchmark with 4K token contexts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"SenseNova-MARS-32B","top_percent":90.2,"top_model_id":"sensenova-mars-32b","top_generation":"SenseNova-MARS","top_model_base":"SenseNova-MARS 32B","top_model_family":"SenseNova","top_company":"sensetime","top_open_source":1,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"sensenova-mars-32b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":90.2},{"place":2,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.5},{"place":3,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":88.5},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":87.88},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.3},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.9},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.4},{"place":8,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":85},{"place":9,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.5},{"place":10,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":84.38},{"place":11,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":84},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.9},{"place":13,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":83.3},{"place":14,"model":"sensenova-mars-8b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":83.1},{"place":15,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83},{"place":16,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.9},{"place":17,"model":"skywork-r1v4","company":"skywork","family":"Skywork","version":"Skywork R1V4","score":82.8},{"place":18,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":81.87},{"place":19,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":81.75},{"place":20,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":81.63},{"place":21,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.2},{"place":22,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":79.9},{"place":23,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.9},{"place":24,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.88},{"place":25,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.5},{"place":26,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.3},{"place":27,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.25},{"place":28,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.8},{"place":29,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.5},{"place":30,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":75.38},{"place":31,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":75.1},{"place":32,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":74.38},{"place":33,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.1},{"place":34,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":71.62},{"place":35,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":69.88},{"place":36,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":69.3},{"place":37,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":69.1},{"place":38,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":67.6},{"place":39,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":67.6},{"place":40,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":67},{"place":41,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":65.5},{"place":42,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":65},{"place":43,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":63},{"place":44,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":50.6}]},{"id":"hrbench8k","name":"HRBench 8K","topic":"Hallucination robustness","description":"Hallucination robustness benchmark with 8K token contexts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"SenseNova-MARS-32B","top_percent":86.6,"top_model_id":"sensenova-mars-32b","top_generation":"SenseNova-MARS","top_model_base":"SenseNova-MARS 32B","top_model_family":"SenseNova","top_company":"sensetime","top_open_source":1,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"sensenova-mars-32b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":86.6},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.4},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":85},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84},{"place":5,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":83.4},{"place":6,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.5},{"place":7,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":82},{"place":8,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.62},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.5},{"place":10,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":80.4},{"place":11,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.4},{"place":12,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80},{"place":13,"model":"skywork-r1v4","company":"skywork","family":"Skywork","version":"Skywork R1V4","score":79.8},{"place":14,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":79.5},{"place":15,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.3},{"place":16,"model":"sensenova-mars-8b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":78.4},{"place":17,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.8},{"place":18,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.9},{"place":19,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":75.38},{"place":20,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":74.88},{"place":21,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.63},{"place":22,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.6},{"place":23,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":74.3},{"place":24,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.2},{"place":25,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.7},{"place":26,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":73.25},{"place":27,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.9},{"place":28,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.88},{"place":29,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":72.88},{"place":30,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.3},{"place":31,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":71},{"place":32,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.4},{"place":33,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":68},{"place":34,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":67.88},{"place":35,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":66.3},{"place":36,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":65.25},{"place":37,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":63.62},{"place":38,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":63.6},{"place":39,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":62.1},{"place":40,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":59.8},{"place":41,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":59.6},{"place":42,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":40.5}]},{"id":"hrm8k","name":"HRM8K","topic":"Korean reasoning","description":"8k-question Korean reasoning and knowledge benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Flash-Thinking (max)","top_percent":93.4,"top_model_id":"deepseek-v4-flash-thinking-max","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Flash","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.4},{"place":2,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":92.2},{"place":3,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":92},{"place":4,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":91.6},{"place":5,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":91.3},{"place":6,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":90.9},{"place":7,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":90.7},{"place":8,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.6},{"place":9,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.6},{"place":10,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":89.4},{"place":11,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":87.6}]},{"id":"hss","name":"HSS","topic":"Scene understanding","description":"HSS scene-understanding benchmark over images and video.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":53.6,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":53.6},{"place":2,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":49.81},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":46.6},{"place":4,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":46.36},{"place":5,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":41.6}]},{"id":"humaneval","name":"HumanEval","topic":"Code generation","description":"Python synthesis problems evaluated by unit tests.","url":"https://github.com/openai/human-eval","leaderboard":"https://llmdb.com/benchmarks/humaneval","github":"https://github.com/openai/human-eval","paper":"https://arxiv.org/abs/2107.03374","metric":"percent","stars":"2916","top_model":"Gemini 3 Pro Preview","top_percent":100,"top_model_id":"gemini-3-pro-preview","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro Preview","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":627,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":100},{"place":2,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":100},{"place":3,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":98.8},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.8},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.8},{"place":6,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":98.78},{"place":7,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":98.2},{"place":8,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":98.17},{"place":9,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":98.17},{"place":10,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":97.6},{"place":11,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":97.6},{"place":12,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":97.6},{"place":13,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":97.6},{"place":14,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":97.6},{"place":15,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":97.2},{"place":16,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":97},{"place":17,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":96.95},{"place":18,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":96.95},{"place":19,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":96.34},{"place":20,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":96.34},{"place":21,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":96.34},{"place":22,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":96.3},{"place":23,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":96.3},{"place":24,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":96.3},{"place":25,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":96.3},{"place":26,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":96.3},{"place":27,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":96.3},{"place":28,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":96.3},{"place":29,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":96.3},{"place":30,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":96.3},{"place":31,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":96.3},{"place":32,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":96.2},{"place":33,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":95.9},{"place":34,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":95.9},{"place":35,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":95.9},{"place":36,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":95.7},{"place":37,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":95.7},{"place":38,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":95.7},{"place":39,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.4},{"place":40,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":95.12},{"place":41,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":95.12},{"place":42,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":95.1},{"place":43,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":95.1},{"place":44,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":94.6},{"place":45,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":94.51},{"place":46,"model":"hy-1.8b","company":"tencent","family":"HY","version":"HY","score":94.51},{"place":47,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":94.5},{"place":48,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":94.5},{"place":49,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":94.5},{"place":50,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":94.1},{"place":51,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":94},{"place":52,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":93.9},{"place":53,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.9},{"place":54,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.9},{"place":55,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":93.9},{"place":56,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":93.9},{"place":57,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":93.6},{"place":58,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.3},{"place":59,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":93.3},{"place":60,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":93.3},{"place":61,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.29},{"place":62,"model":"hy-1.8b-2bit","company":"tencent","family":"HY","version":"HY","score":93.29},{"place":63,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":93.2},{"place":64,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":93.2},{"place":65,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":93.1},{"place":66,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":92.9},{"place":67,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":92.9},{"place":68,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":92.7},{"place":69,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":92.7},{"place":70,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.68},{"place":71,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":92.68},{"place":72,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":92.4},{"place":73,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":92.4},{"place":74,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":92.4},{"place":75,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":92.4},{"place":76,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":92.3},{"place":77,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":92.1},{"place":78,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":92.1},{"place":79,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":92.1},{"place":80,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":92.1},{"place":81,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":92.1},{"place":82,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":92.1},{"place":83,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":92.07},{"place":84,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":92},{"place":85,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":92},{"place":86,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":91.5},{"place":87,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":91.5},{"place":88,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":91.5},{"place":89,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":91.5},{"place":90,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":91.46},{"place":91,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":91},{"place":92,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":91},{"place":93,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":90.9},{"place":94,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":90.5},{"place":95,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":90.2},{"place":96,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":90.2},{"place":97,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":90.2},{"place":98,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":90.2},{"place":99,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":90.2},{"place":100,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":90},{"place":101,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":89.73},{"place":102,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":89.6},{"place":103,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":89.6},{"place":104,"model":"gemini-diffusion","company":"google","family":"Gemini","version":"Gemini Diffusion","score":89.6},{"place":105,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.6},{"place":106,"model":"hy-1.8b-int4gptq","company":"tencent","family":"HY","version":"HY","score":89.02},{"place":107,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":89},{"place":108,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":89},{"place":109,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":89},{"place":110,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":89},{"place":111,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":88.41},{"place":112,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":88.4},{"place":113,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":88.4},{"place":114,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":88.4},{"place":115,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":88.4},{"place":116,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":88.4},{"place":117,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.4},{"place":118,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":88.4},{"place":119,"model":"grok-2","company":"xai","family":"Grok","version":"Grok 2","score":88.4},{"place":120,"model":"grok-beta","company":"xai","family":"Grok","version":"Grok","score":88.4},{"place":121,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":88.4},{"place":122,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.4},{"place":123,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.3},{"place":124,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":88.3},{"place":125,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":88.2},{"place":126,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":88.1},{"place":127,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":88.1},{"place":128,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":88},{"place":129,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":87.8},{"place":130,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":87.8},{"place":131,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":87.8},{"place":132,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":87.8},{"place":133,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.8},{"place":134,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":87.8},{"place":135,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":87.2},{"place":136,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.2},{"place":137,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":87.2},{"place":138,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.2},{"place":139,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":87.2},{"place":140,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":87.2},{"place":141,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":86.9},{"place":142,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":86.7},{"place":143,"model":"stable-diffcoder-8b-instruct","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":86.6},{"place":144,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":86.6},{"place":145,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":86.6},{"place":146,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":86.6},{"place":147,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.6},{"place":148,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.6},{"place":149,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.6},{"place":150,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":86.3},{"place":151,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":86.2},{"place":152,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":86},{"place":153,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":86},{"place":154,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86},{"place":155,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":86},{"place":156,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":85.98},{"place":157,"model":"grok-2-mini","company":"xai","family":"Grok","version":"Grok 2","score":85.7},{"place":158,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":85.4},{"place":159,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":85.4},{"place":160,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.4},{"place":161,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.4},{"place":162,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":85.4},{"place":163,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":85.4},{"place":164,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":85.4},{"place":165,"model":"joyai-llm-flash-base","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":85.37},{"place":166,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":85.37},{"place":167,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":85},{"place":168,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":84.9},{"place":169,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.8},{"place":170,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.8},{"place":171,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":84.8},{"place":172,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":84.8},{"place":173,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":84.8},{"place":174,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.8},{"place":175,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.76},{"place":176,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":84.5},{"place":177,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":84.2},{"place":178,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":84.14},{"place":179,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":84.1},{"place":180,"model":"step-2","company":"stepfun","family":"Step","version":"Step 2","score":84.1},{"place":181,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":84.1},{"place":182,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":84.1},{"place":183,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":84.1},{"place":184,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":83.9},{"place":185,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":83.9},{"place":186,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.84},{"place":187,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":83.7},{"place":188,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":83.5},{"place":189,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":83.5},{"place":190,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":83.5},{"place":191,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.5},{"place":192,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":83.5},{"place":193,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.2},{"place":194,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":83.2},{"place":195,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":82.9},{"place":196,"model":"dream-coder-7b-instruct","company":"huawei","family":"Dream","version":"Dream-Coder v0","score":82.9},{"place":197,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":82.9},{"place":198,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":82.6},{"place":199,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":82.41},{"place":200,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":82.3},{"place":201,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":82.3},{"place":202,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":82.3},{"place":203,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":82.3},{"place":204,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":82.3},{"place":205,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":82.3},{"place":206,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":82},{"place":207,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":81.71},{"place":208,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":81.7},{"place":209,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":81.7},{"place":210,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.6},{"place":211,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":81.31},{"place":212,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":81.1},{"place":213,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":81.1},{"place":214,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":81.1},{"place":215,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":81.1},{"place":216,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":81.1},{"place":217,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":81.1},{"place":218,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":81.1},{"place":219,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":81.1},{"place":220,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":80.51},{"place":221,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":80.5},{"place":222,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":80.5},{"place":223,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":80.5},{"place":224,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":80.49},{"place":225,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":80.49},{"place":226,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":80.49},{"place":227,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":80.49},{"place":228,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":80},{"place":229,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":80},{"place":230,"model":"wizardcoder-33b-v1.1","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.1","score":79.9},{"place":231,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":79.9},{"place":232,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":79.9},{"place":233,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":79.9},{"place":234,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":79.9},{"place":235,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":79.9},{"place":236,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":79.8},{"place":237,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":79.4},{"place":238,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.4},{"place":239,"model":"opencodeinterpreter-ds-33b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":79.3},{"place":240,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.3},{"place":241,"model":"stable-diffcoder-8b-base","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":79.3},{"place":242,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":79.3},{"place":243,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.27},{"place":244,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":78.9},{"place":245,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":78.7},{"place":246,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":78.7},{"place":247,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":78.7},{"place":248,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":78.6},{"place":249,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":78.5},{"place":250,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":78.2},{"place":251,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":78.16},{"place":252,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":78.1},{"place":253,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.05},{"place":254,"model":"abab6.5","company":"minimax","family":"abab","version":"abab6.5","score":78},{"place":255,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":77.44},{"place":256,"model":"opencodeinterpreter-ds-6.7b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":77.4},{"place":257,"model":"speechless-codellama-34b-v2.0","company":"speechless","family":"speechless-codellama-34B-v2.0","version":"speechless-codellama-34B-v2.0","score":77.4},{"place":258,"model":"deepseek-coder-33b","company":"deepseek","family":"DeepSeek Coder","version":"DeepSeek Coder","score":77.4},{"place":259,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.4},{"place":260,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":77.4},{"place":261,"model":"seed-coder-8b-base","company":"bytedance","family":"Seed","version":"Seed Coder","score":77.4},{"place":262,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":77.4},{"place":263,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":76.8},{"place":264,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":76.8},{"place":265,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":76.8},{"place":266,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.8},{"place":267,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":76.8},{"place":268,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":76.8},{"place":269,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":76.8},{"place":270,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":76.3},{"place":271,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":76.2},{"place":272,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":76.2},{"place":273,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":76.2},{"place":274,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":76.2},{"place":275,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":76.2},{"place":276,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":75.7},{"place":277,"model":"artigenz-coder-ds-6.7b","company":"artigenz","family":"Artigenz-Coder-DS-6.7B","version":"Artigenz Coder DS","score":75.6},{"place":278,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":75.6},{"place":279,"model":"xwincoder-34b","company":"xwin","family":"XwinCoder-34B","version":"XwinCoder-34B","score":75.6},{"place":280,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":75.6},{"place":281,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":75.59},{"place":282,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":75.58},{"place":283,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":75.4},{"place":284,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.29},{"place":285,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.29},{"place":286,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":75.2},{"place":287,"model":"codestral-mamba","company":"mistral","family":"Codestral","version":"Codestral","score":75},{"place":288,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":75},{"place":289,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":75},{"place":290,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75},{"place":291,"model":"wavecoder-ultra-6.7b","company":"wavecoder","family":"WaveCoder-Ultra-6.7B","version":"WaveCoder-Ultra-6.7B","score":75},{"place":292,"model":"databricks-dbrx-instruct","company":"databricks","family":"databricks/dbrx-instruct","version":"databricks/dbrx-instruct","score":75},{"place":293,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":75},{"place":294,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":75},{"place":295,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":75},{"place":296,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":74.4},{"place":297,"model":"code-millenials-34b","company":"code","family":"code-millenials-34B","version":"code-millenials-34B","score":74.4},{"place":298,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":74.4},{"place":299,"model":"yuan2.0-m32","company":"yuanlab","family":"Yuan","version":"Yuan2.0-M32","score":74.4},{"place":300,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":74.4},{"place":301,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.4},{"place":302,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":74.4},{"place":303,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.4},{"place":304,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":74.4},{"place":305,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":74.39},{"place":306,"model":"starchat2-15b-v0.1","company":"huggingface","family":"starchat2-15b-v0.1","version":"starchat2-15b-v0.1","score":73.8},{"place":307,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":73.8},{"place":308,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":73.8},{"place":309,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":73.7},{"place":310,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":73.58},{"place":311,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.5},{"place":312,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":73.2},{"place":313,"model":"wizardcoder-python-34b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":73.2},{"place":314,"model":"gpt-3.5-may-2023","company":"openai","family":"GPT","version":"GPT-3.5","score":73.2},{"place":315,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":73.2},{"place":316,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":73.17},{"place":317,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":73},{"place":318,"model":"openchat-3.5-7b-0106","company":"openchat","family":"OpenChat-3.5-7B-0106","version":"OpenChat-3.5-7B-0106","score":72.6},{"place":319,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":72.6},{"place":320,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":72.6},{"place":321,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":72.6},{"place":322,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":72.5},{"place":323,"model":"diffucoder-7b-instruct","company":"apple","family":"DiffuCoder","version":"DiffuCoder","score":72},{"place":324,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":72},{"place":325,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":72},{"place":326,"model":"whiterabbitneo-33b-v1","company":"whiterabbit","family":"WhiteRabbitNeo-33B-v1","version":"WhiteRabbitNeo-33B-v1","score":72},{"place":327,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":72},{"place":328,"model":"glm-4-0116","company":"zai","family":"GLM","version":"GLM 4","score":72},{"place":329,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":71.95},{"place":330,"model":"internlm2.5-20b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":71.95},{"place":331,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":71.8},{"place":332,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":71.7},{"place":333,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":71.7},{"place":334,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":71.4},{"place":335,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":71.34},{"place":336,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":71.3},{"place":337,"model":"speechless-coder-ds-6.7b","company":"speechless","family":"speechless-coder-ds-6.7B","version":"speechless-coder-ds-6.7B","score":71.3},{"place":338,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":71.3},{"place":339,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":71.3},{"place":340,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":71.14},{"place":341,"model":"magicoder-s-cl-7b","company":"magicoder","family":"Magicoder-S-CL-7B","version":"Magicoder-S-CL-7B","score":70.7},{"place":342,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":70.7},{"place":343,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":70.7},{"place":344,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.7},{"place":345,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":70.3},{"place":346,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":70.1},{"place":347,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":70.1},{"place":348,"model":"baichuan-3","company":"baichuan","family":"Baichuan","version":"Baichuan 3","score":70.1},{"place":349,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":70.1},{"place":350,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":69.51},{"place":351,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":69.5},{"place":352,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":69.5},{"place":353,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.5},{"place":354,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":69.5},{"place":355,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":69.5},{"place":356,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":69.5},{"place":357,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":69.5},{"place":358,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":69.5},{"place":359,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.9},{"place":360,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":68.9},{"place":361,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":68.9},{"place":362,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":68.9},{"place":363,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":68.9},{"place":364,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":68.9},{"place":365,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":68.8},{"place":366,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":68.3},{"place":367,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":68.3},{"place":368,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":68.3},{"place":369,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":68.3},{"place":370,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":67.7},{"place":371,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.7},{"place":372,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":67.7},{"place":373,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":67.7},{"place":374,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.2},{"place":375,"model":"speechless-starcoder2-15b","company":"bigcode","family":"speechless-starcoder2-15b","version":"speechless-starcoder2-15b","score":67.1},{"place":376,"model":"codellama-70b","company":"meta","family":"CodeLlama","version":"CodeLlama","score":67.1},{"place":377,"model":"yuan2.0-102b","company":"yuanlab","family":"Yuan","version":"Yuan2.0","score":67.1},{"place":378,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":67.1},{"place":379,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.1},{"place":380,"model":"hy-0.5b","company":"tencent","family":"HY","version":"HY","score":67.07},{"place":381,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":67},{"place":382,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":67},{"place":383,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":67},{"place":384,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":66.71},{"place":385,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.5},{"place":386,"model":"opencoder-8b-base","company":"map","family":"OpenCoder","version":"OpenCoder","score":66.5},{"place":387,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":66.5},{"place":388,"model":"yuan2.0-51b","company":"yuanlab","family":"Yuan","version":"Yuan2.0","score":66.5},{"place":389,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":66.5},{"place":390,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.46},{"place":391,"model":"code-qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":66.4},{"place":392,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.1},{"place":393,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":66.1},{"place":394,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":65.9},{"place":395,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":65.9},{"place":396,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":65.9},{"place":397,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":65.9},{"place":398,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":65.2},{"place":399,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":65.2},{"place":400,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":65.2},{"place":401,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":65.1},{"place":402,"model":"code-290k-6.7b-instruct","company":"code","family":"Code","version":"Code 290k","score":64.6},{"place":403,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":64.6},{"place":404,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":64.6},{"place":405,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":64.6},{"place":406,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":64.1},{"place":407,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":64},{"place":408,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":64},{"place":409,"model":"dolphin-2.6-mixtral-8x7b","company":"mistral","family":"dolphin-2.6-mixtral-8x7b","version":"dolphin-2.6-mixtral-8x7b","score":64},{"place":410,"model":"wizardcoder-python-13b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":64},{"place":411,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":64},{"place":412,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":64},{"place":413,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":63.9},{"place":414,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":63.4},{"place":415,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":63.4},{"place":416,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":63.4},{"place":417,"model":"grok-1","company":"xai","family":"Grok","version":"Grok 1","score":63.2},{"place":418,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.8},{"place":419,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.8},{"place":420,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.8},{"place":421,"model":"codellama-34b-unnatural","company":"meta","family":"CodeLlama","version":"CodeLlama","score":62.2},{"place":422,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":62.2},{"place":423,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":62.2},{"place":424,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":61.85},{"place":425,"model":"llada-moe-7b-a1b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":61.6},{"place":426,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":61.6},{"place":427,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":61.6},{"place":428,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":61.6},{"place":429,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":61.6},{"place":430,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":61.6},{"place":431,"model":"codegemma-1.1-7b","company":"google","family":"CodeGemma","version":"CodeGemma","score":61},{"place":432,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":61},{"place":433,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":61},{"place":434,"model":"phi-3-small-8k-instruct","company":"microsoft","family":"Phi","version":"Phi-3","score":61},{"place":435,"model":"codegemma-7b-it","company":"google","family":"Codegemma","version":"Codegemma","score":60.4},{"place":436,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":59.8},{"place":437,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":59.8},{"place":438,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":59.2},{"place":439,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":59.2},{"place":440,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.1},{"place":441,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":58.5},{"place":442,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":58.5},{"place":443,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.5},{"place":444,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":58.5},{"place":445,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":58.5},{"place":446,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":57.9},{"place":447,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":57.9},{"place":448,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":57.9},{"place":449,"model":"claude-instant-1-mar-2024","company":"anthropic","family":"claude-instant-1","version":"claude-instant-1 (Mar 2024)","score":57.3},{"place":450,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":57.3},{"place":451,"model":"wizardcoder-15b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":57.3},{"place":452,"model":"nemotron-4-340b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-4","score":57.3},{"place":453,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":57},{"place":454,"model":"minicpm-moe-8x2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":56.71},{"place":455,"model":"wizardcoder-15b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":56.7},{"place":456,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":56.7},{"place":457,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.7},{"place":458,"model":"code-13b","company":"code","family":"Code-13B","version":"Code-13B","score":56.1},{"place":459,"model":"speechless-starcoder2-7b","company":"bigcode","family":"speechless-starcoder2-7b","version":"speechless-starcoder2-7b","score":56.1},{"place":460,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":56.1},{"place":461,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":56.1},{"place":462,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":56},{"place":463,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":55.96},{"place":464,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":55.5},{"place":465,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":55.5},{"place":466,"model":"codellama-70b","company":"meta","family":"CodeLlama","version":"CodeLlama","score":55.5},{"place":467,"model":"code-33b","company":"code","family":"Code-33B","version":"Code-33B","score":54.9},{"place":468,"model":"speechless-coding-7b-16k-tora","company":"speechless","family":"speechless-coding-7B-16k-tora","version":"speechless-coding-7B-16k-tora","score":54.9},{"place":469,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":54.9},{"place":470,"model":"yuan2.0-2b","company":"yuanlab","family":"Yuan","version":"Yuan2.0","score":54.9},{"place":471,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":54.9},{"place":472,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":54.9},{"place":473,"model":"openhermes-2.5-code-290k-13b","company":"openhermes","family":"OpenHermes-2.5-Code-290k-13B","version":"OpenHermes-2.5-Code-290k-13B","score":54.3},{"place":474,"model":"coda-1.7b-instruct","company":"salesforce","family":"CoDA","version":"CoDA","score":54.3},{"place":475,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":54.3},{"place":476,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.3},{"place":477,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":54.3},{"place":478,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":53.86},{"place":479,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":53.7},{"place":480,"model":"codellama-python-34b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":53.7},{"place":481,"model":"yi-coder-9b","company":"01ai","family":"Yi","version":"Yi-Coder","score":53.7},{"place":482,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.32},{"place":483,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":53.32},{"place":484,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":53.1},{"place":485,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":53.1},{"place":486,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":53},{"place":487,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":53},{"place":488,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":52.44},{"place":489,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52.4},{"place":490,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":52.4},{"place":491,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":52.4},{"place":492,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":52.4},{"place":493,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":52.4},{"place":494,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":52.4},{"place":495,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":52.2},{"place":496,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":52.03},{"place":497,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":51.8},{"place":498,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":51.8},{"place":499,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":51.8},{"place":500,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":51.6},{"place":501,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":51.33},{"place":502,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":51.22},{"place":503,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":51.22},{"place":504,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":51.2},{"place":505,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":51.2},{"place":506,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":51.2},{"place":507,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":51.2},{"place":508,"model":"wizardcoder-python-7b-v1.0","company":"microsoft","family":"WizardCoder-Python-7B-V1.0","version":"WizardCoder-Python-7B-V1.0","score":50.6},{"place":509,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":50.6},{"place":510,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":50},{"place":511,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50},{"place":512,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":50},{"place":513,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":50},{"place":514,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":50},{"place":515,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":50},{"place":516,"model":"phi-2-2.7b","company":"microsoft","family":"phi-2-2.7B","version":"phi-2-2.7B","score":49.4},{"place":517,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":49.4},{"place":518,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":49.4},{"place":519,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":49.4},{"place":520,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":49.1},{"place":521,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":49},{"place":522,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":49},{"place":523,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.8},{"place":524,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":48.8},{"place":525,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":48.8},{"place":526,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":48.8},{"place":527,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":48.8},{"place":528,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":48.8},{"place":529,"model":"mistral-codealpaca-7b","company":"mistral","family":"Mistral","version":"Mistral Codealpaca","score":48.2},{"place":530,"model":"speechless-code-mistral-7b-v1.0","company":"speechless","family":"speechless-code-mistral-7B-v1.0","version":"speechless-code-mistral-7B-v1.0","score":48.2},{"place":531,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":48.2},{"place":532,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":48.2},{"place":533,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":48.2},{"place":534,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":48.2},{"place":535,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":48.1},{"place":536,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":47.6},{"place":537,"model":"mistralhermes-codepro-7b-v1","company":"mistral","family":"MistralHermes","version":"MistralHermes CodePro v1","score":47.6},{"place":538,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":47.6},{"place":539,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":47.56},{"place":540,"model":"code-davinci-002","company":"openai","family":"Codex","version":"Codex","score":47},{"place":541,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":47},{"place":542,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":46.8},{"place":543,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":46.6},{"place":544,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":46.3},{"place":545,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":46.3},{"place":546,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":46.3},{"place":547,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":46.3},{"place":548,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":46.3},{"place":549,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":46.3},{"place":550,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":46.3},{"place":551,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":46.3},{"place":552,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":45.73},{"place":553,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":45.7},{"place":554,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":45.7},{"place":555,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":45.7},{"place":556,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":45.7},{"place":557,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":45.31},{"place":558,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":45.1},{"place":559,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":45.1},{"place":560,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":45.1},{"place":561,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":45.1},{"place":562,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":45.1},{"place":563,"model":"code-qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":45.1},{"place":564,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":45.1},{"place":565,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":44.7},{"place":566,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":44.51},{"place":567,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":44.51},{"place":568,"model":"codegemma-7b","company":"google","family":"Codegemma","version":"codegemma-7b","score":44.5},{"place":569,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":43.9},{"place":570,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":43.9},{"place":571,"model":"skywork-moe-base","company":"skywork","family":"Skywork","version":"Skywork-MoE","score":43.9},{"place":572,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":43.9},{"place":573,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":43.9},{"place":574,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":43.3},{"place":575,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":43.3},{"place":576,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":43.3},{"place":577,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":43.3},{"place":578,"model":"kwaiyii-13b-chat","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":43.3},{"place":579,"model":"codellama-python-13b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":43.3},{"place":580,"model":"code-qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":43.3},{"place":581,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":43.3},{"place":582,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":43.2},{"place":583,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":42.7},{"place":584,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":42.7},{"place":585,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":42.7},{"place":586,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":42.7},{"place":587,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":42.7},{"place":588,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":42.1},{"place":589,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":42.1},{"place":590,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.1},{"place":591,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":42.1},{"place":592,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":42.1},{"place":593,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":41.5},{"place":594,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":41.5},{"place":595,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":41.5},{"place":596,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":41.5},{"place":597,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":41.5},{"place":598,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":41.5},{"place":599,"model":"yi-coder-1.5b","company":"01ai","family":"Yi","version":"Yi-Coder","score":41.5},{"place":600,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":41.4},{"place":601,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":41.4},{"place":602,"model":"tfree-hat-pretrained-7b-base","company":"alephalpha","family":"TFree","version":"TFree Hat","score":41.1},{"place":603,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":40.9},{"place":604,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":40.9},{"place":605,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":40.9},{"place":606,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":40.85},{"place":607,"model":"kwaiyii-13b-base","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":40.8},{"place":608,"model":"bolmo-7b","company":"allenai","family":"Bolmo","version":"Bolmo 7B","score":40.6},{"place":609,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":40.4},{"place":610,"model":"xdan-l1-chat-rl-v1-7b","company":"xdan","family":"xDAN-L1-Chat-RL-v1-7B","version":"xDAN-L1-Chat-RL-v1-7B","score":40.2},{"place":611,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":40.2},{"place":612,"model":"code-qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":40.2},{"place":613,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":40.2},{"place":614,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":40},{"place":615,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":39.6},{"place":616,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":39.02},{"place":617,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":39},{"place":618,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":39},{"place":619,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":38.8},{"place":620,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":38.41},{"place":621,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":38.4},{"place":622,"model":"codellama-python-7b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":38.4},{"place":623,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":38.4},{"place":624,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":38.4},{"place":625,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":38},{"place":626,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":37.8},{"place":627,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":37.8},{"place":628,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":37.8},{"place":629,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":37.8},{"place":630,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.8},{"place":631,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":37.8},{"place":632,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.8},{"place":633,"model":"palm-2-s","company":"google","family":"PaLM","version":"PaLM 2","score":37.6},{"place":634,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":37.2},{"place":635,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":37.2},{"place":636,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":37.2},{"place":637,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37.2},{"place":638,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.2},{"place":639,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":36.6},{"place":640,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":36.59},{"place":641,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":36.5},{"place":642,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":36},{"place":643,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":36},{"place":644,"model":"codegeex2-6b","company":"zai","family":"CodeGeeX","version":"CodeGeeX2","score":36},{"place":645,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":36},{"place":646,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":36},{"place":647,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":36},{"place":648,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":36},{"place":649,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":35.98},{"place":650,"model":"internlm2.5-1.8b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":35.98},{"place":651,"model":"palm-coder-540b","company":"google","family":"PaLM","version":"PaLM","score":35.9},{"place":652,"model":"codegeex2-6b","company":"zai","family":"CodeGeeX","version":"CodeGeeX2","score":35.9},{"place":653,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":35.4},{"place":654,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":35.4},{"place":655,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":35.4},{"place":656,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":35.4},{"place":657,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.4},{"place":658,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":35.4},{"place":659,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":35.4},{"place":660,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":35.37},{"place":661,"model":"instructcodet5plus-16b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":35},{"place":662,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":34.8},{"place":663,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":34.8},{"place":664,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":34.8},{"place":665,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":34.8},{"place":666,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":34.8},{"place":667,"model":"evabyte-6.5b","company":"hku","family":"EvaByte","version":"EvaByte 6.5B","score":34.7},{"place":668,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":34.7},{"place":669,"model":"qwen1.5-moe-a2.7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":34.2},{"place":670,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":34.15},{"place":671,"model":"starcoder-15b","company":"bigcode","family":"StarCoder-15B","version":"StarCoder","score":34.1},{"place":672,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":34.1},{"place":673,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":33.5},{"place":674,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":33.5},{"place":675,"model":"code-cushman-001","company":"openai","family":"Codex","version":"Codex","score":33.5},{"place":676,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":33.5},{"place":677,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":33.5},{"place":678,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":33.5},{"place":679,"model":"codegen-16b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":32.9},{"place":680,"model":"python-code-13b","company":"python","family":"Python-Code-13B","version":"Python-Code-13B","score":32.9},{"place":681,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":32.9},{"place":682,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":32.3},{"place":683,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":32.3},{"place":684,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":32.3},{"place":685,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":32.3},{"place":686,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":32.3},{"place":687,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":32.3},{"place":688,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":32.3},{"place":689,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":32.3},{"place":690,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.3},{"place":691,"model":"codet5plus-16b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":31.7},{"place":692,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":31.7},{"place":693,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":31.7},{"place":694,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":31.7},{"place":695,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":31.7},{"place":696,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":31.6},{"place":697,"model":"blt-7b","company":"meta","family":"BLT","version":"BLT 7B","score":31.5},{"place":698,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":31.1},{"place":699,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.1},{"place":700,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":31.1},{"place":701,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":31.1},{"place":702,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":31.1},{"place":703,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":31.1},{"place":704,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":31.1},{"place":705,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":31.1},{"place":706,"model":"codet5plus-16b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":30.9},{"place":707,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":30.5},{"place":708,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":30.5},{"place":709,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":30.5},{"place":710,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":30.5},{"place":711,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":30.5},{"place":712,"model":"internlm2-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":30.49},{"place":713,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":30},{"place":714,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":29.9},{"place":715,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":29.9},{"place":716,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":29.9},{"place":717,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":29.9},{"place":718,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":29.9},{"place":719,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":29.9},{"place":720,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":29.9},{"place":721,"model":"codegen-6b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":29.3},{"place":722,"model":"codet5plus-6b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":29.3},{"place":723,"model":"coda-1.7b-base","company":"salesforce","family":"CoDA","version":"CoDA","score":29.3},{"place":724,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":29.3},{"place":725,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":29.3},{"place":726,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":29.3},{"place":727,"model":"stablecode-3b","company":"stability","family":"StableCode","version":"StableCode","score":29.3},{"place":728,"model":"jamba-v0.1","company":"ai21","family":"Jamba","version":"Jamba","score":29.3},{"place":729,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":29.3},{"place":730,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":29.3},{"place":731,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":29.3},{"place":732,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":29.27},{"place":733,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.7},{"place":734,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":28.7},{"place":735,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":28.7},{"place":736,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":28.7},{"place":737,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":28.66},{"place":738,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":28.3},{"place":739,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":28.1},{"place":740,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":28},{"place":741,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":28},{"place":742,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":28},{"place":743,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":27.44},{"place":744,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":27.4},{"place":745,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":27.4},{"place":746,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":27.4},{"place":747,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":26.83},{"place":748,"model":"codegemma-2b","company":"google","family":"Codegemma","version":"codegemma-2b","score":26.8},{"place":749,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":26.8},{"place":750,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":26.8},{"place":751,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":26.22},{"place":752,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":26.22},{"place":753,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":26.22},{"place":754,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":26.2},{"place":755,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":26.2},{"place":756,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":26.2},{"place":757,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":26.2},{"place":758,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":26.2},{"place":759,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":25.61},{"place":760,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":25.6},{"place":761,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":25.6},{"place":762,"model":"qwen1.5-4b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":25.6},{"place":763,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":25},{"place":764,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":25},{"place":765,"model":"codet5-2b","company":"salesforce","family":"CodeT5+-2B","version":"CodeT5+-2B","score":25},{"place":766,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":25},{"place":767,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":25},{"place":768,"model":"codegen-2b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":24.4},{"place":769,"model":"starcoderbase-7b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":24.4},{"place":770,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":24.4},{"place":771,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":24.4},{"place":772,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":24.39},{"place":773,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":24.39},{"place":774,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":23.8},{"place":775,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":23.8},{"place":776,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":23.8},{"place":777,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":23.7},{"place":778,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":23.7},{"place":779,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":23.2},{"place":780,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":23.2},{"place":781,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":22.6},{"place":782,"model":"llama-2-34b","company":"meta","family":"Llama","version":"Llama 2","score":22.6},{"place":783,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":22.6},{"place":784,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":22.6},{"place":785,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":22.12},{"place":786,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":22},{"place":787,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":22},{"place":788,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":22},{"place":789,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":22},{"place":790,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":21.95},{"place":791,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":21.7},{"place":792,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":21.6},{"place":793,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":21.4},{"place":794,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":21.34},{"place":795,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":21.3},{"place":796,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":20.7},{"place":797,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":20.7},{"place":798,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":20.12},{"place":799,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":20.1},{"place":800,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":20.1},{"place":801,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":20.1},{"place":802,"model":"codegen2-16b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":19.5},{"place":803,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":19.5},{"place":804,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":19.5},{"place":805,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":19.5},{"place":806,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":18.9},{"place":807,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":18.9},{"place":808,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":18.9},{"place":809,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":18.9},{"place":810,"model":"codegen2-7b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":18.3},{"place":811,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":18.3},{"place":812,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":18.3},{"place":813,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":18.3},{"place":814,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":18.3},{"place":815,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":18.29},{"place":816,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":18.29},{"place":817,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":18.29},{"place":818,"model":"starcoderbase-3b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":17.7},{"place":819,"model":"gemma-2b-it","company":"google","family":"Gemma","version":"Gemma","score":17.7},{"place":820,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":17.7},{"place":821,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":17.7},{"place":822,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":17.7},{"place":823,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":17.7},{"place":824,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":17.68},{"place":825,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":17.6},{"place":826,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":17.1},{"place":827,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":17.1},{"place":828,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":17.1},{"place":829,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":17.1},{"place":830,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":17.1},{"place":831,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":17.1},{"place":832,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":17.07},{"place":833,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":17.07},{"place":834,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":17.07},{"place":835,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":16.46},{"place":836,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":16.46},{"place":837,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":16.3},{"place":838,"model":"codegen2-3b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":15.9},{"place":839,"model":"incoder-6.7b","company":"ai21","family":"InCoder","version":"InCoder","score":15.9},{"place":840,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":15.9},{"place":841,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":15.9},{"place":842,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":15.9},{"place":843,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":15.85},{"place":844,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":15.85},{"place":845,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":15.85},{"place":846,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":15.8},{"place":847,"model":"bloom-176b","company":"bigscience","family":"BLOOM","version":"176B","score":15.5},{"place":848,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":15.27},{"place":849,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":15.24},{"place":850,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":15.24},{"place":851,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":15.2},{"place":852,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":15.2},{"place":853,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":14.63},{"place":854,"model":"santacoder-1.1b","company":"bigcode","family":"SantaCoder","version":"SantaCoder","score":14.6},{"place":855,"model":"starcoderbase-1b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":14.6},{"place":856,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":14.6},{"place":857,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":14.6},{"place":858,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":14.6},{"place":859,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":14.6},{"place":860,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":14.02},{"place":861,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":14.02},{"place":862,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":14.02},{"place":863,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":14.02},{"place":864,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":14},{"place":865,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":14},{"place":866,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":14},{"place":867,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":13.4},{"place":868,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":13.4},{"place":869,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":13.4},{"place":870,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":12.8},{"place":871,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":12.8},{"place":872,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":12.8},{"place":873,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":12.8},{"place":874,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":12.8},{"place":875,"model":"gpt-j-6b","company":"openai","family":"GPT","version":"GPT-J","score":12.2},{"place":876,"model":"incoder-1.3b","company":"ai21","family":"InCoder","version":"InCoder","score":12.2},{"place":877,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":12.2},{"place":878,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":12.2},{"place":879,"model":"qwen1.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":12.2},{"place":880,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":11.6},{"place":881,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":11.6},{"place":882,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":11.6},{"place":883,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":11.59},{"place":884,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":11.59},{"place":885,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":11.59},{"place":886,"model":"codegen2-1b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":11},{"place":887,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":11},{"place":888,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":11},{"place":889,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":10.4},{"place":890,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":10.4},{"place":891,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":10.4},{"place":892,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":10.37},{"place":893,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":9.8},{"place":894,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":9.2},{"place":895,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":9.2},{"place":896,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":9.2},{"place":897,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":9.15},{"place":898,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":9.1},{"place":899,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":9.1},{"place":900,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":8.5},{"place":901,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":8.5},{"place":902,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":7.93},{"place":903,"model":"gpt-neo-2.7b","company":"openai","family":"GPT","version":"GPT-Neo","score":7.9},{"place":904,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":6.71},{"place":905,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":6.7},{"place":906,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":6.7},{"place":907,"model":"polycoder-2.7b","company":"cmu","family":"PolyCoder-2.7B","version":"PolyCoder-2.7B","score":6.1},{"place":908,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":5.49},{"place":909,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":4.3},{"place":910,"model":"stablelm-7b","company":"stabilityai","family":"StableLM-7B","version":"StableLM-7B","score":2.4},{"place":911,"model":"zyte-1b","company":"zysecai","family":"Zyte","version":"Zyte","score":2.4},{"place":912,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1.2},{"place":913,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":914,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":0},{"place":915,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":0}]},{"id":"humaneval-fim","name":"HumanEval-FIM","topic":"Code infilling","description":"Fill-in-the-middle variant of HumanEval measuring code infilling.","url":"https://github.com/openai/human-eval-infilling","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2207.14255","metric":"percent","stars":"","top_model":"Codestral 22B","top_percent":91.6,"top_model_id":"codestral-22b","top_generation":"Codestral","top_model_base":"Codestral 22B","top_model_family":"Codestral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":91.6},{"place":2,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":85},{"place":3,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":78.2}]},{"id":"humaneval-plus","name":"HumanEval+","topic":"Code generation","description":"Extended HumanEval with more tests.","url":"https://github.com/evalplus/evalplus","leaderboard":"","github":"","paper":"","metric":"percent","stars":"1577","top_model":"Qwen3.8-27B-UD-Q4_K_XL","top_percent":95.73,"top_model_id":"qwen3.8-27b-ud-q4-k-xl","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 27B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":439,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":95.73},{"place":2,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":95.7},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":95.12},{"place":4,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":95.12},{"place":5,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":94.7},{"place":6,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.7},{"place":7,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":94.51},{"place":8,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":94.5},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":94.5},{"place":10,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":94.48},{"place":11,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":94.1},{"place":12,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":93.9},{"place":13,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":93.3},{"place":14,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.3},{"place":15,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":93.3},{"place":16,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":93.3},{"place":17,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":93.3},{"place":18,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93.29},{"place":19,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":92.9},{"place":20,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.8},{"place":21,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":92.8},{"place":22,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":92.7},{"place":23,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":92.7},{"place":24,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":92.7},{"place":25,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":92.7},{"place":26,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":92.7},{"place":27,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.4},{"place":28,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":92.3},{"place":29,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.2},{"place":30,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":92.1},{"place":31,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":92.1},{"place":32,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":92.1},{"place":33,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":91.8},{"place":34,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":91.6},{"place":35,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":91.6},{"place":36,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":91.5},{"place":37,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":91.5},{"place":38,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":91.5},{"place":39,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":91.5},{"place":40,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.46},{"place":41,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":91.4},{"place":42,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":91.4},{"place":43,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":91.2},{"place":44,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":91.2},{"place":45,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":90.9},{"place":46,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.8},{"place":47,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.8},{"place":48,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.6},{"place":49,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":90.3},{"place":50,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":90.2},{"place":51,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":90.2},{"place":52,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":90},{"place":53,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":90},{"place":54,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":89.9},{"place":55,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":89.88},{"place":56,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.7},{"place":57,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":89.7},{"place":58,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":89.7},{"place":59,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":89.63},{"place":60,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":89.63},{"place":61,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":89.63},{"place":62,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89.6},{"place":63,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.6},{"place":64,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.6},{"place":65,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.6},{"place":66,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":89.5},{"place":67,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.3},{"place":68,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":89.1},{"place":69,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":89},{"place":70,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":89},{"place":71,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":89},{"place":72,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":89},{"place":73,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":89},{"place":74,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":89},{"place":75,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":89},{"place":76,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":88.5},{"place":77,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":88.41},{"place":78,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":88.4},{"place":79,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.4},{"place":80,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":88.4},{"place":81,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":88.4},{"place":82,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":88.2},{"place":83,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":88.17},{"place":84,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":88},{"place":85,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":87.9},{"place":86,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.88},{"place":87,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":87.8},{"place":88,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.8},{"place":89,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":87.58},{"place":90,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":87.4},{"place":91,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":87.3},{"place":92,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.2},{"place":93,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":87.2},{"place":94,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":87.2},{"place":95,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.2},{"place":96,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.2},{"place":97,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":86.9},{"place":98,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":86.77},{"place":99,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":86.7},{"place":100,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":86.6},{"place":101,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":86.6},{"place":102,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.6},{"place":103,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":86.6},{"place":104,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.6},{"place":105,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.59},{"place":106,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":86.52},{"place":107,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":86.46},{"place":108,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":86.3},{"place":109,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":86.09},{"place":110,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":86},{"place":111,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":86},{"place":112,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":86},{"place":113,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":85.98},{"place":114,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":85.9},{"place":115,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":85.79},{"place":116,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":85.72},{"place":117,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":85.7},{"place":118,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":85.5},{"place":119,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.37},{"place":120,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":85.37},{"place":121,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.3},{"place":122,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":84.8},{"place":123,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":84.8},{"place":124,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":84.8},{"place":125,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":84.2},{"place":126,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.1},{"place":127,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.9},{"place":128,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.7},{"place":129,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":83.54},{"place":130,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":83.54},{"place":131,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":83.5},{"place":132,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":83.5},{"place":133,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":83.5},{"place":134,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":83},{"place":135,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":83},{"place":136,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":82.93},{"place":137,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":82.9},{"place":138,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.9},{"place":139,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.6},{"place":140,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":82.5},{"place":141,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.32},{"place":142,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.32},{"place":143,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":82.3},{"place":144,"model":"stable-diffcoder-8b-instruct","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":82.3},{"place":145,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":81.71},{"place":146,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":81.71},{"place":147,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81.7},{"place":148,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":81.7},{"place":149,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.7},{"place":150,"model":"gpt-oss-20b-moe","company":"openai","family":"GPT","version":"GPT-OSS","score":81.7},{"place":151,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.7},{"place":152,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":81.7},{"place":153,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":81.7},{"place":154,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81.7},{"place":155,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":81.7},{"place":156,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":81.4},{"place":157,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":81.1},{"place":158,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":81.1},{"place":159,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":81.1},{"place":160,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":81.1},{"place":161,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81.1},{"place":162,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":80.8},{"place":163,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.56},{"place":164,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":80.5},{"place":165,"model":"grok-beta","company":"xai","family":"Grok","version":"Grok","score":80.5},{"place":166,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":80.5},{"place":167,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.49},{"place":168,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":80.49},{"place":169,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":80.49},{"place":170,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.2},{"place":171,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":80.03},{"place":172,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":79.9},{"place":173,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":79.9},{"place":174,"model":"k2-horizon-0.9b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":79.9},{"place":175,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":79.88},{"place":176,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":79.88},{"place":177,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":79.88},{"place":178,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":79.87},{"place":179,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.8},{"place":180,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79.5},{"place":181,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":79.3},{"place":182,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":79.3},{"place":183,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.3},{"place":184,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":79.3},{"place":185,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.27},{"place":186,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":79.27},{"place":187,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":79.27},{"place":188,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":79.2},{"place":189,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":79.2},{"place":190,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":78.84},{"place":191,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":78.7},{"place":192,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":78.7},{"place":193,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":78.7},{"place":194,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":78.6},{"place":195,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":78.43},{"place":196,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":78.33},{"place":197,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":78.05},{"place":198,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.05},{"place":199,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":78.05},{"place":200,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":78},{"place":201,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.56},{"place":202,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":77.4},{"place":203,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":77.4},{"place":204,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":77.4},{"place":205,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.2},{"place":206,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":76.83},{"place":207,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":76.83},{"place":208,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":76.8},{"place":209,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":76.22},{"place":210,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":76.22},{"place":211,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":76.2},{"place":212,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":75.68},{"place":213,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":75.61},{"place":214,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":75.6},{"place":215,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":75.6},{"place":216,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":75.6},{"place":217,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":75.6},{"place":218,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":75.6},{"place":219,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.6},{"place":220,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":75.6},{"place":221,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.3},{"place":222,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":75.26},{"place":223,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":75.1},{"place":224,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":75},{"place":225,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":75},{"place":226,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":75},{"place":227,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":75},{"place":228,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.9},{"place":229,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":74.7},{"place":230,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":74.4},{"place":231,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.4},{"place":232,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":74},{"place":233,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":73.8},{"place":234,"model":"opencodeinterpreter-ds-33b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":73.8},{"place":235,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":73.8},{"place":236,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":73.78},{"place":237,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.78},{"place":238,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":73.78},{"place":239,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":73.39},{"place":240,"model":"wizardcoder-33b-v1.1","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.1","score":73.2},{"place":241,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":73.2},{"place":242,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":72.9},{"place":243,"model":"artigenz-coder-ds-6.7b","company":"artigenz","family":"Artigenz-Coder-DS-6.7B","version":"Artigenz Coder DS","score":72.6},{"place":244,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":72},{"place":245,"model":"opencodeinterpreter-ds-6.7b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":72},{"place":246,"model":"speechless-codellama-34b-v2.0","company":"speechless","family":"speechless-codellama-34B-v2.0","version":"speechless-codellama-34B-v2.0","score":72},{"place":247,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":72},{"place":248,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":72},{"place":249,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":72},{"place":250,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.95},{"place":251,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":71.3},{"place":252,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":71.3},{"place":253,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":71.3},{"place":254,"model":"starchat2-15b-v0.1","company":"huggingface","family":"starchat2-15b-v0.1","version":"starchat2-15b-v0.1","score":71.3},{"place":255,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":71.3},{"place":256,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":70.9},{"place":257,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":70.73},{"place":258,"model":"gpt-3.5-turbo-nov-2023","company":"openai","family":"GPT","version":"GPT-3.5","score":70.7},{"place":259,"model":"code-millenials-34b","company":"code","family":"code-millenials-34B","version":"code-millenials-34B","score":70.7},{"place":260,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.7},{"place":261,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":70.7},{"place":262,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":70.7},{"place":263,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":70.7},{"place":264,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":70.7},{"place":265,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.6},{"place":266,"model":"databricks-dbrx-instruct","company":"databricks","family":"databricks/dbrx-instruct","version":"databricks/dbrx-instruct","score":70.1},{"place":267,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":70.1},{"place":268,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":70.1},{"place":269,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.8},{"place":270,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":69.51},{"place":271,"model":"wavecoder-ultra-6.7b","company":"wavecoder","family":"WaveCoder-Ultra-6.7B","version":"WaveCoder-Ultra-6.7B","score":69.5},{"place":272,"model":"xwincoder-34b","company":"xwin","family":"XwinCoder-34B","version":"XwinCoder-34B","score":69.5},{"place":273,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":69.2},{"place":274,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":69.1},{"place":275,"model":"claude-3-haiku-mar-2024","company":"anthropic","family":"claude-3-haiku","version":"claude-3-haiku (Mar 2024)","score":68.9},{"place":276,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":68.9},{"place":277,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":68.9},{"place":278,"model":"codestral-12b-instruct","company":"mistral","family":"Codestral","version":"Codestral","score":68.3},{"place":279,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":68.3},{"place":280,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.29},{"place":281,"model":"magicoder-s-cl-7b","company":"magicoder","family":"Magicoder-S-CL-7B","version":"Magicoder-S-CL-7B","score":67.7},{"place":282,"model":"openchat-3.5-7b-0106","company":"openchat","family":"OpenChat-3.5-7B-0106","version":"OpenChat-3.5-7B-0106","score":67.7},{"place":283,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.7},{"place":284,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.7},{"place":285,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":67.7},{"place":286,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":67.5},{"place":287,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":67.4},{"place":288,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":67.1},{"place":289,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":67.1},{"place":290,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":67},{"place":291,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":66.77},{"place":292,"model":"gpt-3.5-may-2023","company":"openai","family":"GPT","version":"GPT-3.5","score":66.5},{"place":293,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":66.5},{"place":294,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.5},{"place":295,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.5},{"place":296,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":65.9},{"place":297,"model":"whiterabbitneo-33b-v1","company":"whiterabbit","family":"WhiteRabbitNeo-33B-v1","version":"WhiteRabbitNeo-33B-v1","score":65.9},{"place":298,"model":"speechless-coder-ds-6.7b","company":"speechless","family":"speechless-coder-ds-6.7B","version":"speechless-coder-ds-6.7B","score":65.9},{"place":299,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":65.85},{"place":300,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":65.7},{"place":301,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":65.2},{"place":302,"model":"diffucoder-7b-instruct","company":"apple","family":"DiffuCoder","version":"DiffuCoder","score":65.2},{"place":303,"model":"wizardcoder-python-34b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":64.6},{"place":304,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":64.6},{"place":305,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":64.6},{"place":306,"model":"claude-3-sonnet-mar-2024","company":"anthropic","family":"claude-3-sonnet","version":"claude-3-sonnet (Mar 2024)","score":64},{"place":307,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":64},{"place":308,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":64},{"place":309,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":64},{"place":310,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":62.91},{"place":311,"model":"speechless-starcoder2-15b","company":"bigcode","family":"speechless-starcoder2-15b","version":"speechless-starcoder2-15b","score":62.8},{"place":312,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":62.8},{"place":313,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":62.8},{"place":314,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62.32},{"place":315,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":62.2},{"place":316,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.2},{"place":317,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":62.2},{"place":318,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":61.6},{"place":319,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":61.6},{"place":320,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":61.59},{"place":321,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":61.59},{"place":322,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":61.59},{"place":323,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":61},{"place":324,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.98},{"place":325,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.96},{"place":326,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.4},{"place":327,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":60.4},{"place":328,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.4},{"place":329,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":60.4},{"place":330,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":60.37},{"place":331,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.8},{"place":332,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.8},{"place":333,"model":"code-290k-6.7b-instruct","company":"code","family":"Code","version":"Code 290k","score":59.7},{"place":334,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.5},{"place":335,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":59.1},{"place":336,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":59.1},{"place":337,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":57.93},{"place":338,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":57.9},{"place":339,"model":"dolphin-2.6-mixtral-8x7b","company":"mistral","family":"dolphin-2.6-mixtral-8x7b","version":"dolphin-2.6-mixtral-8x7b","score":57.3},{"place":340,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":57.3},{"place":341,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":57.3},{"place":342,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":56.7},{"place":343,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":56.7},{"place":344,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":56.7},{"place":345,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":56.1},{"place":346,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.8},{"place":347,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":55.5},{"place":348,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":53.7},{"place":349,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":53},{"place":350,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.44},{"place":351,"model":"code-13b","company":"code","family":"Code-13B","version":"Code-13B","score":52.4},{"place":352,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52.4},{"place":353,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":52.1},{"place":354,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":51.83},{"place":355,"model":"codegemma-7b-it","company":"google","family":"Codegemma","version":"Codegemma","score":51.8},{"place":356,"model":"speechless-starcoder2-7b","company":"bigcode","family":"speechless-starcoder2-7b","version":"speechless-starcoder2-7b","score":51.8},{"place":357,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":51.2},{"place":358,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":51.2},{"place":359,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.61},{"place":360,"model":"codellama-70b","company":"meta","family":"CodeLlama","version":"CodeLlama","score":50.6},{"place":361,"model":"wizardcoder-15b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":50.6},{"place":362,"model":"claude-instant-1-mar-2024","company":"anthropic","family":"claude-instant-1","version":"claude-instant-1 (Mar 2024)","score":50.6},{"place":363,"model":"speechless-coding-7b-16k-tora","company":"speechless","family":"speechless-coding-7B-16k-tora","version":"speechless-coding-7B-16k-tora","score":50.6},{"place":364,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.6},{"place":365,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":50},{"place":366,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":50},{"place":367,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":50},{"place":368,"model":"code-33b","company":"code","family":"Code-33B","version":"Code-33B","score":49.4},{"place":369,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.39},{"place":370,"model":"openhermes-2.5-code-290k-13b","company":"openhermes","family":"OpenHermes-2.5-Code-290k-13B","version":"OpenHermes-2.5-Code-290k-13B","score":48.8},{"place":371,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.78},{"place":372,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.35},{"place":373,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":48},{"place":374,"model":"coda-1.7b-instruct","company":"salesforce","family":"CoDA","version":"CoDA","score":47.6},{"place":375,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":47.6},{"place":376,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.3},{"place":377,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":46.3},{"place":378,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":46.3},{"place":379,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":46.3},{"place":380,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":45.73},{"place":381,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":45.7},{"place":382,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":45.12},{"place":383,"model":"wizardcoder-python-7b-v1.0","company":"microsoft","family":"WizardCoder-Python-7B-V1.0","version":"WizardCoder-Python-7B-V1.0","score":45.1},{"place":384,"model":"phi-2-2.7b","company":"microsoft","family":"phi-2-2.7B","version":"phi-2-2.7B","score":45.1},{"place":385,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":45.1},{"place":386,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":44.76},{"place":387,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":44.5},{"place":388,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":44.5},{"place":389,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":44.5},{"place":390,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":44.4},{"place":391,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":43.9},{"place":392,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":43.3},{"place":393,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":43.3},{"place":394,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":42.9},{"place":395,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":42.7},{"place":396,"model":"mistral-codealpaca-7b","company":"mistral","family":"Mistral","version":"Mistral Codealpaca","score":42.1},{"place":397,"model":"mistralhermes-codepro-7b-v1","company":"mistral","family":"MistralHermes","version":"MistralHermes CodePro v1","score":42.1},{"place":398,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":42.1},{"place":399,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":41.6},{"place":400,"model":"codegemma-7b","company":"google","family":"Codegemma","version":"codegemma-7b","score":41.5},{"place":401,"model":"speechless-code-mistral-7b-v1.0","company":"speechless","family":"speechless-code-mistral-7B-v1.0","version":"speechless-code-mistral-7B-v1.0","score":41.5},{"place":402,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":40.2},{"place":403,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":40.2},{"place":404,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":40.2},{"place":405,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":40.2},{"place":406,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":40.2},{"place":407,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.6},{"place":408,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":39.6},{"place":409,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":39},{"place":410,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":38.4},{"place":411,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":38.4},{"place":412,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":37.8},{"place":413,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":37.8},{"place":414,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":37.8},{"place":415,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":37.2},{"place":416,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":37.2},{"place":417,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":37.2},{"place":418,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.19},{"place":419,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":36.6},{"place":420,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":36},{"place":421,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36},{"place":422,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":35.4},{"place":423,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":35.4},{"place":424,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":35.4},{"place":425,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.9},{"place":426,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":34.8},{"place":427,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":34.4},{"place":428,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":34.1},{"place":429,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":34.1},{"place":430,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":34.1},{"place":431,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":33.5},{"place":432,"model":"xdan-l1-chat-rl-v1-7b","company":"xdan","family":"xDAN-L1-Chat-RL-v1-7B","version":"xDAN-L1-Chat-RL-v1-7B","score":32.9},{"place":433,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.9},{"place":434,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":32.5},{"place":435,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.32},{"place":436,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":32.3},{"place":437,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":31.7},{"place":438,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":31.7},{"place":439,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":31.7},{"place":440,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":31.7},{"place":441,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":31.1},{"place":442,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":31.1},{"place":443,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":31.1},{"place":444,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":31},{"place":445,"model":"python-code-13b","company":"python","family":"Python-Code-13B","version":"Python-Code-13B","score":30.5},{"place":446,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":30.5},{"place":447,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":29.9},{"place":448,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":29.9},{"place":449,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":29.88},{"place":450,"model":"starcoder-15b","company":"bigcode","family":"StarCoder-15B","version":"StarCoder","score":29.3},{"place":451,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.3},{"place":452,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":29.3},{"place":453,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":29.3},{"place":454,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":28.7},{"place":455,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":28.7},{"place":456,"model":"codegen-16b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":28},{"place":457,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":28},{"place":458,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":27.4},{"place":459,"model":"codet5-16b","company":"salesforce","family":"CodeT5+-16B","version":"CodeT5+-16B","score":26.8},{"place":460,"model":"codet5plus-16b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":26.8},{"place":461,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.8},{"place":462,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":26.8},{"place":463,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":26.2},{"place":464,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":25.8},{"place":465,"model":"codegen-6b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":25.6},{"place":466,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":25.6},{"place":467,"model":"stablecode-3b","company":"stability","family":"StableCode","version":"StableCode","score":25.6},{"place":468,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":25.6},{"place":469,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":25},{"place":470,"model":"codet5-6b","company":"salesforce","family":"CodeT5+-6B","version":"CodeT5+-6B","score":24.4},{"place":471,"model":"codet5plus-6b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":24.4},{"place":472,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":24.4},{"place":473,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":24.06},{"place":474,"model":"coda-1.7b-base","company":"salesforce","family":"CoDA","version":"CoDA","score":23.8},{"place":475,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":23.8},{"place":476,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":23.8},{"place":477,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":23.2},{"place":478,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":23.2},{"place":479,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":23.17},{"place":480,"model":"codegen-2b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":22.6},{"place":481,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":22.6},{"place":482,"model":"codet5-2b","company":"salesforce","family":"CodeT5+-2B","version":"CodeT5+-2B","score":22},{"place":483,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":22},{"place":484,"model":"starcoderbase-7b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":21.3},{"place":485,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":20.98},{"place":486,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":20.73},{"place":487,"model":"codegemma-2b","company":"google","family":"Codegemma","version":"codegemma-2b","score":20.7},{"place":488,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":20.7},{"place":489,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":20.1},{"place":490,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":18.9},{"place":491,"model":"codegen2-7b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":17.7},{"place":492,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":17.7},{"place":493,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":17.4},{"place":494,"model":"codegen2-16b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":16.5},{"place":495,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":16.5},{"place":496,"model":"starcoderbase-3b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":15.9},{"place":497,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":15.9},{"place":498,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":15.9},{"place":499,"model":"gemma-2b-it","company":"google","family":"Gemma","version":"Gemma","score":15.2},{"place":500,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":15.2},{"place":501,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":14.5},{"place":502,"model":"santacoder-1.1b","company":"bigcode","family":"SantaCoder","version":"SantaCoder","score":14},{"place":503,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":14},{"place":504,"model":"codegen2-3b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":12.8},{"place":505,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":12.8},{"place":506,"model":"incoder-6.7b","company":"ai21","family":"InCoder","version":"InCoder","score":12.2},{"place":507,"model":"starcoderbase-1b","company":"bigcode","family":"StarCoder","version":"StarCoderBase","score":12.2},{"place":508,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":12.2},{"place":509,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":12.2},{"place":510,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":11.6},{"place":511,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":11.6},{"place":512,"model":"gpt-j-6b","company":"openai","family":"GPT","version":"GPT-J","score":11},{"place":513,"model":"incoder-1.3b","company":"ai21","family":"InCoder","version":"InCoder","score":11},{"place":514,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":9.8},{"place":515,"model":"codegen2-1b","company":"salesforce","family":"CodeGen","version":"CodeGen2","score":9.1},{"place":516,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":8.5},{"place":517,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":7.3},{"place":518,"model":"gpt-neo-2.7b","company":"openai","family":"GPT","version":"GPT-Neo","score":6.7},{"place":519,"model":"polycoder-2.7b","company":"cmu","family":"PolyCoder-2.7B","version":"PolyCoder-2.7B","score":6.1},{"place":520,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":5.5},{"place":521,"model":"stablelm-7b","company":"stabilityai","family":"StableLM-7B","version":"StableLM-7B","score":2.4},{"place":522,"model":"zyte-1b","company":"zysecai","family":"Zyte","version":"Zyte","score":1.8}]},{"id":"humaneval-v","name":"HumanEval-V","topic":"Code generation (vision)","description":"HumanEval variant with visual programming prompts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Step3-VL-10B","top_percent":66.05,"top_model_id":"step3-vl-10b","top_generation":"Step3-VL","top_model_base":"Step3-VL 10B","top_model_family":"Step","top_company":"stepfun","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":66.05},{"place":2,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":31.96},{"place":3,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":29.26},{"place":4,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.94},{"place":5,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":24.31}]},{"id":"humaneval-x","name":"HumanEval-X","topic":"Code generation (multilingual)","description":"Multilingual code generation benchmark extending HumanEval to multiple programming languages.","url":"https://github.com/THUDM/CodeGeeX","leaderboard":"","github":"https://github.com/THUDM/CodeGeeX","paper":"","metric":"percent","stars":"","top_model":"TeleChat3-36B-Thinking","top_percent":92.67,"top_model_id":"telechat3-36b-thinking","top_generation":"TeleChat3","top_model_base":"TeleChat3 36B","top_model_family":"TeleChat","top_company":"teleai","top_open_source":1,"lower_is_better":false,"bench_models":58,"total_models":3854,"placements":[{"place":1,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":92.67},{"place":2,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":91.7},{"place":3,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":89.76},{"place":4,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.9},{"place":5,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":88.9},{"place":6,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.29},{"place":7,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":87.3},{"place":8,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.88},{"place":9,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.3},{"place":10,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":82.6},{"place":11,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81.7},{"place":12,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":80.5},{"place":13,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":77.4},{"place":14,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77.3},{"place":15,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":77.2},{"place":16,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":76.5},{"place":17,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":76.1},{"place":18,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":74.8},{"place":19,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":73.8},{"place":20,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":73.8},{"place":21,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":69.3},{"place":22,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":69.2},{"place":23,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":67.44},{"place":24,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":66.1},{"place":25,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":64.9},{"place":26,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":50.3},{"place":27,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":48.4},{"place":28,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":48.2},{"place":29,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":44.7},{"place":30,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":43.9},{"place":31,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":42},{"place":32,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":41.7},{"place":33,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":41},{"place":34,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":39.8},{"place":35,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":39.6},{"place":36,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":38.3},{"place":37,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":38.3},{"place":38,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":38.3},{"place":39,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":35.4},{"place":40,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":31.5},{"place":41,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":31},{"place":42,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":29.9},{"place":43,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":29.2},{"place":44,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":28.8},{"place":45,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":28.5},{"place":46,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.3},{"place":47,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":28},{"place":48,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":27.1},{"place":49,"model":"codegeex2-6b","company":"zai","family":"CodeGeeX","version":"CodeGeeX2","score":24.5},{"place":50,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":24.4},{"place":51,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":19.5},{"place":52,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":18.3},{"place":53,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":17.6},{"place":54,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":17.2},{"place":55,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":16.1},{"place":56,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":15.4},{"place":57,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":12.9},{"place":58,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":11.2},{"place":59,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":10.6}]},{"id":"humanref","name":"HumanRef","topic":"Referring expressions","description":"Referring detection of people in images (HumanRef), F1 mean.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":80.7,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":80.7},{"place":2,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":79.9},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":78.7},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.8},{"place":5,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":77.4},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.6}]},{"id":"humicroedit-decision","name":"Humicroedit (decision)","topic":"Humor judgement","description":"Pick the funnier micro-edited headline; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://www.cs.rochester.edu/u/nhossain/humicroedit.html","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Clef-Flash","top_percent":75.1,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":75.1},{"place":2,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":70.1},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":66.7},{"place":4,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":65.8},{"place":5,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":63.7},{"place":6,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":63.6},{"place":7,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":63},{"place":8,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":63},{"place":9,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":62},{"place":10,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":61.9},{"place":11,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":61.8},{"place":12,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":61.6},{"place":13,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":61.6},{"place":14,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":61.6},{"place":15,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":61.6},{"place":16,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":61.2},{"place":17,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61},{"place":18,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":60.8},{"place":19,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":60.6},{"place":20,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":60.5},{"place":21,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":60.5},{"place":22,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":59.7},{"place":23,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":58.6},{"place":24,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":58.3},{"place":25,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":57.8},{"place":26,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":57.5},{"place":27,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":57.3},{"place":28,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":55.8},{"place":29,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":55.3},{"place":30,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":54.5},{"place":31,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":53.7},{"place":32,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":53.3},{"place":33,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":51.3},{"place":34,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":51.1},{"place":35,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":50.6},{"place":36,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":49.7},{"place":37,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":49.5},{"place":38,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":47.2}]},{"id":"hungarian-math-exam","name":"Hungarian National HS Math Exam","topic":"Math (held-out exam)","description":"Hungarian national high-school mathematics finals (2023) graded by humans; held-out math reasoning test.","url":"https://huggingface.co/datasets/keirp/hungarian_national_hs_finals_exam","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-4","top_percent":68,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":68},{"place":2,"model":"internlm2-math-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":66},{"place":3,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":58},{"place":4,"model":"internlm2-math-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":55},{"place":5,"model":"qwen-72b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":52},{"place":6,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":41},{"place":7,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":39},{"place":8,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":32},{"place":9,"model":"metamath-mistral-7b","company":"metamath","family":"MetaMath","version":"MetaMath","score":29},{"place":10,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":28.5},{"place":11,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":19.5},{"place":12,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":19}]},{"id":"hybridial","name":"HybriDial","topic":"Conversational QA","description":"Hybrid table+text grounded dialogue QA (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":72.9,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":72.9},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":51.1},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":48.9},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":48.2},{"place":5,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":47.4},{"place":6,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":45.4},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":45.3},{"place":8,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":41.3},{"place":9,"model":"o3","company":"openai","family":"o3","version":"o3","score":41.3},{"place":10,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":38}]},{"id":"hypersim","name":"Hypersim","topic":"3D scene understanding","description":"Hypersim benchmark for synthetic indoor scene understanding and reconstruction.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 Mini (minimal)","top_percent":39.3,"top_model_id":"gpt-5-mini-minimal","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":39.3},{"place":2,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":39.3},{"place":3,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":34.7},{"place":4,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":14},{"place":5,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.5},{"place":6,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.1},{"place":7,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13},{"place":8,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":12.7},{"place":9,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12.7},{"place":10,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":12.5},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12.5},{"place":12,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12.5},{"place":13,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12.4},{"place":14,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":12.2},{"place":15,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":12},{"place":16,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":11.9},{"place":17,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":11.9},{"place":18,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":11.4},{"place":19,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":11.2},{"place":20,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":11},{"place":21,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":11},{"place":22,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":9.4},{"place":23,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.2}]},{"id":"icdar2015-f1","name":"ICDAR2015 (F1)","topic":"OCR","description":"ICDAR2015 text grounding and recognition, F1 mean.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":47.8,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":47.8},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":42.6},{"place":3,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":28.1},{"place":4,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":27.1},{"place":5,"model":"pp-ocrv5","company":"paddlepaddle","family":"PP-OCR","version":"PP-OCRv5","score":25.6},{"place":6,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":24.1}]},{"id":"ifbench","name":"IFBench","topic":"Instruction following","description":"Instruction-following benchmark measuring compliance and adherence.","url":"https://github.com/allenai/IFBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"70","top_model":"Flint","top_percent":89.2,"top_model_id":"flint","top_generation":"Flint","top_model_base":"Flint","top_model_family":"Flint","top_company":"recursive","top_open_source":1,"lower_is_better":false,"bench_models":380,"total_models":3854,"placements":[{"place":1,"model":"flint","company":"recursive","family":"Flint","version":"Flint","score":89.2},{"place":2,"model":"flint-nvfp4","company":"recursive","family":"Flint","version":"Flint","score":88.1},{"place":3,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":84.78},{"place":4,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":84.2},{"place":5,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.9},{"place":6,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":82.9},{"place":7,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":82.9},{"place":8,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.8},{"place":9,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":82.75},{"place":10,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.4},{"place":11,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":82.2},{"place":12,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82},{"place":13,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":81.7},{"place":14,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":81.6},{"place":15,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":81.5},{"place":16,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":81.4},{"place":17,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.3},{"place":18,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":80.9},{"place":19,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":80.87},{"place":20,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":80.61},{"place":21,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":80.6},{"place":22,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":80.4},{"place":23,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.3},{"place":24,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":80.2},{"place":25,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":80},{"place":26,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":79.9},{"place":27,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":79.8},{"place":28,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":79.7},{"place":29,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":79.6},{"place":30,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":79.6},{"place":31,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":79.5},{"place":32,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":79.33},{"place":33,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":79.3},{"place":34,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79.2},{"place":35,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79.2},{"place":36,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79.2},{"place":37,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":79.1},{"place":38,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":79.1},{"place":39,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79.1},{"place":40,"model":"nemotron-labs-dory1.0-4b-4loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":79},{"place":41,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.8},{"place":42,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.7},{"place":43,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":78.7},{"place":44,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":78.67},{"place":45,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":78.6},{"place":46,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.2},{"place":47,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":78.2},{"place":48,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":49,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":78},{"place":50,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":78},{"place":51,"model":"nemotron-labs-dory1.0-4b","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":77.94},{"place":52,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.89},{"place":53,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.74},{"place":54,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.67},{"place":55,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.25},{"place":56,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":77.17},{"place":57,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":77.1},{"place":58,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77},{"place":59,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":77},{"place":60,"model":"mercury-2.5","company":"inception","family":"Mercury","version":"Mercury 2.5","score":77},{"place":61,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":76.84},{"place":62,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":76.6},{"place":63,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.5},{"place":64,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.5},{"place":65,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.5},{"place":66,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.5},{"place":67,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":76.5},{"place":68,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":76.3},{"place":69,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":76.3},{"place":70,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.2},{"place":71,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.15},{"place":72,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.1},{"place":73,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":76},{"place":74,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":76},{"place":75,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76},{"place":76,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":76},{"place":77,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":75.9},{"place":78,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":75.9},{"place":79,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.8},{"place":80,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":75.8},{"place":81,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":75.7},{"place":82,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.6},{"place":83,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.6},{"place":84,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":75.4},{"place":85,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":75.4},{"place":86,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":75.4},{"place":87,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":75},{"place":88,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":75},{"place":89,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":75},{"place":90,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":74.69},{"place":91,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":74.6},{"place":92,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":74.6},{"place":93,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":74.5},{"place":94,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":74.5},{"place":95,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":74.33},{"place":96,"model":"nemotron-labs-dory1.0-4b-1loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":74.29},{"place":97,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.2},{"place":98,"model":"agnes-3.0-flash-preview","company":"agnes","family":"Agnes","version":"Agnes 3.0","score":74.2},{"place":99,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":74},{"place":100,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":74},{"place":101,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":74},{"place":102,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":73.9},{"place":103,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":73.9},{"place":104,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.77},{"place":105,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":73.7},{"place":106,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.5},{"place":107,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.47},{"place":108,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.4},{"place":109,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":73.33},{"place":110,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":73.3},{"place":111,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":73.1},{"place":112,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":73.1},{"place":113,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":73},{"place":114,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":72.9},{"place":115,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":72.7},{"place":116,"model":"underdog-saluki-27b-1.0","company":"conwayresearch","family":"Underdog","version":"Underdog 1.0","score":72.7},{"place":117,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.67},{"place":118,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.6},{"place":119,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":72.6},{"place":120,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.56},{"place":121,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.31},{"place":122,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":72.3},{"place":123,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.17},{"place":124,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":72.1},{"place":125,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":72},{"place":126,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":72},{"place":127,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.92},{"place":128,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.9},{"place":129,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.88},{"place":130,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":71.77},{"place":131,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.67},{"place":132,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.5},{"place":133,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.5},{"place":134,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.5},{"place":135,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":71.47},{"place":136,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":71.2},{"place":137,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":71},{"place":138,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":71},{"place":139,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":71},{"place":140,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.9},{"place":141,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.9},{"place":142,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.86},{"place":143,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70.82},{"place":144,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":70.8},{"place":145,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":70.8},{"place":146,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":70.8},{"place":147,"model":"pulsar-16b","company":"multiverse","family":"Pulsar","version":"Pulsar","score":70.79},{"place":148,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":70.7},{"place":149,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":70.7},{"place":150,"model":"nemotron-labs-3-elastic-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70.58},{"place":151,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.4},{"place":152,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":70.4},{"place":153,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":70.2},{"place":154,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.2},{"place":155,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":70.2},{"place":156,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":70.1},{"place":157,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":70.07},{"place":158,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":70},{"place":159,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70},{"place":160,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":70},{"place":161,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":69.7},{"place":162,"model":"xing4.0-29b-a4b","company":"teleai","family":"Xing","version":"Xing4.0","score":69.67},{"place":163,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":69.5},{"place":164,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":69.5},{"place":165,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":69.4},{"place":166,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":69.3},{"place":167,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":69.1},{"place":168,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":69.1},{"place":169,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":69},{"place":170,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":69},{"place":171,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":69},{"place":172,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":69},{"place":173,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":69},{"place":174,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":69},{"place":175,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":69},{"place":176,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":68.7},{"place":177,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":68.5},{"place":178,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":68.46},{"place":179,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":68.32},{"place":180,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":68.1},{"place":181,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.9},{"place":182,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.6},{"place":183,"model":"mercury-voice","company":"inception","family":"Mercury","version":"Mercury 2.5","score":67.4},{"place":184,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":67.3},{"place":185,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":67.3},{"place":186,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":67.3},{"place":187,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":67.1},{"place":188,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":67},{"place":189,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":67},{"place":190,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":67},{"place":191,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.7},{"place":192,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.67},{"place":193,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":66.6},{"place":194,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":66.6},{"place":195,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.33},{"place":196,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":66.33},{"place":197,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":66.3},{"place":198,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":66.3},{"place":199,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":66.21},{"place":200,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":66},{"place":201,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":65.72},{"place":202,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.65},{"place":203,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":65.6},{"place":204,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":65.5},{"place":205,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":65.33},{"place":206,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":65.3},{"place":207,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":65.1},{"place":208,"model":"gpt-oss-20b-a4b","company":"openai","family":"GPT","version":"GPT-OSS","score":65},{"place":209,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":65},{"place":210,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":65},{"place":211,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":64.6},{"place":212,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.5},{"place":213,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64.4},{"place":214,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64.21},{"place":215,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":64.2},{"place":216,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":64},{"place":217,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":63.79},{"place":218,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.71},{"place":219,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":63.61},{"place":220,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.52},{"place":221,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.5},{"place":222,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":63.33},{"place":223,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":63.3},{"place":224,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":63.2},{"place":225,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":63.1},{"place":226,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":62.9},{"place":227,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":62.6},{"place":228,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.5},{"place":229,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":62.5},{"place":230,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":62.2},{"place":231,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":62},{"place":232,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":61.82},{"place":233,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":61.7},{"place":234,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":61.5},{"place":235,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":61.2},{"place":236,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":61},{"place":237,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":60.7},{"place":238,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60.7},{"place":239,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60.7},{"place":240,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":60.5},{"place":241,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":60.45},{"place":242,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.33},{"place":243,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60.1},{"place":244,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":59.5},{"place":245,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":59.4},{"place":246,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.2},{"place":247,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.2},{"place":248,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":59.17},{"place":249,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":59},{"place":250,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":251,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":252,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.91},{"place":253,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.7},{"place":254,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":58.65},{"place":255,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":58.58},{"place":256,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":58.3},{"place":257,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":58.3},{"place":258,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58},{"place":259,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":57.7},{"place":260,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":57.7},{"place":261,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":57.62},{"place":262,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57.44},{"place":263,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":57.4},{"place":264,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.3},{"place":265,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":57.14},{"place":266,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":57.1},{"place":267,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":57},{"place":268,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57},{"place":269,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57},{"place":270,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":56.71},{"place":271,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":56.6},{"place":272,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":56.47},{"place":273,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.47},{"place":274,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":55.8},{"place":275,"model":"solar-pro-3","company":"upstage","family":"Solar","version":"Solar Pro 3","score":55.78},{"place":276,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":55.4},{"place":277,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.4},{"place":278,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.1},{"place":279,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":55},{"place":280,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":54.7},{"place":281,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":54.65},{"place":282,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":54.6},{"place":283,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":54.4},{"place":284,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.33},{"place":285,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.3},{"place":286,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.1},{"place":287,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.1},{"place":288,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":54.1},{"place":289,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":54.08},{"place":290,"model":"claude-4.5-haiku-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54},{"place":291,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.83},{"place":292,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":53.76},{"place":293,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":53.7},{"place":294,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":53.7},{"place":295,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":53.4},{"place":296,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":53.4},{"place":297,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53.1},{"place":298,"model":"gemini-2.5-flash-lite-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":53},{"place":299,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":52.9},{"place":300,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":52.6},{"place":301,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":52.6},{"place":302,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":52.56},{"place":303,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":52.3},{"place":304,"model":"jamba-reasoning-3b","company":"ai21","family":"Jamba","version":"Jamba Reasoning","score":52},{"place":305,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52},{"place":306,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":51.7},{"place":307,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.7},{"place":308,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.5},{"place":309,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.2},{"place":310,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.2},{"place":311,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.11},{"place":312,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51},{"place":313,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":51},{"place":314,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":50.5},{"place":315,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":50.4},{"place":316,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.38},{"place":317,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":50.3},{"place":318,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.3},{"place":319,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":50},{"place":320,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":50},{"place":321,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":50},{"place":322,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":49.92},{"place":323,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49.8},{"place":324,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":49.73},{"place":325,"model":"midm-k-2.5-pro","company":"kt","family":"Mi:dm","version":"Mi:dm K 2.5","score":49},{"place":326,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.7},{"place":327,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.4},{"place":328,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":48.3},{"place":329,"model":"gka-primed-hqwen3-32b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":48.22},{"place":330,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.06},{"place":331,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":48},{"place":332,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":47.8},{"place":333,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":47.67},{"place":334,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":47.6},{"place":335,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.6},{"place":336,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47.44},{"place":337,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":47.33},{"place":338,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.3},{"place":339,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47.25},{"place":340,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":46.67},{"place":341,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":46.67},{"place":342,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46},{"place":343,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":45.6},{"place":344,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.3},{"place":345,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.2},{"place":346,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":45.1},{"place":347,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":44.85},{"place":348,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":44.67},{"place":349,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":44.6},{"place":350,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":44.6},{"place":351,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":44.4},{"place":352,"model":"lfm2-2.6b-exp","company":"liquidai","family":"LFM","version":"LFM2","score":44.4},{"place":353,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":44.3},{"place":354,"model":"apertus-v1.5-8b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":44.3},{"place":355,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.2},{"place":356,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":44.1},{"place":357,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44},{"place":358,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":43.7},{"place":359,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":43.67},{"place":360,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":43.28},{"place":361,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":43.2},{"place":362,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":43},{"place":363,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":43},{"place":364,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.84},{"place":365,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.67},{"place":366,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":42.67},{"place":367,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":42.53},{"place":368,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":42.3},{"place":369,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42},{"place":370,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":41.84},{"place":371,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":41.7},{"place":372,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":41.7},{"place":373,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":41.7},{"place":374,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":41.67},{"place":375,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":41.6},{"place":376,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":41.49},{"place":377,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":41.4},{"place":378,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.4},{"place":379,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.3},{"place":380,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":41.3},{"place":381,"model":"jan-v1-2509","company":"menlo","family":"Jan","version":"Jan v1","score":40.9},{"place":382,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":40.8},{"place":383,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":40.8},{"place":384,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":40.69},{"place":385,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40.4},{"place":386,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":40},{"place":387,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":40},{"place":388,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40},{"place":389,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":39.87},{"place":390,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":39.7},{"place":391,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":39.6},{"place":392,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.48},{"place":393,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.24},{"place":394,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.2},{"place":395,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":39.2},{"place":396,"model":"jan-v1","company":"menlo","family":"Jan","version":"Jan v1","score":39.1},{"place":397,"model":"gka-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":38.96},{"place":398,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":38.8},{"place":399,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":38.78},{"place":400,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":38.4},{"place":401,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":38.4},{"place":402,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":38.1},{"place":403,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":38},{"place":404,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":38},{"place":405,"model":"jamba2-mini","company":"ai21","family":"Jamba","version":"Jamba2","score":38},{"place":406,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":38},{"place":407,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":37.8},{"place":408,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":37.8},{"place":409,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":37.8},{"place":410,"model":"gdn-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":37.8},{"place":411,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":37.6},{"place":412,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":37.4},{"place":413,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":37.4},{"place":414,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.3},{"place":415,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.3},{"place":416,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":37.2},{"place":417,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.1},{"place":418,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":37},{"place":419,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":37},{"place":420,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36.7},{"place":421,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":36.7},{"place":422,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.7},{"place":423,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":36.7},{"place":424,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":36.4},{"place":425,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":36.3},{"place":426,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":36.3},{"place":427,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":36.2},{"place":428,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":36.1},{"place":429,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":36.1},{"place":430,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":36},{"place":431,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":36},{"place":432,"model":"command-a-reasoning-08-2025","company":"cohere","family":"Command","version":"Command","score":36},{"place":433,"model":"jamba2-3b","company":"ai21","family":"Jamba","version":"Jamba2","score":36},{"place":434,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":35.7},{"place":435,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.4},{"place":436,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":35.33},{"place":437,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.3},{"place":438,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":35.3},{"place":439,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.7},{"place":440,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":34.69},{"place":441,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":34.6},{"place":442,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":34.4},{"place":443,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":34.4},{"place":444,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":34.4},{"place":445,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":34.3},{"place":446,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.3},{"place":447,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.1},{"place":448,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":34.1},{"place":449,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.08},{"place":450,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":34},{"place":451,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":34},{"place":452,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":33.7},{"place":453,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.53},{"place":454,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.5},{"place":455,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":33.33},{"place":456,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":33.3},{"place":457,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":33},{"place":458,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":33},{"place":459,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":33},{"place":460,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":32.8},{"place":461,"model":"apertus-v1.5-70b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":32.7},{"place":462,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":32.61},{"place":463,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":32.33},{"place":464,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":32.3},{"place":465,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":32.3},{"place":466,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":32},{"place":467,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":32},{"place":468,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":31.6},{"place":469,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":31.6},{"place":470,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":31.6},{"place":471,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":31.6},{"place":472,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":31.3},{"place":473,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":31.3},{"place":474,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":31.3},{"place":475,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":31},{"place":476,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.3},{"place":477,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":30.28},{"place":478,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":30.27},{"place":479,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":30},{"place":480,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":30},{"place":481,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":29.7},{"place":482,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.33},{"place":483,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":29.3},{"place":484,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.3},{"place":485,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.25},{"place":486,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":29.2},{"place":487,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":29},{"place":488,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.9},{"place":489,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28.4},{"place":490,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":28.3},{"place":491,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":28.3},{"place":492,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":28.3},{"place":493,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":28},{"place":494,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":27.8},{"place":495,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":27.6},{"place":496,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":27.4},{"place":497,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":27},{"place":498,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":27},{"place":499,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":26.7},{"place":500,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":26.7},{"place":501,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":26.5},{"place":502,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":26},{"place":503,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":26},{"place":504,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":26},{"place":505,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":25.88},{"place":506,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":25.85},{"place":507,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":25.8},{"place":508,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25.7},{"place":509,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":25.7},{"place":510,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":25.7},{"place":511,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.67},{"place":512,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":24.93},{"place":513,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":24.93},{"place":514,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.83},{"place":515,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":24.73},{"place":516,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":24.5},{"place":517,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":24.4},{"place":518,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":24},{"place":519,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":24},{"place":520,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":23.8},{"place":521,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":23.73},{"place":522,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":23.67},{"place":523,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":23.53},{"place":524,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":23.4},{"place":525,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":23},{"place":526,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":23},{"place":527,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.87},{"place":528,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":22.7},{"place":529,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":22.3},{"place":530,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":22.1},{"place":531,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":22.09},{"place":532,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22},{"place":533,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":22},{"place":534,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.33},{"place":535,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":21.28},{"place":536,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.27},{"place":537,"model":"phi-4-mini","company":"microsoft","family":"Phi","version":"Phi 4","score":21},{"place":538,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":21},{"place":539,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21},{"place":540,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":20.8},{"place":541,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":20.8},{"place":542,"model":"lfm2-1.2b","company":"liquidai","family":"LFM","version":"LFM2","score":20.7},{"place":543,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":20.7},{"place":544,"model":"lfm2-700m","company":"liquidai","family":"LFM","version":"LFM2","score":20.56},{"place":545,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":20.47},{"place":546,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":20.33},{"place":547,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":20},{"place":548,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":19.93},{"place":549,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":19.8},{"place":550,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":19.75},{"place":551,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":19.7},{"place":552,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":19.1},{"place":553,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":19},{"place":554,"model":"jan-v1-edge","company":"menlo","family":"Jan","version":"Jan v1","score":18.51},{"place":555,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":18.4},{"place":556,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":18.37},{"place":557,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":18.33},{"place":558,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":18.2},{"place":559,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":17.72},{"place":560,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":17.7},{"place":561,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":17.22},{"place":562,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":17},{"place":563,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":16.86},{"place":564,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":16.7},{"place":565,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":16.6},{"place":566,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":16.5},{"place":567,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":16.41},{"place":568,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":15.98},{"place":569,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":15.93},{"place":570,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":14.7},{"place":571,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":14.5},{"place":572,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":14.2},{"place":573,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":13},{"place":574,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":11.2}]},{"id":"ifeval","name":"IFEval","topic":"Instruction following","description":"Instruction following capability evaluation for LLMs.","url":"https://github.com/google-research/google-research/tree/master/ifeval","leaderboard":"","github":"https://github.com/google-research/google-research/tree/master/instruction_following_eval","paper":"https://arxiv.org/abs/2311.07911","metric":"percent","stars":"36312","top_model":"Jamba2 Mini","top_percent":97,"top_model_id":"jamba2-mini","top_generation":"Jamba2","top_model_base":"Jamba2 Mini","top_model_family":"Jamba","top_company":"ai21","top_open_source":1,"lower_is_better":false,"bench_models":482,"total_models":3854,"placements":[{"place":1,"model":"jamba2-mini","company":"ai21","family":"Jamba","version":"Jamba2","score":97},{"place":2,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":96.75},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":96.1},{"place":4,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":95.9},{"place":5,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95.2},{"place":6,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":95.2},{"place":7,"model":"flint","company":"recursive","family":"Flint","version":"Flint","score":95.1},{"place":8,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":95.02},{"place":9,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95},{"place":10,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":95},{"place":12,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":94.82},{"place":13,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":94.8},{"place":14,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":94.8},{"place":15,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.8},{"place":16,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.8},{"place":17,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":94.8},{"place":18,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":94.8},{"place":19,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":94.7},{"place":20,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":94.6},{"place":21,"model":"flint-nvfp4","company":"recursive","family":"Flint","version":"Flint","score":94.6},{"place":22,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.6},{"place":23,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":94.6},{"place":24,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":94.5},{"place":25,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":94.5},{"place":26,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":94.5},{"place":27,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":94.45},{"place":28,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":94.3},{"place":29,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":94.3},{"place":30,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":94.3},{"place":31,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":94.27},{"place":32,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":94.19},{"place":33,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":94.1},{"place":34,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":94.1},{"place":35,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94},{"place":36,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":94},{"place":37,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":93.9},{"place":38,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":93.9},{"place":39,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":93.9},{"place":40,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":93.9},{"place":41,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":93.9},{"place":42,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":93.9},{"place":43,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":93.9},{"place":44,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":93.89},{"place":45,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":93.8},{"place":46,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.74},{"place":47,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":93.7},{"place":48,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":93.7},{"place":49,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":93.6},{"place":50,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":93.53},{"place":51,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.5},{"place":52,"model":"underdog-saluki-27b-1.0","company":"conwayresearch","family":"Underdog","version":"Underdog 1.0","score":93.5},{"place":53,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":93.4},{"place":54,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.4},{"place":55,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":93.4},{"place":56,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":93.4},{"place":57,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":93.35},{"place":58,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.35},{"place":59,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":93.35},{"place":60,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":93.2},{"place":61,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":93.06},{"place":62,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":93},{"place":63,"model":"jamba2-3b","company":"ai21","family":"Jamba","version":"Jamba2","score":93},{"place":64,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":92.98},{"place":65,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":92.8},{"place":66,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":92.8},{"place":67,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.8},{"place":68,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":92.8},{"place":69,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":92.6},{"place":70,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.6},{"place":71,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":92.6},{"place":72,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":92.4},{"place":73,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.4},{"place":74,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":92.24},{"place":75,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":92.2},{"place":76,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":92.1},{"place":77,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":92},{"place":78,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":92},{"place":79,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.9},{"place":80,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.9},{"place":81,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.9},{"place":82,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":91.87},{"place":83,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":91.84},{"place":84,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":91.6},{"place":85,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":91.6},{"place":86,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":91.53},{"place":87,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.5},{"place":88,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.5},{"place":89,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":91.4},{"place":90,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":91.4},{"place":91,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":91.31},{"place":92,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":91.3},{"place":93,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":91.13},{"place":94,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":91.1},{"place":95,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":91},{"place":96,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.9},{"place":97,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":90.9},{"place":98,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":90.82},{"place":99,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":90.8},{"place":100,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":90.8},{"place":101,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.8},{"place":102,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":90.6},{"place":103,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":90.5},{"place":104,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":90.4},{"place":105,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":90.4},{"place":106,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":90.39},{"place":107,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":90.3},{"place":108,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":90.2},{"place":109,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":90.2},{"place":110,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.2},{"place":111,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":90.2},{"place":112,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":90},{"place":113,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":90},{"place":114,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":90},{"place":115,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":90},{"place":116,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":90},{"place":117,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":89.94},{"place":118,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":89.87},{"place":119,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.8},{"place":120,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.8},{"place":121,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.8},{"place":122,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":89.8},{"place":123,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.8},{"place":124,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.8},{"place":125,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":89.7},{"place":126,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":89.7},{"place":127,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":89.7},{"place":128,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":89.65},{"place":129,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":89.6},{"place":130,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":89.6},{"place":131,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.6},{"place":132,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":89.5},{"place":133,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":89.5},{"place":134,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.5},{"place":135,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.46},{"place":136,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":89.4},{"place":137,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.4},{"place":138,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":89.37},{"place":139,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":89.3},{"place":140,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":89.1},{"place":141,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":89.1},{"place":142,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":89.09},{"place":143,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":89},{"place":144,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":88.9},{"place":145,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":88.9},{"place":146,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.9},{"place":147,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":88.9},{"place":148,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":88.9},{"place":149,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":88.9},{"place":150,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":88.83},{"place":151,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":88.8},{"place":152,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.72},{"place":153,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":88.7},{"place":154,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.7},{"place":155,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":88.7},{"place":156,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":88.6},{"place":157,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.5},{"place":158,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":88.5},{"place":159,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":88.5},{"place":160,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":88.5},{"place":161,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":88.42},{"place":162,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":88.4},{"place":163,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":88.4},{"place":164,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.4},{"place":165,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":88.35},{"place":166,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":88.2},{"place":167,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":88.2},{"place":168,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.2},{"place":169,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":88.2},{"place":170,"model":"lfm2-2.6b-exp","company":"liquidai","family":"LFM","version":"LFM2","score":88.13},{"place":171,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.1},{"place":172,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":88},{"place":173,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":88},{"place":174,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":88},{"place":175,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":88},{"place":176,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":88},{"place":177,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88},{"place":178,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88},{"place":179,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88},{"place":180,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":88},{"place":181,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.9},{"place":182,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87.9},{"place":183,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.8},{"place":184,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.8},{"place":185,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.8},{"place":186,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.8},{"place":187,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.8},{"place":188,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":87.8},{"place":189,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.8},{"place":190,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.74},{"place":191,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":87.7},{"place":192,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":87.6},{"place":193,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":87.6},{"place":194,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.6},{"place":195,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":87.6},{"place":196,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":87.55},{"place":197,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":87.5},{"place":198,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.5},{"place":199,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":87.5},{"place":200,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":87.5},{"place":201,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":87.4},{"place":202,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":87.4},{"place":203,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.4},{"place":204,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":87.4},{"place":205,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":87.3},{"place":206,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":87.25},{"place":207,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":87.2},{"place":208,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":87.2},{"place":209,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":87.1},{"place":210,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.1},{"place":211,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":87.1},{"place":212,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":87.06},{"place":213,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.06},{"place":214,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.97},{"place":215,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":86.9},{"place":216,"model":"longcat-flash-thinking","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":86.9},{"place":217,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.9},{"place":218,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":86.88},{"place":219,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.8},{"place":220,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":86.73},{"place":221,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":86.7},{"place":222,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":86.7},{"place":223,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":86.69},{"place":224,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":86.69},{"place":225,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.5},{"place":226,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.5},{"place":227,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":86.5},{"place":228,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":86.5},{"place":229,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.5},{"place":230,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":86.5},{"place":231,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":86.5},{"place":232,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.35},{"place":233,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":86.32},{"place":234,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":86.32},{"place":235,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":86.3},{"place":236,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.3},{"place":237,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":86.3},{"place":238,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":86.23},{"place":239,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.2},{"place":240,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":86.1},{"place":241,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":86.1},{"place":242,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.1},{"place":243,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":86},{"place":244,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":86},{"place":245,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":86},{"place":246,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":86},{"place":247,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86},{"place":248,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.8},{"place":249,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":85.8},{"place":250,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":85.8},{"place":251,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.8},{"place":252,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.62},{"place":253,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.6},{"place":254,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":85.58},{"place":255,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":85.5},{"place":256,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.5},{"place":257,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.5},{"place":258,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":85.5},{"place":259,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.4},{"place":260,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":85.4},{"place":261,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.4},{"place":262,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":85.4},{"place":263,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":85.35},{"place":264,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":85.22},{"place":265,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.2},{"place":266,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":85.2},{"place":267,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.1},{"place":268,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":85.05},{"place":269,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85},{"place":270,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":85},{"place":271,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":85},{"place":272,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":84.9},{"place":273,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":84.84},{"place":274,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.8},{"place":275,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":84.8},{"place":276,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":84.8},{"place":277,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.7},{"place":278,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84.7},{"place":279,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":84.7},{"place":280,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":84.7},{"place":281,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":84.7},{"place":282,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.66},{"place":283,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":84.6},{"place":284,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":84.6},{"place":285,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":84.47},{"place":286,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":84.47},{"place":287,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":84.37},{"place":288,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.3},{"place":289,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.3},{"place":290,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":84.3},{"place":291,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84.29},{"place":292,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84.13},{"place":293,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.1},{"place":294,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":84.1},{"place":295,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.1},{"place":296,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.03},{"place":297,"model":"midm-2.0-base-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":84},{"place":298,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":84},{"place":299,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":83.93},{"place":300,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":83.9},{"place":301,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":83.9},{"place":302,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.9},{"place":303,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.9},{"place":304,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.7},{"place":305,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.7},{"place":306,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":83.7},{"place":307,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":83.7},{"place":308,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":83.7},{"place":309,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.67},{"place":310,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.6},{"place":311,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":83.6},{"place":312,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":83.55},{"place":313,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.53},{"place":314,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":83.5},{"place":315,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":83.5},{"place":316,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.43},{"place":317,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83.4},{"place":318,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.4},{"place":319,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.4},{"place":320,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83.2},{"place":321,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83.2},{"place":322,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.2},{"place":323,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":83.2},{"place":324,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":83.2},{"place":325,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.18},{"place":326,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":83.1},{"place":327,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83},{"place":328,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":83},{"place":329,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":83},{"place":330,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":82.97},{"place":331,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":82.96},{"place":332,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.93},{"place":333,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":82.9},{"place":334,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":82.81},{"place":335,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":82.81},{"place":336,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":82.8},{"place":337,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.8},{"place":338,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":82.8},{"place":339,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":82.8},{"place":340,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.73},{"place":341,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":82.72},{"place":342,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":82.7},{"place":343,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":82.62},{"place":344,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":82.6},{"place":345,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":82.5},{"place":346,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":82.44},{"place":347,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":82.4},{"place":348,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":82.4},{"place":349,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":82.4},{"place":350,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":82.4},{"place":351,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":82.36},{"place":352,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":82.31},{"place":353,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":82.3},{"place":354,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.3},{"place":355,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":82.3},{"place":356,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":82.3},{"place":357,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":82.23},{"place":358,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":82.2},{"place":359,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":82.2},{"place":360,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":82.16},{"place":361,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":82.1},{"place":362,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.1},{"place":363,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":82.1},{"place":364,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":82},{"place":365,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.9},{"place":366,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":81.9},{"place":367,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":81.9},{"place":368,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":81.9},{"place":369,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.89},{"place":370,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":81.89},{"place":371,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.89},{"place":372,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":81.8},{"place":373,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.79},{"place":374,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":81.75},{"place":375,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":81.7},{"place":376,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.7},{"place":377,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":81.7},{"place":378,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.7},{"place":379,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":81.52},{"place":380,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":81.51},{"place":381,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":81.5},{"place":382,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":81.38},{"place":383,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":81.25},{"place":384,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":81.2},{"place":385,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.2},{"place":386,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":81.2},{"place":387,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":81.2},{"place":388,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":81.1},{"place":389,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":81.1},{"place":390,"model":"exaone-3.5-2.4b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":81.1},{"place":391,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":81.06},{"place":392,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":81.02},{"place":393,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":81},{"place":394,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":80.96},{"place":395,"model":"apriel-5b-instruct","company":"servicenow","family":"Apriel","version":"Apriel","score":80.8},{"place":396,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":80.71},{"place":397,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":80.66},{"place":398,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":80.6},{"place":399,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":80.6},{"place":400,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":80.6},{"place":401,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":80.56},{"place":402,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":80.5},{"place":403,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":80.41},{"place":404,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":80.4},{"place":405,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":80.4},{"place":406,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":80.2},{"place":407,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":80.2},{"place":408,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":80.08},{"place":409,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":79.9},{"place":410,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":79.9},{"place":411,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.9},{"place":412,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.7},{"place":413,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":79.7},{"place":414,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":79.63},{"place":415,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":79.61},{"place":416,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":79.56},{"place":417,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":79.5},{"place":418,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":79.5},{"place":419,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":79.48},{"place":420,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":79.44},{"place":421,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":79.41},{"place":422,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":79.3},{"place":423,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":79.3},{"place":424,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":79.12},{"place":425,"model":"llama-spark-8b","company":"arcee","family":"Llama Spark","version":"Llama Spark 8B","score":79.11},{"place":426,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":79.11},{"place":427,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":79.1},{"place":428,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":79.1},{"place":429,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":79.1},{"place":430,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":79},{"place":431,"model":"aquif-3-3.2b","company":"aquif","family":"Aquif","version":"Aquif 3","score":78.9},{"place":432,"model":"aquif-3.5-2.7b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":78.9},{"place":433,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":78.84},{"place":434,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":78.7},{"place":435,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":78.6},{"place":436,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.6},{"place":437,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":78.45},{"place":438,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":78},{"place":439,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.9},{"place":440,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.9},{"place":441,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":77.63},{"place":442,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":77.6},{"place":443,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":77.6},{"place":444,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":77.6},{"place":445,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":77.58},{"place":446,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":77.5},{"place":447,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.5},{"place":448,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":77.45},{"place":449,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":77.4},{"place":450,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.26},{"place":451,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":77.1},{"place":452,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":77.08},{"place":453,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":77.04},{"place":454,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":76.96},{"place":455,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":76.9},{"place":456,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":76.85},{"place":457,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":76.8},{"place":458,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":76.7},{"place":459,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":76.6},{"place":460,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":76.59},{"place":461,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":76.52},{"place":462,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":76.5},{"place":463,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":76.39},{"place":464,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":76.34},{"place":465,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":76.09},{"place":466,"model":"jamba-mini-1.7","company":"ai21","family":"Jamba","version":"Jamba Mini","score":76},{"place":467,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":76},{"place":468,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":75.9},{"place":469,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.9},{"place":470,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":75.8},{"place":471,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":75.78},{"place":472,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":75.6},{"place":473,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":75.52},{"place":474,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":75.4},{"place":475,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":75.36},{"place":476,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":75.3},{"place":477,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.25},{"place":478,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":75.2},{"place":479,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":75.1},{"place":480,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":75},{"place":481,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":74.9},{"place":482,"model":"lfm2-1.2b","company":"liquidai","family":"LFM","version":"LFM2","score":74.89},{"place":483,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":74.82},{"place":484,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.7},{"place":485,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":74.7},{"place":486,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.68},{"place":487,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":74.57},{"place":488,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":74.55},{"place":489,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":74.31},{"place":490,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":74},{"place":491,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.98},{"place":492,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":73.9},{"place":493,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":73.7},{"place":494,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.68},{"place":495,"model":"exaone-3.5-2.4b","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":73.6},{"place":496,"model":"midm-2.0-mini-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":73.6},{"place":497,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.6},{"place":498,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":73.49},{"place":499,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.4},{"place":500,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.4},{"place":501,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.3},{"place":502,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":73.2},{"place":503,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":73.1},{"place":504,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":73.08},{"place":505,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":73},{"place":506,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":72.9},{"place":507,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":72.8},{"place":508,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":72.8},{"place":509,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.5},{"place":510,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":72.5},{"place":511,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":72.5},{"place":512,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":72.44},{"place":513,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":72.36},{"place":514,"model":"lfm2-700m","company":"liquidai","family":"LFM","version":"LFM2","score":72.23},{"place":515,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":72.2},{"place":516,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":72.1},{"place":517,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":72.07},{"place":518,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":71.71},{"place":519,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.65},{"place":520,"model":"llama-3.1-3b","company":"meta","family":"Llama","version":"Llama 3.1","score":71.6},{"place":521,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":71.43},{"place":522,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":71.4},{"place":523,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":71.35},{"place":524,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.2},{"place":525,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":71.2},{"place":526,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":71.2},{"place":527,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":71},{"place":528,"model":"jais-2-70b-chat","company":"g42","family":"Jais","version":"Jais 2","score":70.78},{"place":529,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":70.43},{"place":530,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":70.4},{"place":531,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":532,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":70.06},{"place":533,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":69.9},{"place":534,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":69.8},{"place":535,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":69.7},{"place":536,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":69.3},{"place":537,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":69.15},{"place":538,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":69.1},{"place":539,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":69.1},{"place":540,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":69},{"place":541,"model":"phi-4-mini-3.8b","company":"microsoft","family":"Phi","version":"Phi 4 mini","score":68.6},{"place":542,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":68.58},{"place":543,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":68.4},{"place":544,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.39},{"place":545,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.2},{"place":546,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":68},{"place":547,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.9},{"place":548,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":67.8},{"place":549,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":67.3},{"place":550,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":67.22},{"place":551,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":67.1},{"place":552,"model":"afm-4.5b","company":"arcee","family":"AFM","version":"AFM","score":67.03},{"place":553,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":67},{"place":554,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.91},{"place":555,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":66.5},{"place":556,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.5},{"place":557,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":66},{"place":558,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":65.88},{"place":559,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":65.8},{"place":560,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":65.74},{"place":561,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.6},{"place":562,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":65.2},{"place":563,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":65.12},{"place":564,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":65.1},{"place":565,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":64.98},{"place":566,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":64.96},{"place":567,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.51},{"place":568,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":64.37},{"place":569,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.24},{"place":570,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":64.1},{"place":571,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":63.8},{"place":572,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":63.59},{"place":573,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":63.49},{"place":574,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":63.25},{"place":575,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":63.1},{"place":576,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":63.03},{"place":577,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":62.5},{"place":578,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":62.5},{"place":579,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":62.5},{"place":580,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.16},{"place":581,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":62.1},{"place":582,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":62},{"place":583,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":62},{"place":584,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":61.6},{"place":585,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":61.55},{"place":586,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":61.4},{"place":587,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":61.4},{"place":588,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":61.29},{"place":589,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":61.27},{"place":590,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":61.24},{"place":591,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":61.16},{"place":592,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":60.81},{"place":593,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":60.4},{"place":594,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.94},{"place":595,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.9},{"place":596,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.89},{"place":597,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.89},{"place":598,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":59.7},{"place":599,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":59.7},{"place":600,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.6},{"place":601,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":59.5},{"place":602,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":59.5},{"place":603,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.2},{"place":604,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.1},{"place":605,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.6},{"place":606,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":58},{"place":607,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":57.9},{"place":608,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":57.7},{"place":609,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":57.3},{"place":610,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":56.7},{"place":611,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":56.5},{"place":612,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":56.4},{"place":613,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":56.2},{"place":614,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":55.5},{"place":615,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":55.34},{"place":616,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":54.7},{"place":617,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":54.3},{"place":618,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":54.26},{"place":619,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":53.5},{"place":620,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":53.5},{"place":621,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":53.48},{"place":622,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":52.39},{"place":623,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":52.37},{"place":624,"model":"nemotron-flash-3b","company":"nvidia","family":"Nemotron Flash","version":"Nemotron Flash","score":52.03},{"place":625,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":51.75},{"place":626,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":51.7},{"place":627,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":51.2},{"place":628,"model":"qwen-72b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":50.8},{"place":629,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":50.1},{"place":630,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.8},{"place":631,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":48.7},{"place":632,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":48.5},{"place":633,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":48.4},{"place":634,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":48.1},{"place":635,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.4},{"place":636,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":46.77},{"place":637,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":46.64},{"place":638,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":46.21},{"place":639,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":46.1},{"place":640,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":45.9},{"place":641,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.33},{"place":642,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.3},{"place":643,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":44.6},{"place":644,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":44.5},{"place":645,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.4},{"place":646,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":44.2},{"place":647,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44},{"place":648,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":44},{"place":649,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":43.8},{"place":650,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":42.5},{"place":651,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":42.5},{"place":652,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":42.2},{"place":653,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":42.1},{"place":654,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":41.2},{"place":655,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":40.9},{"place":656,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":40.2},{"place":657,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":38.8},{"place":658,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":38.6},{"place":659,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.52},{"place":660,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":37.3},{"place":661,"model":"trlm-135m","company":"loka","family":"TRLM","version":"TRLM","score":35.49},{"place":662,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":35.4},{"place":663,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.8},{"place":664,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":34.6},{"place":665,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":33.7},{"place":666,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.93},{"place":667,"model":"falcon-e-1b-base","company":"tii","family":"Falcon","version":"Falcon E","score":32.9},{"place":668,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":32.9},{"place":669,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":32.4},{"place":670,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.11},{"place":671,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":31.4},{"place":672,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":31.23},{"place":673,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":31.2},{"place":674,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":30.14},{"place":675,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":29.9},{"place":676,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":29.7},{"place":677,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":29.4},{"place":678,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":28.48},{"place":679,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":28.1},{"place":680,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":24.4},{"place":681,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":24.28},{"place":682,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":23.1},{"place":683,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":21.15},{"place":684,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":11.56},{"place":685,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":10.12}]},{"id":"ifeval-code","name":"IFEval-Code","topic":"Instruction following (code)","description":"Instruction following evaluation for code generation tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-32B","top_percent":28,"top_model_id":"qwen3-32b","top_generation":"Qwen3","top_model_base":"Qwen3 32B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":28},{"place":2,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":26},{"place":3,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":25.73},{"place":4,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":23},{"place":5,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":20.95},{"place":6,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":20.45}]},{"id":"ifeval-strict-prompt","name":"IFEval (Strict Prompt)","topic":"Instruction following","description":"IFEval strict prompt-level accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen2.5 Plus (11-27)","top_percent":86.3,"top_model_id":"qwen2.5-plus-1127","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":53,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.3},{"place":2,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":86},{"place":3,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":85},{"place":4,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":84.3},{"place":5,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.29},{"place":6,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.1},{"place":7,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.73},{"place":8,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":83.6},{"place":9,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":83.55},{"place":10,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":83.36},{"place":11,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":83.18},{"place":12,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":82.62},{"place":13,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":82.6},{"place":14,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":81.33},{"place":15,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":81.15},{"place":16,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81},{"place":17,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":80.8},{"place":18,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":80.78},{"place":19,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":80.4},{"place":20,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.5},{"place":21,"model":"carbon-x","company":"huggingface","family":"Carbon","version":"Carbon","score":79.3},{"place":22,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":77.6},{"place":23,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":77.3},{"place":24,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":77.1},{"place":25,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.3},{"place":26,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":76.16},{"place":27,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":75.9},{"place":28,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.9},{"place":29,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":73.9},{"place":30,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":72.1},{"place":31,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":71.9},{"place":32,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":71.5},{"place":33,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":71.2},{"place":34,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.2},{"place":35,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":70.1},{"place":36,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":69},{"place":37,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":68.4},{"place":38,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":67.1},{"place":39,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":64.5},{"place":40,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":64.1},{"place":41,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":59.9},{"place":42,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":58.8},{"place":43,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.2},{"place":44,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":57.5},{"place":45,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":55.8},{"place":46,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":55.8},{"place":47,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":54.7},{"place":48,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":52.1},{"place":49,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":51},{"place":50,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":51},{"place":51,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":50.3},{"place":52,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":49.4},{"place":53,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.5},{"place":54,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":39},{"place":55,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":38.3},{"place":56,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":29},{"place":57,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27.9},{"place":58,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":20},{"place":59,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":16.8},{"place":60,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":14.6},{"place":61,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":14.6}]},{"id":"ifstruct","name":"IFStruct","topic":"Structured output","description":"Instruction-following benchmark for structured outputs (format/schema-constrained generation).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 2.6B","top_percent":85.49,"top_model_id":"lfm2.5-2.6b","top_generation":"LFM2.5","top_model_base":"LFM2.5 2.6B","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":85.49},{"place":2,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.5},{"place":3,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.65},{"place":4,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.85},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.25}]},{"id":"iheval","name":"IHEval","topic":"Instruction hierarchy","description":"Benchmark for following the instruction hierarchy (system > user > tool) under conflicting instructions.","url":"","leaderboard":"","github":"https://github.com/ytyz1307zzh/IHEval","paper":"","metric":"percent","stars":"","top_model":"Nemotron-3.5-Bolt-E4B","top_percent":84.79,"top_model_id":"nemotron-3.5-bolt-e4b","top_generation":"Nemotron 3.5","top_model_base":"Nemotron-3.5 Bolt E4B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":84.79},{"place":2,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":82.4},{"place":3,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":67.04},{"place":4,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":66.61},{"place":5,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.87},{"place":6,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.57},{"place":7,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":53.75},{"place":8,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":51.31}]},{"id":"imagemining","name":"ImageMining","topic":"Multimodal tool use","description":"Multimodal tool-use benchmark of mining information from images with tools.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-5V-Turbo","top_percent":30.7,"top_model_id":"glm-5v-turbo","top_generation":"GLM 5V","top_model_base":"GLM-5V Turbo","top_model_family":"GLM","top_company":"zai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":30.7},{"place":2,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":24.4}]},{"id":"img-qa-avg","name":"Image QA Average","topic":"Image QA (aggregate)","description":"Average of single-image visual question answering benchmarks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":86.2,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.2},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":83.7},{"place":3,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":81.9},{"place":4,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":81.7},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.3},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.2},{"place":7,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":81.2},{"place":8,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":81.2},{"place":9,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":80.4},{"place":10,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":79.8},{"place":11,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":79.7},{"place":12,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.3},{"place":13,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":78.7},{"place":14,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.4},{"place":15,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.2},{"place":16,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":77.7},{"place":17,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":77.3},{"place":18,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":77.2},{"place":19,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":77},{"place":20,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.3},{"place":21,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":75.9},{"place":22,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":74.6}]},{"id":"imo-2025","name":"IMO 2025","topic":"Math olympiad (proofs)","description":"2025 International Mathematical Olympiad (6 proof problems), graded with MathArena methodology.","url":"https://matharena.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":76.1,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":76.1},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":65.2},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":42.4},{"place":4,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":17.4}]},{"id":"imo-answerbench","name":"IMO AnswerBench","topic":"Math (competition)","description":"Evaluates free-form solutions to International Mathematical Olympiad problems using expert-style grading rubrics.","url":"https://imobench.github.io/","leaderboard":"https://imobench.github.io/#leaderboard","github":"https://github.com/google-deepmind/superhuman/tree/main/imobench","paper":"https://arxiv.org/abs/2511.01846","metric":"percent","stars":"","top_model":"DeepSeek V4-Pro","top_percent":93,"top_model_id":"deepseek-v4-pro","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Pro","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":150,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":92.1},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":91.8},{"place":4,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":91.6},{"place":5,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.5},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":91.4},{"place":7,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":91.1},{"place":8,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.1},{"place":9,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":91.1},{"place":10,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":91},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":91},{"place":12,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":90.9},{"place":13,"model":"ring-1t-2.5-heavy-thinking","company":"antgroup","family":"Ring","version":"Ring 2.5","score":90},{"place":14,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":90},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":90},{"place":16,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":90},{"place":17,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.8},{"place":18,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.8},{"place":19,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":89.3},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89.2},{"place":21,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88.6},{"place":22,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":88.5},{"place":23,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.4},{"place":24,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.4},{"place":25,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88},{"place":26,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":87.31},{"place":27,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87},{"place":28,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":86.8},{"place":29,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":86.8},{"place":30,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.7},{"place":31,"model":"ring-1t-2.5","company":"antgroup","family":"Ring","version":"Ring 2.5","score":86.69},{"place":32,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":86.6},{"place":33,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":86.3},{"place":34,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":86.3},{"place":35,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.3},{"place":36,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":86.12},{"place":37,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":86.1},{"place":38,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":86},{"place":39,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":86},{"place":40,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":86},{"place":41,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":85.4},{"place":42,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.1},{"place":43,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":84.5},{"place":44,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":84.4},{"place":45,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":84.3},{"place":46,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":84.3},{"place":47,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":84},{"place":48,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84},{"place":49,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":84},{"place":50,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83.9},{"place":51,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":83.8},{"place":52,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.8},{"place":53,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":83.7},{"place":54,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":83.5},{"place":55,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":83.3},{"place":56,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":83.2},{"place":57,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":83.1},{"place":58,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.1},{"place":59,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82.8},{"place":60,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":82.5},{"place":61,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82.1},{"place":62,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":82},{"place":63,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":81.8},{"place":64,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":81.8},{"place":65,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":81.8},{"place":66,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":81.8},{"place":67,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":81.8},{"place":68,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":81.6},{"place":69,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.3},{"place":70,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":81.25},{"place":71,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":81},{"place":72,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81},{"place":73,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":80.9},{"place":74,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.9},{"place":75,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.8},{"place":76,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":80.28},{"place":77,"model":"gemini-deep-think-imo-gold","company":"google","family":"Gemini","version":"Gemini Deep Think","score":80},{"place":78,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.9},{"place":79,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.53},{"place":80,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":79.5},{"place":81,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":79.3},{"place":82,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":79},{"place":83,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78.9},{"place":84,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":78.7},{"place":85,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":78.6},{"place":86,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":78.6},{"place":87,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":78.6},{"place":88,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.5},{"place":89,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.5},{"place":90,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":78.3},{"place":91,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":78.3},{"place":92,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":77.7},{"place":93,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":77.53},{"place":94,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.5},{"place":95,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":77.3},{"place":96,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":77.3},{"place":97,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":77.25},{"place":98,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":77.2},{"place":99,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":77},{"place":100,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.8},{"place":101,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":76.5},{"place":102,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":76.4},{"place":103,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":76.3},{"place":104,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":76.3},{"place":105,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":76},{"place":106,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":76},{"place":107,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":75.6},{"place":108,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.3},{"place":109,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75.3},{"place":110,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":75.2},{"place":111,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":74.9},{"place":112,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.8},{"place":113,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.8},{"place":114,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.5},{"place":115,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":74.5},{"place":116,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.3},{"place":117,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":74.2},{"place":118,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":73.5},{"place":119,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":73.5},{"place":120,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":73.1},{"place":121,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73},{"place":122,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.6},{"place":123,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.3},{"place":124,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":72.1},{"place":125,"model":"gemini-2.5-deep-think","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.8},{"place":126,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.6},{"place":127,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":71.03},{"place":128,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.5},{"place":129,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70.4},{"place":130,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70.4},{"place":131,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70},{"place":132,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.8},{"place":133,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.5},{"place":134,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":68.3},{"place":135,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.2},{"place":136,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":67.9},{"place":137,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":67.3},{"place":138,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":66.9},{"place":139,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":66.44},{"place":140,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":66.3},{"place":141,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":66.1},{"place":142,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.9},{"place":143,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":65.81},{"place":144,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.8},{"place":145,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65.6},{"place":146,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":65.5},{"place":147,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.5},{"place":148,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.25},{"place":149,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.09},{"place":150,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.69},{"place":151,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":63.4},{"place":152,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":62.31},{"place":153,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":62.3},{"place":154,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":61.9},{"place":155,"model":"o3","company":"openai","family":"o3","version":"o3","score":61.1},{"place":156,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":61.1},{"place":157,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":60.8},{"place":158,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":60.8},{"place":159,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":60.8},{"place":160,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60.75},{"place":161,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60.7},{"place":162,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":60.6},{"place":163,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":60.4},{"place":164,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":59.3},{"place":165,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.5},{"place":166,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.2},{"place":167,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.3},{"place":168,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.9},{"place":169,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":54.81},{"place":170,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.5},{"place":171,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54.34},{"place":172,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":54.28},{"place":173,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":53.9},{"place":174,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.8},{"place":175,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":53.4},{"place":176,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":53.38},{"place":177,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":52.56},{"place":178,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.6},{"place":179,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":51.5},{"place":180,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":50.9},{"place":181,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":49.4},{"place":182,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":49.38},{"place":183,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.7},{"place":184,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48},{"place":185,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.8},{"place":186,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":46.66},{"place":187,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":46.2},{"place":188,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":45.8},{"place":189,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":45.8},{"place":190,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":45.4},{"place":191,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":44.75},{"place":192,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":43.94},{"place":193,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":43.41},{"place":194,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":41.9},{"place":195,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":41.81},{"place":196,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":39.6},{"place":197,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":39.34},{"place":198,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":38.59},{"place":199,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":38.25},{"place":200,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":37},{"place":201,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.56},{"place":202,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35.3},{"place":203,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":31.75},{"place":204,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":28.7},{"place":205,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.3},{"place":206,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.9},{"place":207,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":24},{"place":208,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":23},{"place":209,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":22.6},{"place":210,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":22.3},{"place":211,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":21.16}]},{"id":"implicitmembench","name":"ImplicitMemBench","topic":"Long-term memory","description":"Tests implicit memory: whether agents apply previously seen preferences and procedures without being explicitly asked to recall them.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MemT-1.0-Flash","top_percent":49.2,"top_model_id":"memt-1.0-flash","top_generation":"MemT-1.0","top_model_base":"MemT-1.0-Flash","top_model_family":"MemT","top_company":"memtensor","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"memt-1.0-flash","company":"memtensor","family":"MemT","version":"MemT-1.0","score":49.2},{"place":2,"model":"memt-1.0-nano","company":"memtensor","family":"MemT","version":"MemT-1.0","score":43.1}]},{"id":"include","name":"INCLUDE","topic":"Inclusiveness / bias","description":"Evaluates inclusive language use and bias mitigation in model outputs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":90.5,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":67,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.5},{"place":2,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":87.5},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":87.4},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":86.2},{"place":5,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":86.2},{"place":6,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.1},{"place":7,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.6},{"place":8,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.1},{"place":9,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":84.9},{"place":10,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":84.3},{"place":11,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":84.2},{"place":12,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.9},{"place":13,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":83.3},{"place":14,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":83},{"place":15,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.8},{"place":16,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":82.3},{"place":17,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":81.8},{"place":18,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.6},{"place":19,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81},{"place":20,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":81},{"place":21,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.7},{"place":22,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.5},{"place":23,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":78.9},{"place":24,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":78.9},{"place":25,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":78.64},{"place":26,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":78.3},{"place":27,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":77.86},{"place":28,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":77.2},{"place":29,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":77.2},{"place":30,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":76.27},{"place":31,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":75.66},{"place":32,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.6},{"place":33,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":75.3},{"place":34,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.5},{"place":35,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.4},{"place":36,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":74},{"place":37,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.7},{"place":38,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":71.9},{"place":39,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.9},{"place":40,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.6},{"place":41,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":71.4},{"place":42,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71},{"place":43,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.9},{"place":44,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":67.26},{"place":45,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67},{"place":46,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":65.6},{"place":47,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":65.3},{"place":48,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":65},{"place":49,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":64.4},{"place":50,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":63.97},{"place":51,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.8},{"place":52,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":62.5},{"place":53,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.4},{"place":54,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":60.3},{"place":55,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60.1},{"place":56,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":58.89},{"place":57,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.4},{"place":58,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":54.3},{"place":59,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":52.05},{"place":60,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":51.8},{"place":61,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":51.62},{"place":62,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":51.1},{"place":63,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":51.06},{"place":64,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":50.7},{"place":65,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":49.1},{"place":66,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":45.1},{"place":67,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":44.9},{"place":68,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.4},{"place":69,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":43.5},{"place":70,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.6},{"place":71,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":38.6},{"place":72,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":35.4}]},{"id":"indicifeval-ground","name":"IndicIFEval (ground)","topic":"Indic languages","description":"Natively written Indic instruction-following prompts; prompt-level strict.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Sarvam-30B","top_percent":40.69,"top_model_id":"sarvam-30b","top_generation":"Sarvam","top_model_base":"Sarvam 30B","top_model_family":"Sarvam","top_company":"sarvam","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":40.69},{"place":2,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":37.88},{"place":3,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37.79},{"place":4,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.73},{"place":5,"model":"gnani-evon-v3.3-30b-a3b","company":"gnani","family":"gnani-evon","version":"gnani-evon-v3.3","score":28.66}]},{"id":"indicifeval-trans","name":"IndicIFEval (translated)","topic":"Indic languages","description":"IFEval-style instruction following, translated into Indic languages; prompt-level strict.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":81.12,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":81.12},{"place":2,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.2},{"place":3,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":51.79},{"place":4,"model":"gnani-evon-v3.3-30b-a3b","company":"gnani","family":"gnani-evon","version":"gnani-evon-v3.3","score":47.45},{"place":5,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":40.76}]},{"id":"indicmmlu-pro","name":"IndicMMLU-Pro","topic":"Indic languages","description":"MMLU-Pro translated/adapted to Indic languages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":79.02,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.02},{"place":2,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":70.34},{"place":3,"model":"gnani-evon-v3.3-30b-a3b","company":"gnani","family":"gnani-evon","version":"gnani-evon-v3.3","score":68.79}]},{"id":"indicsafe5","name":"IndicSafe5","topic":"Indic languages","description":"Safety benchmark of harmful/benign prompts across Indic languages; accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":89.77,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":89.77},{"place":2,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.15},{"place":3,"model":"gnani-evon-v3.3-30b-a3b","company":"gnani","family":"gnani-evon","version":"gnani-evon-v3.3","score":86.5},{"place":4,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":81.26}]},{"id":"indommlu","name":"IndoMMLU","topic":"Indonesian knowledge","description":"Indonesian multi-task exam questions from primary school to university entrance level.","url":"https://huggingface.co/datasets/indolem/IndoMMLU","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2310.04928","metric":"percent","stars":"","top_model":"Qwen2.5-72B-Instruct","top_percent":69.25,"top_model_id":"qwen2.5-72b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.25},{"place":2,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":67.75},{"place":3,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":67.5},{"place":4,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.42},{"place":5,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":66.31},{"place":6,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.09},{"place":7,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":63.21},{"place":8,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":61.73},{"place":9,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.42},{"place":10,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":54.05},{"place":11,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":53.92},{"place":12,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":50.76}]},{"id":"infoqa","name":"InfoQA","topic":"Information-seeking QA","description":"Information retrieval question answering benchmark evaluating factual responses.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":86.9,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.9},{"place":2,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":84.5},{"place":3,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.1},{"place":4,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":83},{"place":5,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":83},{"place":6,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.2},{"place":7,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":82},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82},{"place":9,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":81.9},{"place":10,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":81},{"place":11,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.9},{"place":12,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":80.4},{"place":13,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.3},{"place":14,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":80.3},{"place":15,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":80.3},{"place":16,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":80.1},{"place":17,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":80},{"place":18,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":79.6},{"place":19,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":79.2},{"place":20,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":79.1},{"place":21,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":78.6},{"place":22,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78},{"place":23,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":77.9},{"place":24,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":77.9},{"place":25,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":76.5},{"place":26,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":75.3},{"place":27,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":75.1},{"place":28,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":74.9},{"place":29,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":74.9},{"place":30,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":74.8},{"place":31,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":74.6},{"place":32,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74.3},{"place":33,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":73.4},{"place":34,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":72.6},{"place":35,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":70},{"place":36,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":68.8},{"place":37,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":67.2},{"place":38,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.9},{"place":39,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":63.6},{"place":40,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":56.1},{"place":41,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":55.6},{"place":42,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":53.9},{"place":43,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":50.8},{"place":44,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":46},{"place":45,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":41.6},{"place":46,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":36.6},{"place":47,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":31.5},{"place":48,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":29.4},{"place":49,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":25.8},{"place":50,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":21.4}]},{"id":"information-extraction","name":"Information Extraction","topic":"Information extraction","description":"Information extraction benchmark for economically valuable fields.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.5","top_percent":46.9,"top_model_id":"claude-sonnet-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Sonnet 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":46.9},{"place":2,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":46.1},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":46},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.6},{"place":5,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":43.7}]},{"id":"information-processing","name":"Information Processing","topic":"Information processing","description":"Information processing benchmark for economically valuable tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":56.5,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.5},{"place":2,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55},{"place":3,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":54.3},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":53.9},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.4}]},{"id":"infotabs","name":"InfoTabs","topic":"Table NLI","description":"Natural language inference over infobox tables (MMTab subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":89.7,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":89.7},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":81.8},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":74.4},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":69.3},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":64.3},{"place":6,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.6}]},{"id":"infovqa","name":"InfoVQA","topic":"Infographic VQA","description":"Visual question answering over infographics requiring reading, counting, and reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2.5 Thinking","top_percent":92.6,"top_model_id":"kimi-k2.5-thinking","top_generation":"Kimi K2.5","top_model_base":"Kimi K2.5","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":166,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":92.6},{"place":2,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":91.2},{"place":3,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":91.2},{"place":4,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":90.9},{"place":5,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":89.8},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.5},{"place":7,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":89.1},{"place":8,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.2},{"place":9,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":88},{"place":10,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87.3},{"place":11,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":87.2},{"place":12,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87},{"place":13,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":86.8},{"place":14,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":86.26},{"place":15,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86},{"place":16,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85.24},{"place":17,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":84.8},{"place":18,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":84.6},{"place":19,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":84.5},{"place":20,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":84.5},{"place":21,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.4},{"place":22,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":84.4},{"place":23,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.3},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.2},{"place":25,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":84.1},{"place":26,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":84},{"place":27,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":83.6},{"place":28,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":83.3},{"place":29,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":83.3},{"place":30,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.1},{"place":31,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":83.1},{"place":32,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.2},{"place":33,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":82.1},{"place":34,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82},{"place":35,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":82},{"place":36,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":81.9},{"place":37,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":81.9},{"place":38,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.8},{"place":39,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":81.5},{"place":40,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":81.4},{"place":41,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":81.4},{"place":42,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":81.1},{"place":43,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":81},{"place":44,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":80.8},{"place":45,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":80.33},{"place":46,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.3},{"place":47,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.3},{"place":48,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":80.3},{"place":49,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":80.3},{"place":50,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":80.1},{"place":51,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":79.8},{"place":52,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.5},{"place":53,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":79.2},{"place":54,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":79.2},{"place":55,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":79.1},{"place":56,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":79.1},{"place":57,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":79},{"place":58,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":78.7},{"place":59,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":78.6},{"place":60,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":78.3},{"place":61,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":78.1},{"place":62,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":78.1},{"place":63,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78},{"place":64,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":78},{"place":65,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":77.8},{"place":66,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":77.6},{"place":67,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":77.6},{"place":68,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":77.1},{"place":69,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.9},{"place":70,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.9},{"place":71,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":76.5},{"place":72,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":76.5},{"place":73,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":76.12},{"place":74,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":75.94},{"place":75,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":75.9},{"place":76,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":75.8},{"place":77,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":75.8},{"place":78,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":75.5},{"place":79,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":75.2},{"place":80,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":75.2},{"place":81,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":75.1},{"place":82,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":75},{"place":83,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":75},{"place":84,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":74.9},{"place":85,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":74.8},{"place":86,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":74.7},{"place":87,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74.3},{"place":88,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74.1},{"place":89,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":74},{"place":90,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":73.76},{"place":91,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.5},{"place":92,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":73.4},{"place":93,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.1},{"place":94,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":73},{"place":95,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":72.7},{"place":96,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":72.6},{"place":97,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":72.5},{"place":98,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.4},{"place":99,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":72.1},{"place":100,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":72},{"place":101,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.9},{"place":102,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":71.84},{"place":103,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":71.6},{"place":104,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":70.8},{"place":105,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":70.7},{"place":106,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":70.6},{"place":107,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":70.2},{"place":108,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":70.1},{"place":109,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":70},{"place":110,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":69.9},{"place":111,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":69.9},{"place":112,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":69.6},{"place":113,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":69.4},{"place":114,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":69.3},{"place":115,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":69.29},{"place":116,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":68.9},{"place":117,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":68.8},{"place":118,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":68.6},{"place":119,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":68.3},{"place":120,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":67.8},{"place":121,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":67.4},{"place":122,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":67.37},{"place":123,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":67.3},{"place":124,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":67.1},{"place":125,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67},{"place":126,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":66.8},{"place":127,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":66.3},{"place":128,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":66.1},{"place":129,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":66.1},{"place":130,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":65.5},{"place":131,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":65.5},{"place":132,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":65.5},{"place":133,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":65.2},{"place":134,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":64},{"place":135,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":62.71},{"place":136,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":62.7},{"place":137,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.2},{"place":138,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.2},{"place":139,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":60.99},{"place":140,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":60.9},{"place":141,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":60.9},{"place":142,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":60.7},{"place":143,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":59.7},{"place":144,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":59.5},{"place":145,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":58.9},{"place":146,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":58.9},{"place":147,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":58.5},{"place":148,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":58.35},{"place":149,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":58.3},{"place":150,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":57.2},{"place":151,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":56.1},{"place":152,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":56},{"place":153,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":55.6},{"place":154,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":55.41},{"place":155,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":54.7},{"place":156,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":54.5},{"place":157,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.4},{"place":158,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":53.9},{"place":159,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":51.9},{"place":160,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":51.5},{"place":161,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":51},{"place":162,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":50.9},{"place":163,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":50.8},{"place":164,"model":"docowl-1.5-chat","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Chat","score":50.7},{"place":165,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":50.5},{"place":166,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":49.2},{"place":167,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":49.2},{"place":168,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":49},{"place":169,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":47.3},{"place":170,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":46.9},{"place":171,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":46.4},{"place":172,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":46},{"place":173,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":46},{"place":174,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":44.56},{"place":175,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":44.5},{"place":176,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":43.02},{"place":177,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":43},{"place":178,"model":"ureader","company":"alibaba","family":"mPLUG","version":"UReader","score":42.2},{"place":179,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":41.8},{"place":180,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":39.5},{"place":181,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":38.3},{"place":182,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":38},{"place":183,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":37.75},{"place":184,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":37.6},{"place":185,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":36.6},{"place":186,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":36.4},{"place":187,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":34.4},{"place":188,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":30},{"place":189,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":28.6},{"place":190,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":24.64},{"place":191,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":23.92},{"place":192,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":22.07},{"place":193,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":21.3},{"place":194,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":20.2},{"place":195,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":14.1},{"place":196,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":6.2}]},{"id":"inscit","name":"INSCIT","topic":"Conversational QA","description":"Information-seeking conversations with mixed-initiative (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":40,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":40},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":34.4},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":33.2},{"place":4,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":32.1},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":30.9},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":30.3},{"place":7,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":30},{"place":8,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":28.7},{"place":9,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":26.7},{"place":10,"model":"o3","company":"openai","family":"o3","version":"o3","score":26.7}]},{"id":"intention-recognition","name":"Intention Recognition","topic":"Intent recognition","description":"Intent recognition benchmark for practical applications.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":65.3,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65.3},{"place":2,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":63.8},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":63.2},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.7},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":58.3}]},{"id":"intphys-2","name":"IntPhys 2","topic":"Intuitive physics","description":"Intuitive physics reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Spark Open","top_percent":68.3,"top_model_id":"muse-spark-open","top_generation":"Muse Spark Open","top_model_base":"Muse Spark Open","top_model_family":"Muse","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":68.3},{"place":2,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":63.4},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":60.3},{"place":4,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":59.2},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":58.3},{"place":6,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":58},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.9},{"place":8,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.3},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.3},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":56},{"place":11,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":55.2},{"place":12,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":55},{"place":13,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":54.9},{"place":14,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.1},{"place":15,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":53},{"place":16,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":52},{"place":17,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51.9},{"place":18,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":51}]},{"id":"inverse-ifeval","name":"Inverse IFEval","topic":"Instruction following (inverse)","description":"Inverse instruction-following evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Flash","top_percent":80.9,"top_model_id":"gemini-3-flash","top_generation":"Gemini 3","top_model_base":"Gemini 3 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":80.9},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80.6},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":80.3},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":79.6},{"place":5,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":78.9},{"place":6,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":78.9},{"place":7,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.1},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.3},{"place":9,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":74.8},{"place":10,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.4},{"place":11,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":72.3},{"place":12,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.2},{"place":13,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.3},{"place":14,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":69.3},{"place":15,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":46.84},{"place":16,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":45.26},{"place":17,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42},{"place":18,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":39.75},{"place":19,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":36.02},{"place":20,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":35.25},{"place":21,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.98},{"place":22,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.04}]},{"id":"ioi-2025","name":"IOI 2025","topic":"Competitive programming","description":"International Olympiad in Informatics 2025 problem set; total score out of 600 points.","url":"https://ioi2025.bo/","leaderboard":"","github":"","paper":"","metric":"points","stars":"","top_model":"Kimi-K2.6 Thinking","top_percent":585,"top_model_id":"kimi-k2.6-thinking","top_generation":"Kimi K2.6","top_model_base":"Kimi K2.6","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":585},{"place":2,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":580.1},{"place":3,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":570},{"place":4,"model":"nemotron-labs-3-competitive-coding-550b-a55b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":502},{"place":5,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":456.5},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":441.3},{"place":7,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":439.3},{"place":8,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":348.6}]},{"id":"ipho-2025-theory","name":"IPhO 2025 (Theory)","topic":"Physics olympiad","description":"Theory problems of the 2025 International Physics Olympiad.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.4 Pro","top_percent":93.5,"top_model_id":"gpt-5.4-pro","top_generation":"GPT-5.4","top_model_base":"GPT-5.4 Pro","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":93.5},{"place":2,"model":"gemini-3.1-deep-think","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.7},{"place":3,"model":"muse-spark-contemplating","company":"meta","family":"Muse","version":"Muse Spark","score":82.6}]},{"id":"isarcasmeval","name":"iSarcasmEval","topic":"Sarcasm detection","description":"SemEval-2022 iSarcasmEval track A (English) sarcasm F1 (Jev Decision Index suite, posed as typed decisions).","url":"https://github.com/iabufarha/iSarcasmEval","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"pplx-decider-v1.2","top_percent":74.7,"top_model_id":"pplx-decider-v1.2","top_generation":"v1.2","top_model_base":"pplx-decider","top_model_family":"pplx-decider","top_company":"perplexity","top_open_source":1,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":74.7},{"place":2,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":66.8},{"place":3,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":60.3},{"place":4,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":59.4},{"place":5,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":56.2},{"place":6,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":55.4},{"place":7,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":53.7},{"place":8,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":53.5},{"place":9,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":53.3},{"place":10,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":51.6},{"place":11,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":50.5},{"place":12,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":50.2},{"place":13,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":46.4},{"place":14,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":46.4},{"place":15,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":43.1},{"place":16,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":42},{"place":17,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":40.1},{"place":18,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":39.7},{"place":19,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":39.5},{"place":20,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":37.2},{"place":21,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":36},{"place":22,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":35.9},{"place":23,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":34.6},{"place":24,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":32.9},{"place":25,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":32.4},{"place":26,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":31.7},{"place":27,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":29.6},{"place":28,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":28.7},{"place":29,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":27.5},{"place":30,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":26.3},{"place":31,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":23.4},{"place":32,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":21.3},{"place":33,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":21.2},{"place":34,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":19.7},{"place":35,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":16.3}]},{"id":"isl-osl-8k-16k","name":"ISL/OSL 8k/16k","topic":"Throughput","description":"Relative throughput on ISL/OSL 8k/16k context workloads.","url":"","leaderboard":"","github":"","paper":"","metric":"relative_throughput","stars":"","top_model":"Nemotron-3-Nano-30B-A3B","top_percent":3.3,"top_model_id":"nemotron-3-nano-30b-a3b","top_generation":"Nemotron 3","top_model_base":"Nemotron-3 Nano 30B A3B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.3},{"place":2,"model":"gpt-oss-20b-a4b","company":"openai","family":"GPT","version":"GPT-OSS","score":1.5},{"place":3,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1}]},{"id":"jamc-qa","name":"JamC-QA","topic":"Japanese knowledge QA","description":"Japanese-specific knowledge multiple-choice QA (culture, customs, regional, law, medicine) from the Swallow evaluation suite.","url":"https://swallow-llm.github.io/leaderboard/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 mini","top_percent":70.1,"top_model_id":"gpt-5-mini","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":70.1},{"place":2,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.9},{"place":3,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":63},{"place":4,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":61.1},{"place":5,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":59.5},{"place":6,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":58.9},{"place":7,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":55.1},{"place":8,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":53.4},{"place":9,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":53.3},{"place":10,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":52.8},{"place":11,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":51.6},{"place":12,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":51.3},{"place":13,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":50.4},{"place":14,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":49.6},{"place":15,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":49.6},{"place":16,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":49.5},{"place":17,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":49.3},{"place":18,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":48.8},{"place":19,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":47.9},{"place":20,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":46},{"place":21,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":45.5},{"place":22,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":44.9},{"place":23,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":44.4},{"place":24,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":43.9},{"place":25,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":43.8},{"place":26,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":40.3},{"place":27,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":39.8},{"place":28,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":36.2},{"place":29,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":35.3},{"place":30,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":27.9},{"place":31,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":27.6}]},{"id":"jculture","name":"JCulture","topic":"Japanese culture knowledge","description":"Japanese culture knowledge QA benchmark (as reported by Liquid AI).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 1.2B JP 202606","top_percent":35.77,"top_model_id":"lfm2.5-1.2b-jp-202606","top_generation":"LFM2.5","top_model_base":"LFM2.5 1.2B JP","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":35.77},{"place":2,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":34.38},{"place":3,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":33.33},{"place":4,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":31.17},{"place":5,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":29.67},{"place":6,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":28.42},{"place":7,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":27.42},{"place":8,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":25.53},{"place":9,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":23.42},{"place":10,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":22.52}]},{"id":"jec-qa","name":"JEC-QA","topic":"Legal QA (Chinese)","description":"Chinese National Judicial Examination multiple-choice QA.","url":"https://jecqa.thunlp.org/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1911.12011","metric":"percent","stars":"","top_model":"GPT-4","top_percent":59.32,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":59.32},{"place":2,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":47.4},{"place":3,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":46.42},{"place":4,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":44.46},{"place":5,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":42.31},{"place":6,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":41.34},{"place":7,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":40.76},{"place":8,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":35.32},{"place":9,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":34.64},{"place":10,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":34.08},{"place":11,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":29.2},{"place":12,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":28.38},{"place":13,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":27.54},{"place":14,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":27.45},{"place":15,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":27.45},{"place":16,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":23.66}]},{"id":"jevbench","name":"JevBench (Benchmark Heaven)","topic":"Typed decisions","description":"Benchmark Heaven JevBench for typed probabilistic decision models; score is the chance-corrected Intelligence (typed decision accuracy) axis.","url":"https://benchmarkheaven.com/jev-models","leaderboard":"https://benchmarkheaven.com/jev-models","github":"https://github.com/fstandhartinger/jevbench","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna (medium)","top_percent":96.9,"top_model_id":"gpt-6-luna-medium","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":96.9},{"place":2,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":96.6},{"place":3,"model":"pplx-decider-v1.1-27b","company":"perplexity","family":"pplx-decider","version":"v1.1","score":75.7},{"place":4,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":73.7},{"place":5,"model":"quyet-1.0-large","company":"chinhnc","family":"Quyet","version":"Quyet-1.0","score":73.4},{"place":6,"model":"d1-ultra","company":"liquidai","family":"d1","version":"d1","score":69.7},{"place":7,"model":"glide","company":"fastino","family":"GLiDE","version":"GLiDE","score":66.1},{"place":8,"model":"mercury-decide","company":"inception","family":"Mercury","version":"Mercury Decide","score":65.9},{"place":9,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":63.6},{"place":10,"model":"d1","company":"liquidai","family":"d1","version":"d1","score":62.1},{"place":11,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":60.4},{"place":12,"model":"h2o-lightning-4b","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":60},{"place":13,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":59.9},{"place":14,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":59.1},{"place":15,"model":"celeris-1-decision","company":"celeris","family":"Celeris","version":"Celeris-1","score":58.9},{"place":16,"model":"microsoft-decision-1","company":"microsoft","family":"Microsoft-Decision","version":"Microsoft-Decision-1","score":57.2},{"place":17,"model":"gpt-6-luna-decisions","company":"openai","family":"GPT","version":"GPT-6","score":56.9},{"place":18,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":56.8},{"place":19,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":56.5},{"place":20,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":42.2},{"place":21,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":35.8},{"place":22,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":34.5},{"place":23,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":22.1},{"place":24,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":7},{"place":25,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":3.3}]},{"id":"jevbench-public","name":"JevBench public set","topic":"Typed decisions","description":"Accuracy on JevBench's 231 public items (easy, original/standard and hard tiers).","url":"https://github.com/fstandhartinger/jevbench","leaderboard":"","github":"https://github.com/fstandhartinger/jevbench","paper":"","metric":"percent","stars":"","top_model":"strands-decider-26B-A4B-gemma4-v1-2610","top_percent":89.6,"top_model_id":"strands-decider-26b-a4b","top_generation":"v1-2610","top_model_base":"strands-decider","top_model_family":"strands-decider","top_company":"amazon","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"strands-decider-26b-a4b","company":"amazon","family":"strands-decider","version":"v1-2610","score":89.6},{"place":2,"model":"h2o-lightning-4b","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":87.9},{"place":3,"model":"strands-decider-12b","company":"amazon","family":"strands-decider","version":"v1-2610","score":86.6},{"place":4,"model":"h2o-lightning-4b-nemotron-nano","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":83.1},{"place":5,"model":"strands-decider-e4b","company":"amazon","family":"strands-decider","version":"v1-2610","score":81},{"place":6,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":77.9},{"place":7,"model":"strands-decider-e2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":77.9}]},{"id":"jevbench-public-easy","name":"JevBench public (easy)","topic":"Typed decisions","description":"Accuracy on the 48-item easy tier of JevBench's public set.","url":"https://github.com/fstandhartinger/jevbench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Jev 1.13","top_percent":100,"top_model_id":"jev-1.13","top_generation":"Jev 1.13","top_model_base":"Jev 1.13","top_model_family":"Jev","top_company":"typesafe","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":100},{"place":2,"model":"semif","company":"theoleecj","family":"SemIf","version":"SemIf","score":100},{"place":3,"model":"jevk5","company":"alibiserikbay","family":"JevK5","version":"JevK5","score":100},{"place":4,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":100},{"place":5,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":100},{"place":6,"model":"h2o-lightning-4b","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":100},{"place":7,"model":"h2o-lightning-4b-nemotron-nano","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":100},{"place":8,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":100},{"place":9,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":97.92},{"place":10,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":95.83}]},{"id":"jevbench-public-hard","name":"JevBench public (hard)","topic":"Typed decisions","description":"Accuracy on the hard tier of JevBench's public set.","url":"https://github.com/fstandhartinger/jevbench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"H2O-Lightning-4B","top_percent":76.6,"top_model_id":"h2o-lightning-4b","top_generation":"H2O-Lightning","top_model_base":"H2O-Lightning-4B","top_model_family":"H2O-Lightning","top_company":"h2oai","top_open_source":1,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"h2o-lightning-4b","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":76.6},{"place":2,"model":"jevk5","company":"alibiserikbay","family":"JevK5","version":"JevK5","score":73.87},{"place":3,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":73.87},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":72.07},{"place":5,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":70.3},{"place":6,"model":"h2o-lightning-4b-nemotron-nano","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":65.8},{"place":7,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":63.96},{"place":8,"model":"semif","company":"theoleecj","family":"SemIf","version":"SemIf","score":61.26},{"place":9,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":58.6},{"place":10,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":52.25},{"place":11,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":28.83}]},{"id":"jevbench-public-original","name":"JevBench public (original/standard)","topic":"Typed decisions","description":"Accuracy on the 72-item original (standard) tier of JevBench's public set.","url":"https://github.com/fstandhartinger/jevbench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Jev 1.13","top_percent":98.61,"top_model_id":"jev-1.13","top_generation":"Jev 1.13","top_model_base":"Jev 1.13","top_model_family":"Jev","top_company":"typesafe","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":98.61},{"place":2,"model":"semif","company":"theoleecj","family":"SemIf","version":"SemIf","score":98.61},{"place":3,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":98.61},{"place":4,"model":"h2o-lightning-4b-nemotron-nano","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":98.6},{"place":5,"model":"jevk5","company":"alibiserikbay","family":"JevK5","version":"JevK5","score":97.22},{"place":6,"model":"h2o-lightning-4b","company":"h2oai","family":"H2O-Lightning","version":"H2O-Lightning","score":97.2},{"place":7,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":93.1},{"place":8,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":84.72},{"place":9,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":80.56},{"place":10,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":72.22}]},{"id":"jfbench","name":"JFBench","topic":"Instruction following (Japanese)","description":"Japanese instruction-following benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 1.2B JP 202606","top_percent":54.77,"top_model_id":"lfm2.5-1.2b-jp-202606","top_generation":"LFM2.5","top_model_base":"LFM2.5 1.2B JP","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":54.77},{"place":2,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":36.67},{"place":3,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.61},{"place":4,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":34.25},{"place":5,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":31.26},{"place":6,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":31.15},{"place":7,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":30.92},{"place":8,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":27.41},{"place":9,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":24.66},{"place":10,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":21.78}]},{"id":"jgpqa","name":"JGPQA","topic":"Graduate-level QA (Japanese)","description":"Japanese translation of GPQA graduate-level science QA.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 mini","top_percent":75,"top_model_id":"gpt-5-mini","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":41,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":75},{"place":2,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.9},{"place":3,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":71},{"place":4,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":70.5},{"place":5,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":66.3},{"place":6,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":63.6},{"place":7,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":62.9},{"place":8,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":60.7},{"place":9,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":59.6},{"place":10,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":59.4},{"place":11,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":57.8},{"place":12,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":57.6},{"place":13,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":57.1},{"place":14,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":57.1},{"place":15,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.8},{"place":16,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":55.8},{"place":17,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":55.6},{"place":18,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":54.7},{"place":19,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":54.7},{"place":20,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":52.9},{"place":21,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":52.7},{"place":22,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":49.1},{"place":23,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":48.7},{"place":24,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":44.6},{"place":25,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":41.7},{"place":26,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":40.4},{"place":27,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":39.3},{"place":28,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":34.6},{"place":29,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":32.32},{"place":30,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":32.1},{"place":31,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":31.72},{"place":32,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":31},{"place":33,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":29.5},{"place":34,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":29.29},{"place":35,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":28.69},{"place":36,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.26},{"place":37,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":26.26},{"place":38,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":24.44},{"place":39,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":24.24},{"place":40,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":22.22},{"place":41,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":17.68}]},{"id":"jhumaneval","name":"JHumanEval","topic":"Code (Japanese)","description":"Japanese-prompt translation of HumanEval code generation benchmark.","url":"https://github.com/KuramitsuLab/jhuman-eval","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 mini","top_percent":94.5,"top_model_id":"gpt-5-mini","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":94.5},{"place":2,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.8},{"place":3,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":93.5},{"place":4,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":93},{"place":5,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":92.7},{"place":6,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":92.7},{"place":7,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":92.5},{"place":8,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":92.4},{"place":9,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":92.3},{"place":10,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":92.2},{"place":11,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":91.5},{"place":12,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":91},{"place":13,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":91},{"place":14,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":90.9},{"place":15,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":90.9},{"place":16,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":90.4},{"place":17,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.9},{"place":18,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":89.4},{"place":19,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":88.8},{"place":20,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":88.5},{"place":21,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":88.5},{"place":22,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":86.9},{"place":23,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":86.7},{"place":24,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":86.6},{"place":25,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":83.3},{"place":26,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":83},{"place":27,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":79.8},{"place":28,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":79.6},{"place":29,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":72.1},{"place":30,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":70.2},{"place":31,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":58.4}]},{"id":"jhumaneval-plus","name":"JHumanEval+","topic":"Code (Japanese)","description":"Japanese-prompt HumanEval+ code generation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Granite-4.0-1B","top_percent":51.22,"top_model_id":"granite-4.0-1b","top_generation":"Granite 4.0","top_model_base":"Granite 4.0 1B","top_model_family":"Granite","top_company":"IBM","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":51.22},{"place":2,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":49.39},{"place":3,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.56},{"place":4,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":35.37},{"place":5,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":28.66},{"place":6,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":28.6},{"place":7,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":26.83},{"place":8,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":25},{"place":9,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":21.95},{"place":10,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":17.68}]},{"id":"jmmlu","name":"JMMLU","topic":"Multi-domain knowledge (Japanese)","description":"Japanese Massive Multitask Language Understanding benchmark (translated and culture-specific MMLU questions).","url":"https://github.com/nlp-waseda/JMMLU","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen2.5-72B-Instruct","top_percent":80.56,"top_model_id":"qwen2.5-72b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.56},{"place":2,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":77.37},{"place":3,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.55},{"place":4,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":75.77},{"place":5,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":73.89},{"place":6,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":73.74},{"place":7,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.78},{"place":8,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":64.59},{"place":9,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":61.88},{"place":10,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":57.71},{"place":11,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":55.17},{"place":12,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":54.19},{"place":13,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":53.26},{"place":14,"model":"lfm2.5-1.2b-jp","company":"liquidai","family":"LFM","version":"LFM2.5","score":50.7},{"place":15,"model":"gemma-2-llama-swallow-2b-it-v0.1","company":"tokyotech","family":"Swallow","version":"Gemma-2-Llama Swallow","score":48.1},{"place":16,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":48},{"place":17,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":47.98},{"place":18,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":47.7},{"place":19,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.7},{"place":20,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.67},{"place":21,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":47.61},{"place":22,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":43.05},{"place":23,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":42.2},{"place":24,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":40.24},{"place":25,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":40.2},{"place":26,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":34.5},{"place":27,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":34.45},{"place":28,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":34},{"place":29,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":33.97},{"place":30,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":33.93},{"place":31,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":31.84}]},{"id":"jobbench","name":"JobBench","topic":"Professional tool use","description":"Agentic benchmark of professional, job-like tasks requiring tool use.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":75.4,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":51,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":75.4},{"place":2,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":75.3},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":73.1},{"place":4,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":70.5},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":66.1},{"place":7,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":65.7},{"place":8,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":64.9},{"place":9,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":62},{"place":10,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":61.8},{"place":11,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":61.7},{"place":12,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":61.6},{"place":13,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":61.4},{"place":14,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":61.2},{"place":15,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":58.2},{"place":16,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":57.5},{"place":17,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57.4},{"place":18,"model":"iquest-q1","company":"iquest","family":"IQuest","version":"IQuest Q1","score":55.7},{"place":19,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":54.7},{"place":20,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":54.3},{"place":21,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.1},{"place":22,"model":"nex-n2.5-max","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":53.6},{"place":23,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":53.4},{"place":24,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":52.9},{"place":25,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":52.7},{"place":26,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":52.57},{"place":27,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":50.3},{"place":28,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50},{"place":29,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":49.7},{"place":30,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":48.4},{"place":31,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":45.4},{"place":32,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":44.8},{"place":33,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":43.81},{"place":34,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":43.4},{"place":35,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":41.4},{"place":36,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":38.3},{"place":37,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":34.6},{"place":38,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":34.5},{"place":39,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":33.79},{"place":40,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":31.1},{"place":41,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":30.1},{"place":42,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":28.5},{"place":43,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":27.2},{"place":44,"model":"fx-work","company":"endless-frontier","family":"Fx","version":"Fx","score":25.19},{"place":45,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":25},{"place":46,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":19.18},{"place":47,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":18.9},{"place":48,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":18.88},{"place":49,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":18.62},{"place":50,"model":"mimo-v2.6-distill-qwen-9b","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":18.3},{"place":51,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":17},{"place":52,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":16.6},{"place":53,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":15.9},{"place":54,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":14.99},{"place":55,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":9.39},{"place":56,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":9},{"place":57,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":7.97},{"place":58,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":7.19},{"place":59,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.6}]},{"id":"jobbench-easy","name":"JobBench (Easy)","topic":"Professional job tasks","description":"JobBench easy split of realistic professional job tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":82.81,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.81},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.72},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":78.22},{"place":4,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":75.49},{"place":5,"model":"fx-work","company":"endless-frontier","family":"Fx","version":"Fx","score":70.06},{"place":6,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":65.49},{"place":7,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64.59},{"place":8,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.08},{"place":9,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":63.13},{"place":10,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":56.02},{"place":11,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":52.93},{"place":12,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":44.38},{"place":13,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":41.74}]},{"id":"judgebench","name":"JudgeBench","topic":"LLM-as-judge","description":"Pairwise response-correctness judgement benchmark for LLM judges.","url":"https://github.com/ScalerLab/JudgeBench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2410.12784","metric":"percent","stars":"","top_model":"Jev 1.13","top_percent":78.57,"top_model_id":"jev-1.13","top_generation":"Jev 1.13","top_model_base":"Jev 1.13","top_model_family":"Jev","top_company":"typesafe","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":78.57},{"place":2,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":78.29}]},{"id":"judgemark-v2-1","name":"JudgeMark v2.1","topic":"LLM judging ability","description":"A benchmark measuring LLM judging ability.","url":"","leaderboard":"https://eqbench.com/judgemark-v2.html","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.6","top_percent":94.08,"top_model_id":"claude-sonnet-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Sonnet 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":94.08},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":92.93},{"place":3,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":86.58},{"place":4,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":85.58},{"place":5,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.45},{"place":6,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":85.38},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":84.98},{"place":8,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.56},{"place":9,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.31},{"place":10,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":82.01},{"place":11,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":81.99},{"place":12,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.85},{"place":13,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.39},{"place":14,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.2},{"place":15,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":81.2},{"place":16,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":81.14},{"place":17,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.03},{"place":18,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.92},{"place":19,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.72},{"place":20,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":77.48},{"place":21,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":76.31},{"place":22,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":75.82},{"place":23,"model":"o3","company":"openai","family":"o3","version":"o3","score":75.1},{"place":24,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.99},{"place":25,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":74.49},{"place":26,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":74.49},{"place":27,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73.09},{"place":28,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.06},{"place":29,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":68.2},{"place":30,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":66.28},{"place":31,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":66.18},{"place":32,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":64.47},{"place":33,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":64.46},{"place":34,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":63.41},{"place":35,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.97},{"place":36,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":61.08},{"place":37,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":59.69},{"place":38,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":58.53},{"place":39,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":57.26},{"place":40,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.18},{"place":41,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":56.1},{"place":42,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.99},{"place":43,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":54.78},{"place":44,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":52.2},{"place":45,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":51.6},{"place":46,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":50.21},{"place":47,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":42.8},{"place":48,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":34.58},{"place":49,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":19.18}]},{"id":"kernelbench-hard","name":"KernelBench Hard","topic":"GPU kernel optimization","description":"KernelBench Hard: agents write optimized GPU kernels; score relative to hardware peak throughput.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":30.7,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":30.7},{"place":2,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":28.8},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":20.9},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":18.6},{"place":5,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":10.5}]},{"id":"kernelgen-1p","name":"KernelGen 1P","topic":"AI research automation","description":"OpenAI internal eval (GPT-5.6 announcement): optimizing GPU kernels.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":66.72,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":66.72},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":61.1},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":61.08},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":60.44},{"place":5,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":49.2},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":45.34},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":38.12},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":29.3},{"place":9,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":22.4}]},{"id":"kgc-safety","name":"KGC-Safety","topic":"Safety (Korean)","description":"Korean safety benchmark evaluating harmfulness and compliance.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"K-EXAONE 2.0","top_percent":99.8,"top_model_id":"k-exaone-2.0","top_generation":"K-EXAONE 2.0","top_model_base":"K-EXAONE 2.0","top_model_family":"K-EXAONE","top_company":"lg","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":99.8},{"place":2,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":96.1},{"place":3,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":92.5},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92},{"place":5,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.8},{"place":6,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":73},{"place":7,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":69.3},{"place":8,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.2},{"place":9,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":58}]},{"id":"kimi-claw-24-7-bench","name":"Kimi Claw 24/7 Bench","topic":"Long-horizon agents","description":"Moonshot in-house benchmark of persistent multi-day coworking tasks (17 scenarios, 610 evaluation points) run through the OpenClaw harness; average pass rate over 3 runs.","url":"https://huggingface.co/moonshotai/Kimi-K2.7-Code","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":52.8,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":52.8},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":50.4},{"place":3,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":46.9},{"place":4,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":42.9}]},{"id":"kimi-code-bench-v2","name":"Kimi Code Bench v2","topic":"Agentic coding","description":"Moonshot in-house coding-agent benchmark (Kimi Code Bench 2.0): realistic software engineering tasks across 10+ languages and production tech stacks.","url":"https://huggingface.co/moonshotai/Kimi-K2.7-Code","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":76.9,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":76.9},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":72.9},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":71.7},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":67.4},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.8},{"place":7,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":64.2},{"place":8,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":62},{"place":9,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":50.9}]},{"id":"kimi-code-bench-v3-long-horizon","name":"Kimi Code Bench 3.0 Long-horizon","topic":"Agentic coding","description":"Moonshot in-house long-horizon coding-agent benchmark (Kimi Code Bench 3.0, long-horizon split).","url":"https://www.kimi.ai/blog/kimi-k3-1-pro","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":66.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":66.5},{"place":2,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":61.2},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":58.8},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":58.5},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":55.95},{"place":6,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":51.5},{"place":7,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":45.5}]},{"id":"kimi-hallu-bench","name":"Kimi Hallu Bench","topic":"Hallucination","description":"Moonshot in-house benchmark: percentage of factual claims containing errors, without tools (lower is better).","url":"https://www.kimi.ai/blog/kimi-k3-1-pro","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":4.2,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":4.2},{"place":2,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":5.4},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":6.8},{"place":4,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":11.4},{"place":5,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":13.1},{"place":6,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":14.8}]},{"id":"kimi-hallu-bench-hard-with-tools","name":"Kimi Hallu Bench Hard (With Tools)","topic":"Hallucination","description":"Moonshot in-house hard hallucination benchmark with tools: percentage of factual claims containing errors (lower is better).","url":"https://www.kimi.ai/blog/kimi-k3-1-pro","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":5.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":5.5},{"place":2,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":8.3},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":15},{"place":4,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":22.6},{"place":5,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":23.3},{"place":6,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":23.3},{"place":7,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":23.4}]},{"id":"kina","name":"KINA","topic":"Knowledge","description":"Knowledge benchmark of culturally grounded factual questions (reported in the Seed2.1 model card).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":53.2,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":53.2},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":52.6},{"place":3,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":48.3},{"place":4,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":46.7},{"place":5,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":46.6}]},{"id":"kk-4-people","name":"KK-4 People","topic":"Working memory (4 people)","description":"Keep/kill working-memory benchmark with 4 people entities.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"K2-V2","top_percent":92.9,"top_model_id":"k2-v2","top_generation":"K2 V2","top_model_base":"K2 V2","top_model_family":"K2","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":92.9},{"place":2,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":42.4},{"place":3,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.1},{"place":4,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":7.6},{"place":5,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":4.8},{"place":6,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":4.2}]},{"id":"kk-8-people","name":"KK-8 People","topic":"Working memory (8 people)","description":"Keep/kill working-memory benchmark with 8 people entities.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"K2-V2","top_percent":82.8,"top_model_id":"k2-v2","top_generation":"K2 V2","top_model_base":"K2 V2","top_model_family":"K2","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":82.8},{"place":2,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":13},{"place":3,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":5.7},{"place":4,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":1.3},{"place":5,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":1.1},{"place":6,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":0.5}]},{"id":"kmmlu","name":"KMMLU","topic":"Korean knowledge","description":"Korean Massive Multitask Language Understanding benchmark.","url":"https://huggingface.co/datasets/HAERAE-HUB/KMMLU","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V3.1","top_percent":78.7,"top_model_id":"deepseek-v3.1","top_generation":"DeepSeek V3.1","top_model_base":"DeepSeek V3.1","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":29,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":78.7},{"place":2,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":77.7},{"place":3,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":73},{"place":4,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":68.26},{"place":5,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":67.56},{"place":6,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":67.32},{"place":7,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":65.75},{"place":8,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.49},{"place":9,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.25},{"place":10,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":62.25},{"place":11,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":62.15},{"place":12,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":62.15},{"place":13,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":61.98},{"place":14,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":61.96},{"place":15,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":61.56},{"place":16,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.75},{"place":17,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.71},{"place":18,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":57.04},{"place":19,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":56.77},{"place":20,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":56.42},{"place":21,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":53.23},{"place":22,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":50.28},{"place":23,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":47.92},{"place":24,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.59},{"place":25,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":46.24},{"place":26,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":44.17},{"place":27,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":43.96},{"place":28,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":43.08},{"place":29,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":42.28},{"place":30,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":42.22}]},{"id":"kmmlu-pro","name":"KMMLU-Pro","topic":"Multilingual knowledge","description":"Korean Multilingual Massive Multitask Language Understanding Pro","url":"https://huggingface.co/datasets/HAERAE-HUB/KMMLU","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Pro-Thinking (max)","top_percent":80.5,"top_model_id":"deepseek-v4-pro-thinking-max","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Pro","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":84,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.5},{"place":2,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":80.5},{"place":3,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":79.2},{"place":4,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.9},{"place":5,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.8},{"place":6,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":78.4},{"place":7,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.4},{"place":8,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":78.1},{"place":9,"model":"o1","company":"openai","family":"o1","version":"o1","score":77.54},{"place":10,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.4},{"place":11,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":76.5},{"place":12,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":75.98},{"place":13,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":75.8},{"place":14,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":75.51},{"place":15,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":73.4},{"place":16,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":73.33},{"place":17,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73},{"place":18,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":72.81},{"place":19,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":72.73},{"place":20,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":72.5},{"place":21,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":72.35},{"place":22,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":72.1},{"place":23,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.6},{"place":24,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.1},{"place":25,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":70.54},{"place":26,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":69.42},{"place":27,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":69.2},{"place":28,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":69.1},{"place":29,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":69.1},{"place":30,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":68.9},{"place":31,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":68.2},{"place":32,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":68.03},{"place":33,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":67.9},{"place":34,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.9},{"place":35,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":67.7},{"place":36,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":67.6},{"place":37,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":67.3},{"place":38,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":66.6},{"place":39,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.45},{"place":40,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":66.03},{"place":41,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":65.89},{"place":42,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":64.9},{"place":43,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64.75},{"place":44,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":64.55},{"place":45,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":64.32},{"place":46,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64.01},{"place":47,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":64},{"place":48,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":63.86},{"place":49,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":63.01},{"place":50,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":62.4},{"place":51,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":62.24},{"place":52,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":62.06},{"place":53,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.97},{"place":54,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":61.54},{"place":55,"model":"command-a","company":"cohere","family":"Command","version":"Command","score":61.46},{"place":56,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":60.3},{"place":57,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":60.15},{"place":58,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.4},{"place":59,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.39},{"place":60,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":55.27},{"place":61,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":54.63},{"place":62,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":53.02},{"place":63,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":50.91},{"place":64,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.92},{"place":65,"model":"phi-4-14b","company":"microsoft","family":"Phi","version":"Phi 4","score":44.33},{"place":66,"model":"exaone-4.0-1.2b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":42.69},{"place":67,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":41.06},{"place":68,"model":"ko-r1-7b-v2.1","company":"onelineai","family":"Ko-R1","version":"Ko-R1","score":38.7},{"place":69,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":38.6},{"place":70,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":38.3},{"place":71,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":38.27},{"place":72,"model":"hyperclovax-seed-text-instruct-1.5b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":38.1},{"place":73,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":37.48},{"place":74,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":33.81},{"place":75,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":33.27},{"place":76,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":32.86},{"place":77,"model":"kanana-nano-2.1b-instruct","company":"kakao","family":"Kanana Nano","version":"Kanana Nano","score":32.6},{"place":78,"model":"audio-flamingo-3","company":"nvidia","family":"Audio Flamingo","version":"Audio Flamingo 3","score":31.8},{"place":79,"model":"aya-expanse-8b","company":"cohere","family":"Aya","version":"Aya Expanse","score":31.65},{"place":80,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":31.1},{"place":81,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":30.5},{"place":82,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":30.42},{"place":83,"model":"aya-expanse-32b","company":"cohere","family":"Aya","version":"Aya Expanse","score":28.46},{"place":84,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":25.53},{"place":85,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":24.6},{"place":86,"model":"qwen2-audio-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Audio","score":23.8},{"place":87,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.6},{"place":88,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":20.55},{"place":89,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":18.7},{"place":90,"model":"x-omni","company":"tencent","family":"X-Omni","version":"X-Omni","score":17.7},{"place":91,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":16.4}]},{"id":"kmmlu-redux","name":"KMMLU-Redux","topic":"Multilingual knowledge","description":"Redux variant of KMMLU benchmark","url":"https://huggingface.co/datasets/HAERAE-HUB/KMMLU","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2507.08924","metric":"percent","stars":"","top_model":"o1","top_percent":81.14,"top_model_id":"o1","top_generation":"o1","top_model_base":"o1","top_model_family":"o1","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":53,"total_models":3854,"placements":[{"place":1,"model":"o1","company":"openai","family":"o1","version":"o1","score":81.14},{"place":2,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":79.92},{"place":3,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":79.36},{"place":4,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":78.51},{"place":5,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":77.58},{"place":6,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":76.88},{"place":7,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":75.9},{"place":8,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":75.86},{"place":9,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":75.8},{"place":10,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.49},{"place":11,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":73.4},{"place":12,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":72.9},{"place":13,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":72.71},{"place":14,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":71.47},{"place":15,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.54},{"place":16,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":68.77},{"place":17,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":68.3},{"place":18,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":67.84},{"place":19,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":67.49},{"place":20,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":67.34},{"place":21,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":67.03},{"place":22,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":65.71},{"place":23,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":65.64},{"place":24,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.25},{"place":25,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.98},{"place":26,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":64.79},{"place":27,"model":"command-a","company":"cohere","family":"Command","version":"Command","score":62.93},{"place":28,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":58.79},{"place":29,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.41},{"place":30,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":57.25},{"place":31,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":56.17},{"place":32,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":54.04},{"place":33,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":52.92},{"place":34,"model":"phi-4-14b","company":"microsoft","family":"Phi","version":"Phi 4","score":49.75},{"place":35,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.25},{"place":36,"model":"exaone-4.0-1.2b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":46.85},{"place":37,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":46.7},{"place":38,"model":"ko-r1-7b-v2.1","company":"onelineai","family":"Ko-R1","version":"Ko-R1","score":41.94},{"place":39,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":40.43},{"place":40,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":38},{"place":41,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.8},{"place":42,"model":"hyperclovax-seed-text-instruct-1.5b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":33.94},{"place":43,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":33.7},{"place":44,"model":"aya-expanse-32b","company":"cohere","family":"Aya","version":"Aya Expanse","score":33.05},{"place":45,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":31.89},{"place":46,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.99},{"place":47,"model":"aya-expanse-8b","company":"cohere","family":"Aya","version":"Aya Expanse","score":28.3},{"place":48,"model":"kanana-nano-2.1b-instruct","company":"kakao","family":"Kanana Nano","version":"Kanana Nano","score":27.25},{"place":49,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":25.09},{"place":50,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":25},{"place":51,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.74},{"place":52,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":24.5},{"place":53,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":21.3},{"place":54,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":17.59}]},{"id":"ko-longbench","name":"Ko-LongBench","topic":"Korean long-context","description":"Long-context understanding benchmark in Korean.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Pro-Thinking (max)","top_percent":91.4,"top_model_id":"deepseek-v4-pro-thinking-max","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Pro","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.4},{"place":2,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.3},{"place":3,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":89.6},{"place":4,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":87.9},{"place":5,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":86.8},{"place":6,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":83.6},{"place":7,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.2},{"place":8,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":82.2},{"place":9,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":68}]},{"id":"kobolt","name":"KoBALT","topic":"Korean knowledge","description":"Korean benchmark for knowledge and language understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Flash-Thinking (max)","top_percent":75.3,"top_model_id":"deepseek-v4-flash-thinking-max","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Flash","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.3},{"place":2,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":73},{"place":3,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":72},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":5,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":66},{"place":6,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":63.6},{"place":7,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.7},{"place":8,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":61.8},{"place":9,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":59.1},{"place":10,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":56.1},{"place":11,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.9},{"place":12,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":54.3},{"place":13,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":54},{"place":14,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":52.1},{"place":15,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":51.4},{"place":16,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.1},{"place":17,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":51},{"place":18,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":27.7},{"place":19,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":25.4},{"place":20,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":17.7},{"place":21,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":17.1},{"place":22,"model":"audio-flamingo-3","company":"nvidia","family":"Audio Flamingo","version":"Audio Flamingo 3","score":12.9},{"place":23,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":10.3},{"place":24,"model":"x-omni","company":"tencent","family":"X-Omni","version":"X-Omni","score":9.6},{"place":25,"model":"qwen2-audio-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Audio","score":8.9},{"place":26,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":5.9}]},{"id":"komt-bench","name":"KoMT-Bench","topic":"Korean chat ability","description":"Korean multi-turn chat evaluation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Qwen3-30B-A3B-Instruct-2507","top_percent":8.49,"top_model_id":"qwen3-30b-a3b-instruct-2507","top_generation":"Qwen3","top_model_base":"Qwen3 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":8.49},{"place":2,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":8.24},{"place":3,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":8.21},{"place":4,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":7.94},{"place":5,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":7.89},{"place":6,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":6.92},{"place":7,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":6.54},{"place":8,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.29},{"place":9,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5.21}]},{"id":"konet","name":"KoNET","topic":"Korean exams (multimodal)","description":"Korean National Educational Test benchmark (elementary to college entrance exams) with images.","url":"https://arxiv.org/abs/2502.15422","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":96.17,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":96.17},{"place":2,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":89.44},{"place":3,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":79.81},{"place":4,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":75.39},{"place":5,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":57.47},{"place":6,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":25.12}]},{"id":"kor-bench","name":"KOR-Bench","topic":"Reasoning","description":"Comprehensive reasoning benchmark spanning diverse domains and cognitive skills.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":77.4,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":77.4},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":76.2},{"place":3,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":76},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":75},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74.5},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.2},{"place":7,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":73.76},{"place":8,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73.2},{"place":9,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":70.56},{"place":10,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":69.44},{"place":11,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":69.2},{"place":12,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":68.96},{"place":13,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":68},{"place":14,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":65.12},{"place":15,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":64.24},{"place":16,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":63.2},{"place":17,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":63.04},{"place":18,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":62.8},{"place":19,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.68},{"place":20,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.96},{"place":21,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":50.64},{"place":22,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":49.92},{"place":23,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":49.04},{"place":24,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":48},{"place":25,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":46.64},{"place":26,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":46.64},{"place":27,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":44.96},{"place":28,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":43.6},{"place":29,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":43.52},{"place":30,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":37.26}]},{"id":"korbench","name":"KORBench","topic":"General reasoning","description":"Korean reasoning benchmark evaluating diverse reasoning capabilities.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2 (high)","top_percent":79.2,"top_model_id":"gpt-5.2-high","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":79.2},{"place":2,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.5},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.4},{"place":4,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":76},{"place":6,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":74.2},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":73.9},{"place":8,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73},{"place":9,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":72.8}]},{"id":"kosimpleqa","name":"KoSimpleQA","topic":"Korean QA","description":"Korean simple question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kanana-2-30B-A3B-Mid-2601","top_percent":49.7,"top_model_id":"kanana-2-30b-a3b-mid-2601","top_generation":"Kanana 2","top_model_base":"Kanana 2 30B A3B","top_model_family":"Kanana","top_company":"kakao","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":49.7},{"place":2,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":49.4},{"place":3,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":49.4},{"place":4,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":45.7},{"place":5,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":32.5},{"place":6,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":28.5},{"place":7,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.33},{"place":8,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":26.33},{"place":9,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":22.29},{"place":10,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":17.81},{"place":11,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":13.4},{"place":12,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":3.21},{"place":13,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.82}]},{"id":"ksm","name":"KSM","topic":"Multilingual math","description":"Korean STEM and math benchmark","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"EXAONE Deep 2.4B","top_percent":60.9,"top_model_id":"exaone-deep-2.4b","top_generation":"EXAONE Deep","top_model_base":"EXAONE Deep 2.4B","top_model_family":"EXAONE","top_company":"lg","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":60.9},{"place":2,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":60.6},{"place":3,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":52.9},{"place":4,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":49.7},{"place":5,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":22.8}]},{"id":"kubricount-testb","name":"KubriCount (testB)","topic":"Visual counting","description":"KubriCount testB object counting, exact-match accuracy.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":40.1,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":40.1},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":32.4},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":22.4},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":19.1},{"place":5,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":18.8}]},{"id":"l-eval","name":"L-Eval","topic":"Long-context eval","description":"Long-context understanding and generation.","url":"https://github.com/OpenLMLab/LEval","leaderboard":"","github":"","paper":"","metric":"percent","stars":"389","top_model":"Qwen1.5-72B-Chat","top_percent":78.12,"top_model_id":"qwen1.5-72b-chat","top_generation":"Qwen1.5","top_model_base":"Qwen1.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":78.12},{"place":2,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":76.44},{"place":3,"model":"qwen-72b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":73.42},{"place":4,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":73.11},{"place":5,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":65.16},{"place":6,"model":"qwen1.5-4b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":57.05},{"place":7,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":49.4},{"place":8,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":48.6},{"place":9,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":48.5},{"place":10,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":48.4},{"place":11,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":43.9},{"place":12,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":43.72},{"place":13,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":41.7},{"place":14,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":39.7},{"place":15,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":34.6},{"place":16,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":34},{"place":17,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":33.4},{"place":18,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":32.5},{"place":19,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":32.14},{"place":20,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":29.4},{"place":21,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":27.3}]},{"id":"labbench2","name":"LAB-Bench 2","topic":"Biology research","description":"LABBench2: biology real-world research tasks (macro-average over 11 sub-tasks: DbQA2, FigQA2-img/pdf, LitQA3, PatentQA, ProtocolQA2, SourceQuality, SuppQA2, TableQA2-img/pdf, TrialQA).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":88.8,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":88.8},{"place":2,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":86.2},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":85.4},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84.2},{"place":5,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":82.1},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":82.1},{"place":7,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":81.2},{"place":8,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.1},{"place":9,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":76.1},{"place":10,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":73.1},{"place":11,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":68.6}]},{"id":"lambada","name":"LAMBADA","topic":"Language modeling","description":"Word prediction requiring broad context understanding.","url":"https://zenodo.org/record/2630551","leaderboard":"","github":"","paper":"https://arxiv.org/pdf/1606.06031","metric":"percent","stars":"","top_model":"GPT-3","top_percent":86.4,"top_model_id":"gpt-3","top_generation":"GPT-3","top_model_base":"GPT-3","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":60,"total_models":3854,"placements":[{"place":1,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":86.4},{"place":2,"model":"glm-130b","company":"zai","family":"GLM","version":"GLM-130B","score":80.21},{"place":3,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":78.9},{"place":4,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":78.8},{"place":5,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":78.3},{"place":6,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":78.1},{"place":7,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":77.7},{"place":8,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77.6},{"place":9,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":77.4},{"place":10,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":77.2},{"place":11,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":77.2},{"place":12,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":76.5},{"place":13,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":76.3},{"place":14,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":76.2},{"place":15,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":76.1},{"place":16,"model":"qwen-72b","company":"qwen","family":"Qwen","version":"Qwen","score":76.1},{"place":17,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":76},{"place":18,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":75.5},{"place":19,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":75.2},{"place":20,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":74.1},{"place":21,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":74},{"place":22,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":73.9},{"place":23,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":73.3},{"place":24,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":73.3},{"place":25,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":73.3},{"place":26,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":73.1},{"place":27,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":73.1},{"place":28,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":73},{"place":29,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":72.9},{"place":30,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":72.9},{"place":31,"model":"apertus-v1.5-70b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":72.9},{"place":32,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":72.8},{"place":33,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":72.3},{"place":34,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":71.8},{"place":35,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":71.8},{"place":36,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":71.4},{"place":37,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":71.3},{"place":38,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":71.1},{"place":39,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":71},{"place":40,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":70.9},{"place":41,"model":"eurollm-22b-base","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":70.9},{"place":42,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":70.5},{"place":43,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.5},{"place":44,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":70.5},{"place":45,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.3},{"place":46,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":70.2},{"place":47,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":70.1},{"place":48,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":70},{"place":49,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":68.9},{"place":50,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":68.9},{"place":51,"model":"apertus-v1.5-8b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":68.8},{"place":52,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":68.8},{"place":53,"model":"marin-32b-base","company":"marin","family":"Marin","version":"Marin 32B","score":68.7},{"place":54,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":67.9},{"place":55,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":67},{"place":56,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":65.5},{"place":57,"model":"pythia-2.8b","company":"eleutherai","family":"Pythia","version":"Pythia","score":65.1},{"place":58,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":65.1},{"place":59,"model":"gpt-2","company":"openai","family":"GPT","version":"GPT-2","score":63.24},{"place":60,"model":"pythia-1.4b","company":"eleutherai","family":"Pythia","version":"Pythia","score":61.9},{"place":61,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":58.4},{"place":62,"model":"pythia-1b","company":"eleutherai","family":"Pythia","version":"Pythia","score":58},{"place":63,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":54.3},{"place":64,"model":"pythia-410m","company":"eleutherai","family":"Pythia","version":"Pythia","score":52.4},{"place":65,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":48.2},{"place":66,"model":"pythia-160m","company":"eleutherai","family":"Pythia","version":"Pythia","score":34.2},{"place":67,"model":"pythia-70m","company":"eleutherai","family":"Pythia","version":"Pythia","score":19.2}]},{"id":"latent-jailbreak","name":"LatentJailbreak","topic":"Safety / jailbreak","description":"Robustness to latent jailbreak adversarial techniques.","url":"","leaderboard":"","github":"https://github.com/qiuhuachuan/latent-jailbreak","paper":"https://arxiv.org/pdf/2307.08487.pdf","metric":"percent","stars":"39","top_model":"GPT-3.5-turbo","top_percent":77.4,"top_model_id":"gpt-3.5-turbo","top_generation":"GPT-3.5","top_model_base":"GPT-3.5 Turbo","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":77.4},{"place":2,"model":"belle-7b-2m","company":"belle","family":"BELLE","version":"BELLE 7B","score":59.6},{"place":3,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":37},{"place":4,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":24.7}]},{"id":"lbv1-qa","name":"LBV1-QA","topic":"Vision-language","description":"Vision-language QA benchmark v1.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":73.7,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":73.7},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.28},{"place":3,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.9},{"place":4,"model":"qwen3-max-thinking-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":70.71},{"place":5,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":70.4},{"place":6,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":69.9},{"place":7,"model":"qwenlong-l1","company":"qwen","family":"QwenLong","version":"QwenLong","score":68.4},{"place":8,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":67.1},{"place":9,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":67.1},{"place":10,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.86},{"place":11,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":66.3}]},{"id":"lbv2","name":"LBV2","topic":"Vision-language","description":"Vision-language benchmark v2.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":65.72,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.72},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":62.82},{"place":3,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.48},{"place":4,"model":"qwen3-max-thinking-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":57.89},{"place":5,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.46},{"place":6,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.77},{"place":7,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":55.27},{"place":8,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49.11},{"place":9,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":47.01},{"place":10,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":43.74},{"place":11,"model":"qwenlong-l1","company":"qwen","family":"QwenLong","version":"QwenLong","score":40.76}]},{"id":"leetcode-contest","name":"LeetCode Contest","topic":"Code generation (competition)","description":"LeetCode weekly/biweekly contest problems (Jul 2023 - Jan 2024) collected by DeepSeek; pass@1.","url":"https://github.com/deepseek-ai/DeepSeek-Coder/tree/main/Evaluation/LeetCode","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2401.14196","metric":"percent","stars":"","top_model":"GPT-4","top_percent":48.4,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":48.4},{"place":2,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":40.6},{"place":3,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":27.8},{"place":4,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":23.3},{"place":5,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":19.4},{"place":6,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":17.5},{"place":7,"model":"phind-codellama-34b-v2","company":"phind","family":"Phind-CodeLlama-34B-v2","version":"Phind-CodeLlama-34B-v2","score":13.3},{"place":8,"model":"qwen-72b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":12.7},{"place":9,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":9.4},{"place":10,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":7.9},{"place":11,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":7.2},{"place":12,"model":"wizardcoder-15b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":5},{"place":13,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":4.7},{"place":14,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":2.4},{"place":15,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":1.6}]},{"id":"legal-agent-benchmark","name":"Legal Agent Benchmark","topic":"Legal agents","description":"Harvey Legal Agent Benchmark, full public set.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Mythos 5","top_percent":16.9,"top_model_id":"claude-mythos-5","top_generation":"Claude 5","top_model_base":"Claude Mythos 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":16.9},{"place":2,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":13.4},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":9.6},{"place":4,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":8.9},{"place":5,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":8}]},{"id":"legal-agent-benchmark-held-out","name":"Legal Agent Benchmark (Held-Out)","topic":"Legal agents","description":"Harvey Legal Agent Benchmark, Harvey's held-out set.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":19.6,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":19.6},{"place":2,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":19.6},{"place":3,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":15.8},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":13.3},{"place":5,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":12.9},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":11.7},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":11.3},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":10.4},{"place":9,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":10},{"place":10,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":8.8},{"place":11,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":6.7},{"place":12,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":6.7},{"place":13,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":5.8},{"place":14,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":5.4},{"place":15,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":5.4},{"place":16,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":5},{"place":17,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":3.8},{"place":18,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":2.5},{"place":19,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":2.1},{"place":20,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":0.8},{"place":21,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":0.8},{"place":22,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":0}]},{"id":"legal-research-bench","name":"Legal Research Bench","topic":"Legal research","description":"Vals AI Legal Research benchmark of agentic legal research tasks.","url":"https://www.vals.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":49.5,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":49.5},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":48.1},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":44.2},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":43.8},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":40.4},{"place":6,"model":"minimax-m3.1-flash-max","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":34.13},{"place":7,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":31.3}]},{"id":"legalbench","name":"LegalBench","topic":"Legal QA","description":"Suite of legal question answering and reasoning tasks.","url":"https://legalbench.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":83.1,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":83.1},{"place":2,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":81.7},{"place":3,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":80.9},{"place":4,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.7},{"place":5,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.3},{"place":6,"model":"thomson-1.0-small","company":"thomsonreuters","family":"Thomson","version":"Thomson-1.0","score":79.9}]},{"id":"lexam","name":"LEXam","topic":"Legal exams","description":"LEXam benchmark of law-school exam questions (open and multiple-choice) across jurisdictions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Darwin-180B-RSI","top_percent":68.94,"top_model_id":"darwin-180b-rsi","top_generation":"Darwin","top_model_base":"Darwin 180B RSI","top_model_family":"Darwin","top_company":"finalbench","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"darwin-180b-rsi","company":"finalbench","family":"Darwin","version":"Darwin","score":68.94},{"place":2,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":52.41},{"place":3,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.19}]},{"id":"lexam-hard","name":"LEXam (hard)","topic":"Legal exams","description":"Hard subset of the LEXam legal-exam benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Darwin-180B-RSI","top_percent":45.72,"top_model_id":"darwin-180b-rsi","top_generation":"Darwin","top_model_base":"Darwin 180B RSI","top_model_family":"Darwin","top_company":"finalbench","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"darwin-180b-rsi","company":"finalbench","family":"Darwin","version":"Darwin","score":45.72},{"place":2,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":40.82},{"place":3,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.93},{"place":4,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":36.18},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":29.54}]},{"id":"lexam-mcq4-en","name":"LEXam MCQ (4-choice, EN)","topic":"Legal exams","description":"LEXam legal-exam benchmark, English 4-option multiple-choice subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":87.4,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.4},{"place":2,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75.8},{"place":3,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":75.6},{"place":4,"model":"thomson-1.0-small","company":"thomsonreuters","family":"Thomson","version":"Thomson-1.0","score":72.2},{"place":5,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.2}]},{"id":"lifebench","name":"LIFEBench","topic":"Instruction following","description":"Length-based instruction-following evaluation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ling 3.0 Flash","top_percent":77.3,"top_model_id":"ling-3.0-flash","top_generation":"Ling 3.0","top_model_base":"Ling 3.0 Flash","top_model_family":"Ling","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":77.3},{"place":2,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.1},{"place":3,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":72.5},{"place":4,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":71.8},{"place":5,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":71.3},{"place":6,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":69.2},{"place":7,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":66.9},{"place":8,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.3},{"place":9,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.9},{"place":10,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.3},{"place":11,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":62.3},{"place":12,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":61.7},{"place":13,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60.2},{"place":14,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":57.9},{"place":15,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":57.6},{"place":16,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":57.2},{"place":17,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":55.5},{"place":18,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":54.9},{"place":19,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.8},{"place":20,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":49.4},{"place":21,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":44.6},{"place":22,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":42.3}]},{"id":"lifescibench","name":"LifeSciBench","topic":"Life sciences","description":"Life-sciences research workflow benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":60.3,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":60.3},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":59.9},{"place":3,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":56},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":53.6},{"place":5,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":51.2},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":50.4}]},{"id":"lingoqa","name":"LingoQA","topic":"Driving scene QA","description":"Question answering benchmark for autonomous driving scene understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":84.8,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.8},{"place":2,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":83.4},{"place":3,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.6},{"place":5,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.8},{"place":6,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.4},{"place":7,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.2},{"place":8,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.8},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":78.2},{"place":10,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":77.8},{"place":11,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.6},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":77.4},{"place":13,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":76},{"place":14,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.4},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":73.8},{"place":16,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.8},{"place":17,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":72.6},{"place":18,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":72.4},{"place":19,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":72},{"place":20,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.4},{"place":21,"model":"cosmos-reason2-32b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":69},{"place":22,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":68.8},{"place":23,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.4},{"place":24,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":68.2},{"place":25,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.8},{"place":26,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.8},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":66.8},{"place":28,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":65},{"place":29,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":64},{"place":30,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":62.4},{"place":31,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62},{"place":32,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":59.6},{"place":33,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.2},{"place":34,"model":"cosmos-reason2-2b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":59},{"place":35,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":57},{"place":36,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":46.4},{"place":37,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":45.2},{"place":38,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":41.2},{"place":39,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":17.8},{"place":40,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":12.8}]},{"id":"livebench","name":"LiveBench","topic":"General capability","description":"Continually updated capability benchmark across diverse tasks.","url":"","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":82.4,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":164,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.4},{"place":2,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":79.3},{"place":3,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":78.59},{"place":4,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":78.4},{"place":5,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":77.1},{"place":6,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.1},{"place":7,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":76.8},{"place":8,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":76.6},{"place":9,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":76.45},{"place":10,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":76.4},{"place":11,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":76.4},{"place":12,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":75.8},{"place":13,"model":"o1","company":"openai","family":"o1","version":"o1","score":75.7},{"place":14,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":75.7},{"place":15,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.4},{"place":16,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":75.34},{"place":17,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":75.2},{"place":18,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.9},{"place":19,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":74.9},{"place":20,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":74.8},{"place":21,"model":"o3-pro-high","company":"openai","family":"o3","version":"o3","score":74.72},{"place":22,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":74.61},{"place":23,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":74.6},{"place":24,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.3},{"place":25,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.3},{"place":26,"model":"claude-4.1-opus-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":73.48},{"place":27,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":72.93},{"place":28,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":72.9},{"place":29,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":72.4},{"place":30,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":72.2},{"place":31,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":72.11},{"place":32,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.1},{"place":33,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":72.08},{"place":34,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":71.98},{"place":35,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.8},{"place":36,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":71.6},{"place":37,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":71.52},{"place":38,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":71.3},{"place":39,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.3},{"place":40,"model":"gemini-2.5-pro-max-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.95},{"place":41,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.76},{"place":42,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":70.75},{"place":43,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":70.69},{"place":44,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.3},{"place":45,"model":"deepseek-r1-2025-05-28","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70.1},{"place":46,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":70},{"place":47,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":69.8},{"place":48,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.39},{"place":49,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":69},{"place":50,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":68.9},{"place":51,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.8},{"place":52,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":67.7},{"place":53,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.6},{"place":54,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":67.43},{"place":55,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":67.3},{"place":56,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":66.87},{"place":57,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":66.3},{"place":58,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":65.93},{"place":59,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.4},{"place":60,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":65.15},{"place":61,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64.93},{"place":62,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":64.72},{"place":63,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.42},{"place":64,"model":"gpt-5-mini-low","company":"openai","family":"GPT","version":"GPT-5","score":63.85},{"place":65,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.71},{"place":66,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":63.55},{"place":67,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":63.37},{"place":68,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":63},{"place":69,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":62.7},{"place":70,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":62.55},{"place":71,"model":"grok-3-mini-beta-high","company":"xai","family":"Grok","version":"Grok 3","score":62.36},{"place":72,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62},{"place":73,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.9},{"place":74,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":60.78},{"place":75,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":60.45},{"place":76,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":59.93},{"place":77,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":59.8},{"place":78,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":59.8},{"place":79,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":59.7},{"place":80,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":81,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.4},{"place":82,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.02},{"place":83,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":58.74},{"place":84,"model":"gpt-4.5-preview","company":"openai","family":"GPT","version":"GPT-4.5","score":58.65},{"place":85,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":58.48},{"place":86,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":58.47},{"place":87,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":58.1},{"place":88,"model":"grok-code-fast","company":"xai","family":"Grok","version":"Grok Code","score":57.94},{"place":89,"model":"gemini-2.5-flash-lite-preview-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.53},{"place":90,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":56.46},{"place":91,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.19},{"place":92,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":56.05},{"place":93,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":56},{"place":94,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":55.99},{"place":95,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":55.9},{"place":96,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":55.41},{"place":97,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":54.74},{"place":98,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":54.6},{"place":99,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.6},{"place":100,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":54.21},{"place":101,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.03},{"place":102,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":53.5},{"place":103,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":53.2},{"place":104,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":53.11},{"place":105,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52.92},{"place":106,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":52.3},{"place":107,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":51.93},{"place":108,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":51.93},{"place":109,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.8},{"place":110,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":51.57},{"place":111,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":51.4},{"place":112,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.34},{"place":113,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.7},{"place":114,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":50.65},{"place":115,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":49.9},{"place":116,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":49.27},{"place":117,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":49.23},{"place":118,"model":"deepseek-r1-distill-llama-70b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":48.53},{"place":119,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":48.5},{"place":120,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":47.78},{"place":121,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":47.43},{"place":122,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":47.3},{"place":123,"model":"gemini-2.0-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.0","score":46.78},{"place":124,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":46.6},{"place":125,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":46.26},{"place":126,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":45.74},{"place":127,"model":"gpt-5-nano-low","company":"openai","family":"GPT","version":"GPT-5","score":45.45},{"place":128,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":44.5},{"place":129,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":44.4},{"place":130,"model":"command-a","company":"cohere","family":"Command","version":"Command","score":44.17},{"place":131,"model":"hunyuan-turbos","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":43.99},{"place":132,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":43.31},{"place":133,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":43.3},{"place":134,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":43.1},{"place":135,"model":"qwen2.5-72b-instruct-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.51},{"place":136,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.3},{"place":137,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":42},{"place":138,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":41.6},{"place":139,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":41.5},{"place":140,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":41.44},{"place":141,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.73},{"place":142,"model":"mistral-small","company":"mistral","family":"Mistral","version":"Mistral","score":40.55},{"place":143,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":40.51},{"place":144,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":39.6},{"place":145,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":39.51},{"place":146,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37.13},{"place":147,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":37.08},{"place":148,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":36.86},{"place":149,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":36.83},{"place":150,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":36.7},{"place":151,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35.9},{"place":152,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":34.3},{"place":153,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":34.13},{"place":154,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":33.8},{"place":155,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":32.35},{"place":156,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":32.09},{"place":157,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":31.73},{"place":158,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":31.1},{"place":159,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":30.6},{"place":160,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":30.14},{"place":161,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":29.2},{"place":162,"model":"gemma-3n-e4b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":27.85},{"place":163,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.78},{"place":164,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":27.6},{"place":165,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":27.4},{"place":166,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27.32},{"place":167,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":27.15},{"place":168,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.8},{"place":169,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":26.7},{"place":170,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":26.6},{"place":171,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":26.37},{"place":172,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":26.01},{"place":173,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":23.33},{"place":174,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":21.74},{"place":175,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":21.65},{"place":176,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":20.8},{"place":177,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":20.1},{"place":178,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":18.8},{"place":179,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":18.79},{"place":180,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":17},{"place":181,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":14.97},{"place":182,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":14.27},{"place":183,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":14.1},{"place":184,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":12.6},{"place":185,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":12.4},{"place":186,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":7.4}]},{"id":"livebench-2.0","name":"LiveBench 2.0","topic":"General capability","description":"LiveBench 2.0 overall score across seven category boards.","url":"https://livebench.ai","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Smaug-Nemotron-3.5-NVFP4","top_percent":58.1,"top_model_id":"smaug-nemotron-3.5-nvfp4","top_generation":"Smaug","top_model_base":"Smaug Nemotron 3.5","top_model_family":"Smaug","top_company":"abacusai","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":58.1},{"place":2,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":56},{"place":3,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":52.9}]},{"id":"livebench-2.0-agentic","name":"LiveBench 2.0 (Long Agentic)","topic":"Agentic tasks","description":"LiveBench 2.0 Long Agentic category board.","url":"https://livebench.ai","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5.1","top_percent":77.9,"top_model_id":"claude-fable-5.1","top_generation":"Claude 5.1","top_model_base":"Claude Fable 5.1","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":77.9},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":77.5},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":72.8},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":68.7},{"place":5,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":63.4},{"place":6,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":61.2},{"place":7,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":52.6},{"place":8,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":46.1},{"place":9,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":40.9},{"place":10,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":40},{"place":11,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":39.1},{"place":12,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":35.2},{"place":13,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":33.1},{"place":14,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":30.9},{"place":15,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":29.9},{"place":16,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":28.8},{"place":17,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":28},{"place":18,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":26.4},{"place":19,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":25.5},{"place":20,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":20.6},{"place":21,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":19.6},{"place":22,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":19.4},{"place":23,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":19},{"place":24,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":18.1},{"place":25,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":16.5},{"place":26,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":15.8},{"place":27,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":11.7},{"place":28,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":11.7},{"place":29,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":11.5},{"place":30,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":11.2},{"place":31,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":10.7},{"place":32,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":8.8},{"place":33,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":8.5},{"place":34,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":8.4},{"place":35,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":7.3}]},{"id":"livebench-2.0-browser","name":"LiveBench 2.0 (Browser)","topic":"Browser use","description":"LiveBench 2.0 Browser category board.","url":"https://livebench.ai","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":93.3,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":93.3},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":91.3},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":89.8},{"place":4,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":89.3},{"place":5,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":88.4},{"place":6,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":82.8},{"place":7,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":80.6},{"place":8,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":77.3},{"place":9,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":75.9},{"place":10,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":75.2},{"place":11,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":70.3},{"place":12,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":70.3},{"place":13,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":69.5},{"place":14,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":67.2},{"place":15,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":60},{"place":16,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":59.8},{"place":17,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":49.4},{"place":18,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":49.4},{"place":19,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":49.3},{"place":20,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":45.1},{"place":21,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":30.9},{"place":22,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":26.2},{"place":23,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":25.6},{"place":24,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":24.8},{"place":25,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":24.2},{"place":26,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":21.6},{"place":27,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":18},{"place":28,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":12},{"place":29,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":0.6},{"place":30,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0}]},{"id":"livebench-2.0-coding","name":"LiveBench 2.0 (Coding)","topic":"Code generation","description":"LiveBench 2.0 Coding category board.","url":"https://livebench.ai","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5.1","top_percent":97.7,"top_model_id":"claude-fable-5.1","top_generation":"Claude 5.1","top_model_base":"Claude Fable 5.1","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":97.7},{"place":2,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":96.3},{"place":3,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":96},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":96},{"place":5,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":94.7},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":93.7},{"place":7,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":91.4},{"place":8,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":90.2},{"place":9,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":89.7},{"place":10,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":89.1},{"place":11,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.8},{"place":12,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":86.2},{"place":13,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":86.2},{"place":14,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":85.6},{"place":15,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":84.5},{"place":16,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":84.5},{"place":17,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":83.9},{"place":18,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":82.2},{"place":19,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":81.8},{"place":20,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":81.5},{"place":21,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":80.6},{"place":22,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":73.6},{"place":23,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":72.2},{"place":24,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.3},{"place":25,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":66.2},{"place":26,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":65.5},{"place":27,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":64},{"place":28,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":61.3},{"place":29,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":60.3},{"place":30,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":60},{"place":31,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":59.3},{"place":32,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":49},{"place":33,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":43.6}]},{"id":"livebench-2.0-data-analysis","name":"LiveBench 2.0 (Data Analysis)","topic":"Data analysis","description":"LiveBench 2.0 Data Analysis category board.","url":"https://livebench.ai","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":85.2,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":85.2},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":83},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":82.7},{"place":4,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":81.6},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":80.3},{"place":6,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":80.3},{"place":7,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":79.6},{"place":8,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":79.5},{"place":9,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":79.3},{"place":10,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":79.1},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":78.7},{"place":12,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":78.4},{"place":13,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":76.9},{"place":14,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.6},{"place":15,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":76.5},{"place":16,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":76.4},{"place":17,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":75.3},{"place":18,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":73.4},{"place":19,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":72.8},{"place":20,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":72.3},{"place":21,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":71.4},{"place":22,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":65.7},{"place":23,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":65.1},{"place":24,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":64.6},{"place":25,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":63.5},{"place":26,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":60.2},{"place":27,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":59.5},{"place":28,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":54},{"place":29,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.3},{"place":30,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":53.1}]},{"id":"livebench-2.0-design","name":"LiveBench 2.0 (Design)","topic":"Design","description":"LiveBench 2.0 Design category board.","url":"https://livebench.ai","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":86.9,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":86.9},{"place":2,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":85},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":83.4},{"place":4,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":83.4},{"place":5,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":83.1},{"place":6,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":82.5},{"place":7,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":82.1},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":82},{"place":9,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":79.8},{"place":10,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":78.6},{"place":11,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":78.5},{"place":12,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":78},{"place":13,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":77.8},{"place":14,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":77.2},{"place":15,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":77.2},{"place":16,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":76.9},{"place":17,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":76},{"place":18,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.9},{"place":19,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":75.1},{"place":20,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":74.8},{"place":21,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":74},{"place":22,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":73.7},{"place":23,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":72.7},{"place":24,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":65.6},{"place":25,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":62.8},{"place":26,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":62.7},{"place":27,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":60.3},{"place":28,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.4},{"place":29,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":58.3},{"place":30,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":57.1}]},{"id":"livebench-2.0-reasoning","name":"LiveBench 2.0 (Reasoning)","topic":"Reasoning","description":"LiveBench 2.0 Reasoning category board.","url":"https://livebench.ai","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":95.1,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":95.1},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":92.7},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":92.6},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":92.2},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":91.7},{"place":6,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":91.6},{"place":7,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":91.2},{"place":8,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":91.1},{"place":9,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":90.7},{"place":10,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":90.6},{"place":11,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":90.6},{"place":12,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":89.7},{"place":13,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":89.3},{"place":14,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":89.1},{"place":15,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":88.2},{"place":16,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":83.9},{"place":17,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":83.8},{"place":18,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":82.9},{"place":19,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":82.7},{"place":20,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":82.4},{"place":21,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":81.8},{"place":22,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":80},{"place":23,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":79.6},{"place":24,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":78.3},{"place":25,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":77.6},{"place":26,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":75.1},{"place":27,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":74.6},{"place":28,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":73.7},{"place":29,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.7},{"place":30,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.3}]},{"id":"livebench-2.0-research","name":"LiveBench 2.0 (Research)","topic":"Research","description":"LiveBench 2.0 Research category board.","url":"https://livebench.ai","leaderboard":"https://livebench.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Wonder","top_percent":88,"top_model_id":"muse-wonder","top_generation":"Muse Wonder","top_model_base":"Muse Wonder","top_model_family":"Muse","top_company":"meta","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":88},{"place":2,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":86.4},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":85.2},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":85},{"place":5,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":84.5},{"place":6,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":83.6},{"place":7,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":83.5},{"place":8,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":83.1},{"place":9,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":82},{"place":10,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":81.9},{"place":11,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":80.3},{"place":12,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":79.5},{"place":13,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":79.1},{"place":14,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":79},{"place":15,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":77.9},{"place":16,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":76.7},{"place":17,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":72.8},{"place":18,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":72.7},{"place":19,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.9},{"place":20,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":70.1},{"place":21,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":69.9},{"place":22,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":68.6},{"place":23,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":67.8},{"place":24,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":66.7},{"place":25,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":60.4},{"place":26,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":59.9},{"place":27,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":59.4},{"place":28,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.4},{"place":29,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":43.5},{"place":30,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":28.1}]},{"id":"livebrowsecomp","name":"LiveBrowseComp","topic":"Agentic web browsing","description":"Live (continuously refreshed) BrowseComp-style benchmark of hard-to-find web information for deep-search agents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"XYZ-Aquila-pro","top_percent":53.7,"top_model_id":"xyz-aquila-pro","top_generation":"XYZ-Aquila","top_model_base":"XYZ-Aquila pro","top_model_family":"XYZ-Aquila","top_company":"xyzlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"xyz-aquila-pro","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":53.7},{"place":2,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":50.4},{"place":3,"model":"xyz-aquila-mini","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":48.7},{"place":4,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":41.4},{"place":5,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.3},{"place":6,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":34.9},{"place":7,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":34.1},{"place":8,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":32.8},{"place":9,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":31.7},{"place":10,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":29.6}]},{"id":"liveclaw","name":"LiveClaw","topic":"Agentic assistant tasks","description":"Live benchmark of OpenClaw agent tasks executed in real environments.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 24B A2B","top_percent":48.09,"top_model_id":"lfm2.5-24b-a2b","top_generation":"LFM2.5","top_model_base":"LFM2.5 24B A2B","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":48.09},{"place":2,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.25},{"place":3,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":38.19},{"place":4,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":37.72}]},{"id":"livecodebench","name":"LiveCodeBench","topic":"Code generation","description":"Live coding and execution-based evaluation benchmark (v6 dataset).","url":"https://livecodebench.github.io/","leaderboard":"https://livecodebench.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":96.2,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":666,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":96.2},{"place":2,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.6},{"place":3,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.1},{"place":4,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.1},{"place":5,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93.8},{"place":6,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.5},{"place":7,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.5},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":93.28},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":93.2},{"place":10,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":93.2},{"place":11,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":92.9},{"place":12,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":92.6},{"place":13,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":92.5},{"place":14,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":92.4},{"place":15,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":92.3},{"place":16,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":92},{"place":17,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.9},{"place":18,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":91.7},{"place":19,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":91.7},{"place":20,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.6},{"place":21,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":91.6},{"place":22,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.6},{"place":23,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":91.5},{"place":24,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":91},{"place":25,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":91},{"place":26,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.9},{"place":27,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":90.8},{"place":28,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.7},{"place":29,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.6},{"place":30,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.3},{"place":31,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":90.2},{"place":32,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":90.07},{"place":33,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.05},{"place":34,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":89.9},{"place":35,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.8},{"place":36,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":89.8},{"place":37,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":89.6},{"place":38,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":89.6},{"place":39,"model":"ring-1t-2.5-heavy-thinking","company":"antgroup","family":"Ring","version":"Ring 2.5","score":89.4},{"place":40,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.4},{"place":41,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.2},{"place":42,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":89.1},{"place":43,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":89},{"place":44,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89},{"place":45,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":88.8},{"place":46,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88.7},{"place":47,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":88.7},{"place":48,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":88.5},{"place":49,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.4},{"place":50,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":88.3},{"place":51,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":88.3},{"place":52,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":88.22},{"place":53,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":88.2},{"place":54,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":88.2},{"place":55,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88.1},{"place":56,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":88},{"place":57,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":87.96},{"place":58,"model":"ring-1t-2.5","company":"antgroup","family":"Ring","version":"Ring 2.5","score":87.89},{"place":59,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":87.8},{"place":60,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":87.8},{"place":61,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":87.8},{"place":62,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":87.7},{"place":63,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":87.7},{"place":64,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":87.7},{"place":65,"model":"mai-thinking-1","company":"microsoft","family":"MAI","version":"MAI-Thinking-1","score":87.7},{"place":66,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":87.7},{"place":67,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":87.5},{"place":68,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.4},{"place":69,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":87.4},{"place":70,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":87.2},{"place":71,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.1},{"place":72,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.1},{"place":73,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":87},{"place":74,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":87},{"place":75,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":87},{"place":76,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87},{"place":77,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":87},{"place":78,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":87},{"place":79,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":87},{"place":80,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":86.95},{"place":81,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.9},{"place":82,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":86.6},{"place":83,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":86.5},{"place":84,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":86.4},{"place":85,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":86.4},{"place":86,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.34},{"place":87,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":86.1},{"place":88,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":86},{"place":89,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.9},{"place":90,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":85.9},{"place":91,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":85.7},{"place":92,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":85.7},{"place":93,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":85.68},{"place":94,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":85.5},{"place":95,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":85.46},{"place":96,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":85.3},{"place":97,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":85.1},{"place":98,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":85},{"place":99,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":85},{"place":100,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":85},{"place":101,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":84.9},{"place":102,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":84.9},{"place":103,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":84.8},{"place":104,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.8},{"place":105,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":84.7},{"place":106,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":84.7},{"place":107,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":84.5},{"place":108,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":84},{"place":109,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":84},{"place":110,"model":"o3","company":"openai","family":"o3","version":"o3","score":83.9},{"place":111,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.9},{"place":112,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":83.7},{"place":113,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":83.7},{"place":114,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.6},{"place":115,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":83.5},{"place":116,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":83.4},{"place":117,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":83.3},{"place":118,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.3},{"place":119,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.3},{"place":120,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":83.2},{"place":121,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":83.2},{"place":122,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":83.1},{"place":123,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":83},{"place":124,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":82.8},{"place":125,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":82.8},{"place":126,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82.8},{"place":127,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":82.8},{"place":128,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":82.8},{"place":129,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":82.71},{"place":130,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":82.7},{"place":131,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.6},{"place":132,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":82.5},{"place":133,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":82.49},{"place":134,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":82.4},{"place":135,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.3},{"place":136,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":82.2},{"place":137,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82.2},{"place":138,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82},{"place":139,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":82},{"place":140,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":81.9},{"place":141,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":81.9},{"place":142,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":81.8},{"place":143,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":81.7},{"place":144,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":81.7},{"place":145,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":81.7},{"place":146,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":81.6},{"place":147,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":81.4},{"place":148,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":81.39},{"place":149,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.2},{"place":150,"model":"iquest-coder-v1-40b-loop-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":81.1},{"place":151,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":81.06},{"place":152,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":81},{"place":153,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":81},{"place":154,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":80.8},{"place":155,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":80.8},{"place":156,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":80.8},{"place":157,"model":"flint-nvfp4","company":"recursive","family":"Flint","version":"Flint","score":80.8},{"place":158,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":80.7},{"place":159,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.7},{"place":160,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":80.6},{"place":161,"model":"gpt-5-thinking-high","company":"openai","family":"GPT","version":"GPT-5","score":80.6},{"place":162,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":80.6},{"place":163,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":80.6},{"place":164,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":80.5},{"place":165,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":80.5},{"place":166,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":80.4},{"place":167,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.4},{"place":168,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":80.4},{"place":169,"model":"flint","company":"recursive","family":"Flint","version":"Flint","score":80.3},{"place":170,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":80.2},{"place":171,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":80.2},{"place":172,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.1},{"place":173,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":80},{"place":174,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80},{"place":175,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":79.8},{"place":176,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":79.5},{"place":177,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":79.5},{"place":178,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":79.4},{"place":179,"model":"longcat-flash-thinking","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":79.4},{"place":180,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.3},{"place":181,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":79.3},{"place":182,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.2},{"place":183,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":79.2},{"place":184,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":79.2},{"place":185,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":79},{"place":186,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":79},{"place":187,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":79},{"place":188,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.9},{"place":189,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":78.8},{"place":190,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.7},{"place":191,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":78.4},{"place":192,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":78.4},{"place":193,"model":"ring-1t-preview","company":"antgroup","family":"Ring","version":"Ring","score":78.3},{"place":194,"model":"ring-1t","company":"antgroup","family":"Ring","version":"Ring","score":78.3},{"place":195,"model":"pacore-8b","company":"stepfun","family":"Step","version":"PaCoRe","score":78.2},{"place":196,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":78.2},{"place":197,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":78.1},{"place":198,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":78.1},{"place":199,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78.1},{"place":200,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.8},{"place":201,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.7},{"place":202,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":77.4},{"place":203,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":77.2},{"place":204,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":77.1},{"place":205,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.1},{"place":206,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.1},{"place":207,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":77},{"place":208,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":77},{"place":209,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":76.9},{"place":210,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":76.71},{"place":211,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.7},{"place":212,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":76.5},{"place":213,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":76.43},{"place":214,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":76.4},{"place":215,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":76.21},{"place":216,"model":"grok-3-mini-fast-high-reasoning","company":"xai","family":"Grok","version":"Grok 3","score":76.2},{"place":217,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":76.2},{"place":218,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.2},{"place":219,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":76.2},{"place":220,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":75.8},{"place":221,"model":"o3","company":"openai","family":"o3","version":"o3","score":75.8},{"place":222,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":75.77},{"place":223,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":75.77},{"place":224,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":75.72},{"place":225,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":75.6},{"place":226,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.4},{"place":227,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":75.33},{"place":228,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":75.1},{"place":229,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.1},{"place":230,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":75.1},{"place":231,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":75},{"place":232,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":74.9},{"place":233,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":74.9},{"place":234,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":74.9},{"place":235,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":74.9},{"place":236,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":74.8},{"place":237,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":74.7},{"place":238,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.67},{"place":239,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":74.6},{"place":240,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.6},{"place":241,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.6},{"place":242,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.53},{"place":243,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.5},{"place":244,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":74.5},{"place":245,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":74.3},{"place":246,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":74.2},{"place":247,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":74.2},{"place":248,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":74.1},{"place":249,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.1},{"place":250,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.01},{"place":251,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74},{"place":252,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":73.9},{"place":253,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":73.8},{"place":254,"model":"gemini-2.5-pro-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.6},{"place":255,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.6},{"place":256,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":73.4},{"place":257,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":73.4},{"place":258,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":73.3},{"place":259,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":73.24},{"place":260,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":73.22},{"place":261,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.14},{"place":262,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":73.1},{"place":263,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73},{"place":264,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73},{"place":265,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":73},{"place":266,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":73},{"place":267,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":73},{"place":268,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":72.94},{"place":269,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.9},{"place":270,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":72.8},{"place":271,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":72.8},{"place":272,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":72.7},{"place":273,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.5},{"place":274,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":72.5},{"place":275,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":72.3},{"place":276,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":72.3},{"place":277,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":72.3},{"place":278,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":72.1},{"place":279,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.01},{"place":280,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":72},{"place":281,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72},{"place":282,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":72},{"place":283,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72},{"place":284,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":72},{"place":285,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":71.97},{"place":286,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":71.9},{"place":287,"model":"gemini-2.5-pro-05-06","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.8},{"place":288,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":71.7},{"place":289,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":71.6},{"place":290,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":71.5},{"place":291,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":71.4},{"place":292,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.3},{"place":293,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.24},{"place":294,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":71.2},{"place":295,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":71.1},{"place":296,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":71.1},{"place":297,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71},{"place":298,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71},{"place":299,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":70.88},{"place":300,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":70.76},{"place":301,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":70.76},{"place":302,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.7},{"place":303,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":70.7},{"place":304,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.65},{"place":305,"model":"grok-3-beta-think","company":"xai","family":"Grok","version":"Grok 3","score":70.6},{"place":306,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.6},{"place":307,"model":"rlvr-8b-0926","company":"stepfun","family":"Step","version":"PaCoRe","score":70.6},{"place":308,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":70.5},{"place":309,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":310,"model":"north-mini-code-1.0","company":"cohere","family":"North","version":"North 1.0","score":70.3},{"place":311,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70.2},{"place":312,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":70.2},{"place":313,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":70.2},{"place":314,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.1},{"place":315,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":70},{"place":316,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":70},{"place":317,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":70},{"place":318,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":69.9},{"place":319,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":69.9},{"place":320,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.86},{"place":321,"model":"ring-flash-linear-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":69.82},{"place":322,"model":"openreasoning-nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":69.8},{"place":323,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":69.8},{"place":324,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":69.71},{"place":325,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":69.7},{"place":326,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.5},{"place":327,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":69.5},{"place":328,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.45},{"place":329,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":69.4},{"place":330,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.4},{"place":331,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":69.3},{"place":332,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":69.2},{"place":333,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":69.1},{"place":334,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":69.1},{"place":335,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":69.01},{"place":336,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":69},{"place":337,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":69},{"place":338,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":69},{"place":339,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":69},{"place":340,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":68.7},{"place":341,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":68.7},{"place":342,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":68.6},{"place":343,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":68.6},{"place":344,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":68.6},{"place":345,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":68.4},{"place":346,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.3},{"place":347,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":68.3},{"place":348,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.3},{"place":349,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.3},{"place":350,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.2},{"place":351,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":68.17},{"place":352,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.9},{"place":353,"model":"nouscoder-14b","company":"nousresearch","family":"NousCoder","version":"NousCoder","score":67.87},{"place":354,"model":"openreasoning-nemotron-14b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":67.8},{"place":355,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":67.8},{"place":356,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":67.8},{"place":357,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.6},{"place":358,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":67.51},{"place":359,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":67.5},{"place":360,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":67.4},{"place":361,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":67.3},{"place":362,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":67},{"place":363,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":67},{"place":364,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":67},{"place":365,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":67},{"place":366,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":66.9},{"place":367,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.89},{"place":368,"model":"opencodereasoning-nemotron-1.1-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenCodeReasoning","score":66.8},{"place":369,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":66.8},{"place":370,"model":"grok-3-mini-high","company":"xai","family":"Grok","version":"Grok 3","score":66.7},{"place":371,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":66.7},{"place":372,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":66.7},{"place":373,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":66.59},{"place":374,"model":"claude-opus-4-1-20250805-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":66.5},{"place":375,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":66.5},{"place":376,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":66.45},{"place":377,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":66.3},{"place":378,"model":"grok-3-mini-fast-low-reasoning","company":"xai","family":"Grok","version":"Grok 3","score":66.3},{"place":379,"model":"iquest-coder-v1-14b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":66.3},{"place":380,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":66.2},{"place":381,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":66.1},{"place":382,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66},{"place":383,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66},{"place":384,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":66},{"place":385,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":66},{"place":386,"model":"o4-mini-low","company":"openai","family":"o4","version":"o4","score":65.9},{"place":387,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.9},{"place":388,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":65.8},{"place":389,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":65.71},{"place":390,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.7},{"place":391,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":65.7},{"place":392,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":65.6},{"place":393,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.6},{"place":394,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":65.6},{"place":395,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":65.58},{"place":396,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":65.5},{"place":397,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":65.5},{"place":398,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":65.5},{"place":399,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":65.4},{"place":400,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":65.3},{"place":401,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":65.3},{"place":402,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":65.22},{"place":403,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.14},{"place":404,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":65.14},{"place":405,"model":"xbai-o4-medium","company":"xbai","family":"XBai o4","version":"XBai o4","score":65},{"place":406,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":65},{"place":407,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":64.9},{"place":408,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":64.6},{"place":409,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":64.6},{"place":410,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":64.6},{"place":411,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64.6},{"place":412,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":64.5},{"place":413,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":64.5},{"place":414,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.2},{"place":415,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":64.2},{"place":416,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":64.1},{"place":417,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.1},{"place":418,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64},{"place":419,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64},{"place":420,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":64},{"place":421,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":63.97},{"place":422,"model":"o1","company":"openai","family":"o1","version":"o1","score":63.9},{"place":423,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":63.8},{"place":424,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":63.77},{"place":425,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.7},{"place":426,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":63.62},{"place":427,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":63.6},{"place":428,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63.5},{"place":429,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.5},{"place":430,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":63.5},{"place":431,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":63.5},{"place":432,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":63.3},{"place":433,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.11},{"place":434,"model":"o3-mini-2025-01-31-med","company":"openai","family":"o3","version":"o3","score":63},{"place":435,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":63},{"place":436,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":63},{"place":437,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.8},{"place":438,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":62.6},{"place":439,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":62.6},{"place":440,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":62.6},{"place":441,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.6},{"place":442,"model":"ring-mini-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":62.56},{"place":443,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":62.5},{"place":444,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":62.4},{"place":445,"model":"qwen3-32b-thinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":62.33},{"place":446,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":62.3},{"place":447,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.3},{"place":448,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":62.28},{"place":449,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":62.28},{"place":450,"model":"ring-mini-sparse-2.0-exp","company":"antgroup","family":"Ring","version":"Ring 2.0","score":62.19},{"place":451,"model":"grok-code-fast","company":"xai","family":"Grok","version":"Grok Code","score":62},{"place":452,"model":"claude-4.5-haiku-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62},{"place":453,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62},{"place":454,"model":"gemini-2.5-flash-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.9},{"place":455,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.9},{"place":456,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":61.68},{"place":457,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":61.66},{"place":458,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":61.6},{"place":459,"model":"ministral-3-8b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":61.6},{"place":460,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":61.51},{"place":461,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":61.5},{"place":462,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.4},{"place":463,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.2},{"place":464,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.2},{"place":465,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":61.01},{"place":466,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":61},{"place":467,"model":"gpt-oss-20b-a4b","company":"openai","family":"GPT","version":"GPT-OSS","score":61},{"place":468,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":61},{"place":469,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":61},{"place":470,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":61},{"place":471,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":61},{"place":472,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.85},{"place":473,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":60.8},{"place":474,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":60.7},{"place":475,"model":"gemini-2.5-flash-04-17","company":"google","family":"Gemini","version":"Gemini 2.5","score":60.6},{"place":476,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":60.6},{"place":477,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":60.4},{"place":478,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":60.4},{"place":479,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":60.2},{"place":480,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.1},{"place":481,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":60},{"place":482,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":60},{"place":483,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.8},{"place":484,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":59.7},{"place":485,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.7},{"place":486,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":59.6},{"place":487,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.5},{"place":488,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":59.5},{"place":489,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":59.43},{"place":490,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":59.41},{"place":491,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.4},{"place":492,"model":"magistral-medium-1.0","company":"mistral","family":"Magistral","version":"Magistral 1.0","score":59.36},{"place":493,"model":"magistral-medium-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":59.35},{"place":494,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":59.3},{"place":495,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":59.2},{"place":496,"model":"magistral-small-1.1","company":"mistral","family":"Magistral","version":"Magistral 1.1","score":59.17},{"place":497,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":59.1},{"place":498,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":59.05},{"place":499,"model":"gemini-2.5-flash-lite-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":59},{"place":500,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":58.9},{"place":501,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.9},{"place":502,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":58.86},{"place":503,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":58.8},{"place":504,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":58.7},{"place":505,"model":"llama-3.3-nemotron-super-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron Super","score":58.4},{"place":506,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.3},{"place":507,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":58.3},{"place":508,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":58.24},{"place":509,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":58.2},{"place":510,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58},{"place":511,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":58},{"place":512,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":57.9},{"place":513,"model":"simplesd-4b-thinking","company":"apple","family":"SimpleSD","version":"SimpleSD","score":57.8},{"place":514,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":57.79},{"place":515,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":57.71},{"place":516,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":57.71},{"place":517,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.58},{"place":518,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":57.5},{"place":519,"model":"aquif-3.6-1b","company":"aquif","family":"Aquif","version":"Aquif 3.6","score":57.5},{"place":520,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":57.5},{"place":521,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.4},{"place":522,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":57.2},{"place":523,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":57.2},{"place":524,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":57.1},{"place":525,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":57.1},{"place":526,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.1},{"place":527,"model":"o3-mini-2025-01-31-low","company":"openai","family":"o3","version":"o3","score":57},{"place":528,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":56.94},{"place":529,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.9},{"place":530,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.8},{"place":531,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":56.8},{"place":532,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":56.8},{"place":533,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":56.7},{"place":534,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":56.7},{"place":535,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":56.6},{"place":536,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":56.6},{"place":537,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":56.6},{"place":538,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":56.6},{"place":539,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":56.57},{"place":540,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":56.57},{"place":541,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":56.5},{"place":542,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.4},{"place":543,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":56.4},{"place":544,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":56.3},{"place":545,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":56.1},{"place":546,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":55.9},{"place":547,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":55.9},{"place":548,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.9},{"place":549,"model":"magistral-small-1.0","company":"mistral","family":"Magistral","version":"Magistral 1.0","score":55.84},{"place":550,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":55.8},{"place":551,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.8},{"place":552,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.7},{"place":553,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":55.6},{"place":554,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":55.6},{"place":555,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":55.5},{"place":556,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.5},{"place":557,"model":"simplesd-30b-instruct","company":"apple","family":"SimpleSD","version":"SimpleSD","score":55.3},{"place":558,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55.3},{"place":559,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.2},{"place":560,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":55.2},{"place":561,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":55.07},{"place":562,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.92},{"place":563,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":54.9},{"place":564,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":54.86},{"place":565,"model":"ministral-3-3b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":54.8},{"place":566,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":54.7},{"place":567,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.6},{"place":568,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54.5},{"place":569,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":54.3},{"place":570,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":54.29},{"place":571,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54.2},{"place":572,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.2},{"place":573,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":54.1},{"place":574,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":53.9},{"place":575,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.9},{"place":576,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":53.71},{"place":577,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.71},{"place":578,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":53.7},{"place":579,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":53.7},{"place":580,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":53.7},{"place":581,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":53.6},{"place":582,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":53.39},{"place":583,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.2},{"place":584,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":53.1},{"place":585,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":53},{"place":586,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":53},{"place":587,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":52.9},{"place":588,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":52.6},{"place":589,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":52.5},{"place":590,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":52.48},{"place":591,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":52.2},{"place":592,"model":"acereason-nemotron-1.1","company":"nvidia","family":"AceReason","version":"1.1","score":52.1},{"place":593,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":52.09},{"place":594,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":52},{"place":595,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52},{"place":596,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":51.94},{"place":597,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.9},{"place":598,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.8},{"place":599,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":51.8},{"place":600,"model":"deepseek-r1-lite-preview","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":51.6},{"place":601,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":51.5},{"place":602,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":51.5},{"place":603,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":51.43},{"place":604,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":51.4},{"place":605,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":51.4},{"place":606,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":51.38},{"place":607,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":51.3},{"place":608,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.3},{"place":609,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":51.3},{"place":610,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":51.3},{"place":611,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":51.2},{"place":612,"model":"vibethinker-1.5b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":51.1},{"place":613,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51},{"place":614,"model":"jan-code-4b","company":"menlo","family":"Jan","version":"Jan Code","score":51},{"place":615,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":51},{"place":616,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51},{"place":617,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":50.9},{"place":618,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":50.7},{"place":619,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":50.5},{"place":620,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.4},{"place":621,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":50.4},{"place":622,"model":"o1","company":"openai","family":"o1","version":"o1","score":50.3},{"place":623,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":50.3},{"place":624,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":50.03},{"place":625,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":50},{"place":626,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":49.71},{"place":627,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":49.6},{"place":628,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":49.5},{"place":629,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.4},{"place":630,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":49.4},{"place":631,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":49.3},{"place":632,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.12},{"place":633,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":49},{"place":634,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":48.95},{"place":635,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":48.9},{"place":636,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":48.9},{"place":637,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":48.74},{"place":638,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.72},{"place":639,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":48.71},{"place":640,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":48.6},{"place":641,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":48.57},{"place":642,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.57},{"place":643,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":48.5},{"place":644,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":48.5},{"place":645,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.5},{"place":646,"model":"qwen3-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":48.4},{"place":647,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":48.02},{"place":648,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":48},{"place":649,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":47.61},{"place":650,"model":"qwen3-4b-saferl-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":47.5},{"place":651,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":47.43},{"place":652,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":47.4},{"place":653,"model":"magistral-small-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":47.4},{"place":654,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":47.4},{"place":655,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":47.3},{"place":656,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":47.1},{"place":657,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":47},{"place":658,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":46.9},{"place":659,"model":"gemini-2.5-flash-preview-05-20-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":46.9},{"place":660,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":46.9},{"place":661,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":46.9},{"place":662,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":46.8},{"place":663,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.74},{"place":664,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":46.5},{"place":665,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":46.42},{"place":666,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":46.1},{"place":667,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":46},{"place":668,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":45.93},{"place":669,"model":"jan-v3","company":"menlo","family":"Jan","version":"Jan v3","score":45.8},{"place":670,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":45.7},{"place":671,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":45.7},{"place":672,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":45.6},{"place":673,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":45.43},{"place":674,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":45.37},{"place":675,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":45.3},{"place":676,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":44.8},{"place":677,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":44.7},{"place":678,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.7},{"place":679,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":44.27},{"place":680,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":44.11},{"place":681,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":44.05},{"place":682,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44},{"place":683,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":43.7},{"place":684,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":43.6},{"place":685,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":43.4},{"place":686,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":43.4},{"place":687,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":43.4},{"place":688,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":43.4},{"place":689,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":43.4},{"place":690,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":43.2},{"place":691,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":43.2},{"place":692,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":43.1},{"place":693,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":43.1},{"place":694,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.1},{"place":695,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":42.99},{"place":696,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":42.9},{"place":697,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.9},{"place":698,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":42.7},{"place":699,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":42.7},{"place":700,"model":"skywork-or1-7b","company":"skywork","family":"Skywork OR1","version":"Skywork OR1","score":42.7},{"place":701,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":42.7},{"place":702,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.6},{"place":703,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.6},{"place":704,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":42.51},{"place":705,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":42.5},{"place":706,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":42.4},{"place":707,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":42.4},{"place":708,"model":"glm-z1","company":"zai","family":"GLM","version":"GLM Z1","score":42.3},{"place":709,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":42.29},{"place":710,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":42.29},{"place":711,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":42.2},{"place":712,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":42.2},{"place":713,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":42.1},{"place":714,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":41.9},{"place":715,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":41.9},{"place":716,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":41.8},{"place":717,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":41.7},{"place":718,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":41.64},{"place":719,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":41.63},{"place":720,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":41.6},{"place":721,"model":"simplesd-4b-instruct","company":"apple","family":"SimpleSD","version":"SimpleSD","score":41.5},{"place":722,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":40.7},{"place":723,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":40.5},{"place":724,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":40.5},{"place":725,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":40.3},{"place":726,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.22},{"place":727,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":40.09},{"place":728,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":40.09},{"place":729,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":40},{"place":730,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":40},{"place":731,"model":"iquest-coder-v1-14b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":40},{"place":732,"model":"joyai-llm-flash-base","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":39.91},{"place":733,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":39.9},{"place":734,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":39.8},{"place":735,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":39.71},{"place":736,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":39.7},{"place":737,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":39.7},{"place":738,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":39.6},{"place":739,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":39.3},{"place":740,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39},{"place":741,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.99},{"place":742,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":38.8},{"place":743,"model":"grok-2","company":"xai","family":"Grok","version":"Grok 2","score":38.7},{"place":744,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":38.5},{"place":745,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.1},{"place":746,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":37.9},{"place":747,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37.8},{"place":748,"model":"glm-5.3-flash-base","company":"zai","family":"GLM","version":"GLM 5.3","score":37.6},{"place":749,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":37.6},{"place":750,"model":"k2-horizon-0.9b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":37.4},{"place":751,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":37.34},{"place":752,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":37.2},{"place":753,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":37.1},{"place":754,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":37.1},{"place":755,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":37},{"place":756,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":36.9},{"place":757,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":36.8},{"place":758,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36.7},{"place":759,"model":"iquest-coder-v1-7b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":36.6},{"place":760,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":36.6},{"place":761,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":36.4},{"place":762,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":36.4},{"place":763,"model":"llama-3.3-instruct-turbo-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":36.3},{"place":764,"model":"llama-3.3-nemotron-super-4","company":"nvidia","family":"Nemotron","version":"Nemotron Super","score":36.3},{"place":765,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":36.3},{"place":766,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":36.3},{"place":767,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.11},{"place":768,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":36},{"place":769,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":36},{"place":770,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":35.9},{"place":771,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":35.8},{"place":772,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":35.7},{"place":773,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":35.68},{"place":774,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":35.5},{"place":775,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":35.3},{"place":776,"model":"command-a","company":"cohere","family":"Command","version":"Command","score":35.1},{"place":777,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":35.1},{"place":778,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":35.03},{"place":779,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":34.86},{"place":780,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":34.8},{"place":781,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":34.7},{"place":782,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":34.6},{"place":783,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":34.6},{"place":784,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":34.5},{"place":785,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":34.4},{"place":786,"model":"glm-5-base","company":"zai","family":"GLM","version":"GLM 5","score":34.4},{"place":787,"model":"deepseek-v2.5-1210","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":34.38},{"place":788,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":34.3},{"place":789,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":34.2},{"place":790,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":34.2},{"place":791,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":34.1},{"place":792,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":34.1},{"place":793,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":34},{"place":794,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":33.52},{"place":795,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":33.5},{"place":796,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":33.48},{"place":797,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":33.4},{"place":798,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":33.4},{"place":799,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":33.3},{"place":800,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":33.3},{"place":801,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":33.04},{"place":802,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":32.8},{"place":803,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":32.8},{"place":804,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":32.8},{"place":805,"model":"hy-1.8b-2bit","company":"tencent","family":"HY","version":"HY","score":32.73},{"place":806,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.68},{"place":807,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":32.6},{"place":808,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":32.6},{"place":809,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":32.5},{"place":810,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":32.2},{"place":811,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":32.1},{"place":812,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":32.1},{"place":813,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":32},{"place":814,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":32},{"place":815,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":31.9},{"place":816,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":31.83},{"place":817,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":31.8},{"place":818,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":31.74},{"place":819,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":31.6},{"place":820,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":31.5},{"place":821,"model":"hy-1.8b","company":"tencent","family":"HY","version":"HY","score":31.5},{"place":822,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":31.4},{"place":823,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":31.3},{"place":824,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":31.1},{"place":825,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":31},{"place":826,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":30.92},{"place":827,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":30.9},{"place":828,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":30.86},{"place":829,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":30.8},{"place":830,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":30.8},{"place":831,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":30.7},{"place":832,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":30.7},{"place":833,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":30.7},{"place":834,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":30.7},{"place":835,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":30.5},{"place":836,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":30.4},{"place":837,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":30.4},{"place":838,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":30.4},{"place":839,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":30.3},{"place":840,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":30.1},{"place":841,"model":"hy-1.8b-int4gptq","company":"tencent","family":"HY","version":"HY","score":30.08},{"place":842,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.9},{"place":843,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":29.9},{"place":844,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.8},{"place":845,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.8},{"place":846,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.8},{"place":847,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.8},{"place":848,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":29.78},{"place":849,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":29.7},{"place":850,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":29.5},{"place":851,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":29.31},{"place":852,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":29.3},{"place":853,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":29.3},{"place":854,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":29.2},{"place":855,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":29.1},{"place":856,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.1},{"place":857,"model":"mobilellm-r1.5-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":29.1},{"place":858,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":29.1},{"place":859,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":29},{"place":860,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":28.85},{"place":861,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":28.8},{"place":862,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":28.7},{"place":863,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":28.7},{"place":864,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":28.7},{"place":865,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28.7},{"place":866,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28.7},{"place":867,"model":"aquif-3-moe-17b-a2.8b","company":"aquif","family":"Aquif","version":"Aquif 3","score":28.6},{"place":868,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":28.6},{"place":869,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":28.58},{"place":870,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":28.5},{"place":871,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":28.4},{"place":872,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":28.4},{"place":873,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":28.3},{"place":874,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":28.3},{"place":875,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":28.2},{"place":876,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":28.14},{"place":877,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":28.1},{"place":878,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":28.1},{"place":879,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":28.1},{"place":880,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":28},{"place":881,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":27.9},{"place":882,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":27.7},{"place":883,"model":"qwen3-4b-saferl","company":"qwen","family":"Qwen","version":"Qwen3","score":27.7},{"place":884,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":27.7},{"place":885,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":27.5},{"place":886,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":27.5},{"place":887,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":27.43},{"place":888,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":27.43},{"place":889,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27.4},{"place":890,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":27.4},{"place":891,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":27.2},{"place":892,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":26.9},{"place":893,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":26.81},{"place":894,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":26.76},{"place":895,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":26.73},{"place":896,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":26.6},{"place":897,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":26.6},{"place":898,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":26.4},{"place":899,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.4},{"place":900,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":26.3},{"place":901,"model":"ernie-4.5-21b-a3b-pt","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":26.1},{"place":902,"model":"qwen3-8b-nothinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":26.1},{"place":903,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":26},{"place":904,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":26},{"place":905,"model":"hunyuan-80b-a13b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":25.8},{"place":906,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":25.5},{"place":907,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":25.5},{"place":908,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":25.3},{"place":909,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":25.3},{"place":910,"model":"phi-4-14b","company":"microsoft","family":"Phi","version":"Phi 4","score":25.2},{"place":911,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":25.1},{"place":912,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":25},{"place":913,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":24.9},{"place":914,"model":"aquif-3.5-nano-1b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":24.8},{"place":915,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":24.8},{"place":916,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":24.6},{"place":917,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.6},{"place":918,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":24.6},{"place":919,"model":"iquest-coder-v1-7b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":24.6},{"place":920,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":24.3},{"place":921,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":24.23},{"place":922,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":24.07},{"place":923,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":23.9},{"place":924,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":23.87},{"place":925,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":23.8},{"place":926,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":23.4},{"place":927,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":23.4},{"place":928,"model":"aquif-3.5-2.7b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":23.1},{"place":929,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":22.91},{"place":930,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":22.6},{"place":931,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":22.6},{"place":932,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":22.5},{"place":933,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":22.5},{"place":934,"model":"jamba-1.6-large","company":"ai21","family":"Jamba","version":"Jamba 1.6","score":22.3},{"place":935,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":22.3},{"place":936,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":22.3},{"place":937,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":21.8},{"place":938,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":21.33},{"place":939,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.3},{"place":940,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":21.3},{"place":941,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":21.04},{"place":942,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":20.4},{"place":943,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":20.3},{"place":944,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":20.2},{"place":945,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.2},{"place":946,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":20.2},{"place":947,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":20.1},{"place":948,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":20},{"place":949,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":19.9},{"place":950,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":19.9},{"place":951,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":19.9},{"place":952,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":19.8},{"place":953,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":19.77},{"place":954,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":19.4},{"place":955,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":19.4},{"place":956,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":19.05},{"place":957,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":18.9},{"place":958,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":18.9},{"place":959,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":18.9},{"place":960,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":18.86},{"place":961,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":18.8},{"place":962,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":18.8},{"place":963,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":18.8},{"place":964,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":18.3},{"place":965,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":18.2},{"place":966,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":18.2},{"place":967,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.06},{"place":968,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":17.9},{"place":969,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":17.8},{"place":970,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":17.61},{"place":971,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":17.6},{"place":972,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":17.3},{"place":973,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":17.2},{"place":974,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":16.8},{"place":975,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":16.7},{"place":976,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":16.4},{"place":977,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":16.4},{"place":978,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":16.3},{"place":979,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":16},{"place":980,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":16},{"place":981,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":15.85},{"place":982,"model":"mistral-small-1.0","company":"mistral","family":"Mistral Small","version":"Mistral Small","score":15.8},{"place":983,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":15.8},{"place":984,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":15.5},{"place":985,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":15.5},{"place":986,"model":"aquif-3-3.2b","company":"aquif","family":"Aquif","version":"Aquif 3","score":15.4},{"place":987,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":15.2},{"place":988,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":15.2},{"place":989,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":15},{"place":990,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":14.9},{"place":991,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":14.8},{"place":992,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":14.8},{"place":993,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":14.52},{"place":994,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":14.41},{"place":995,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":14.3},{"place":996,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.88},{"place":997,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":13.3},{"place":998,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":12.9},{"place":999,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":12.72},{"place":1000,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":12.6},{"place":1001,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":12.52},{"place":1002,"model":"exaone-3.5-2.4b","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":12.5},{"place":1003,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":12.3},{"place":1004,"model":"hy-0.5b","company":"tencent","family":"HY","version":"HY","score":12.11},{"place":1005,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":12.1},{"place":1006,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":12},{"place":1007,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":11.9},{"place":1008,"model":"codegemma-7b","company":"google","family":"Codegemma","version":"codegemma-7b","score":11.8},{"place":1009,"model":"apriel-5b-instruct","company":"servicenow","family":"Apriel","version":"Apriel","score":11.6},{"place":1010,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":11.6},{"place":1011,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":11.47},{"place":1012,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":11.2},{"place":1013,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":11.18},{"place":1014,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":10.8},{"place":1015,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":10.8},{"place":1016,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":10.5},{"place":1017,"model":"phi-4-mini-3.8b","company":"microsoft","family":"Phi","version":"Phi 4 mini","score":10.4},{"place":1018,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":9.9},{"place":1019,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.78},{"place":1020,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":8.7},{"place":1021,"model":"mobilellm-r1.5-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":8.6},{"place":1022,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":8.4},{"place":1023,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":8.3},{"place":1024,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.19},{"place":1025,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.9},{"place":1026,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":7.9},{"place":1027,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":7.2},{"place":1028,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":7.1},{"place":1029,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":7.05},{"place":1030,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.6},{"place":1031,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":6.15},{"place":1032,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":6.1},{"place":1033,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":6.1},{"place":1034,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":6},{"place":1035,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":5.8},{"place":1036,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5.33},{"place":1037,"model":"mobilellm-r1-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":5.1},{"place":1038,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":5.1},{"place":1039,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":5.1},{"place":1040,"model":"mobilellm-r1-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":4.8},{"place":1041,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":4.8},{"place":1042,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":4.5},{"place":1043,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":4.4},{"place":1044,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":4.27},{"place":1045,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":4.1},{"place":1046,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":4.1},{"place":1047,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":4.08},{"place":1048,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":3.6},{"place":1049,"model":"llama-3.1-3b","company":"meta","family":"Llama","version":"Llama 3.1","score":3.4},{"place":1050,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":3.3},{"place":1051,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":3.13},{"place":1052,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.94},{"place":1053,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":2.89},{"place":1054,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":2.74},{"place":1055,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":2.35},{"place":1056,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":2},{"place":1057,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":2},{"place":1058,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":1.9},{"place":1059,"model":"mobilellm-r1-140m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":1.7},{"place":1060,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":1.6},{"place":1061,"model":"mobilellm-r1.5-140m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":1.5},{"place":1062,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":1.2},{"place":1063,"model":"mobilellm-r1-140m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":1},{"place":1064,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":0.78},{"place":1065,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0.7},{"place":1066,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0},{"place":1067,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":0},{"place":1068,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":0}]},{"id":"livecodebench-ko","name":"LiveCodeBench-Ko","topic":"Code generation (Korean)","description":"Korean translation of LiveCodeBench.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-30B-A3B-Thinking-2507","top_percent":66.3,"top_model_id":"qwen3-30b-a3b-thinking-2507","top_generation":"Qwen3","top_model_base":"Qwen3 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.3},{"place":2,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.5},{"place":3,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":51.2},{"place":4,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":9.4}]},{"id":"livecodebench-pro","name":"LiveCodeBench Pro","topic":"Competitive coding problems from Codeforces, ICPC, and IOI","description":"LiveCodeBench Pro evaluates competitive programming performance across Codeforces, ICPC, and IOI contests. Elo rating, higher is better.","url":"https://livecodebench.github.io/","leaderboard":"https://livecodebench.github.io/leaderboard.html","github":"","paper":"","metric":"elo","stars":"","top_model":"Gemini 3 Deep Think","top_percent":3298,"top_model_id":"gemini-3-deep-think","top_generation":"Gemini 3","top_model_base":"Gemini 3 Deep Think","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":46,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":3298},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":2887},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":2439},{"place":4,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":2393},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":2393},{"place":6,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":2393},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":2316},{"place":8,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":2269},{"place":9,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":2243},{"place":10,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":2176},{"place":11,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":2114},{"place":12,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":2092},{"place":13,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":1930},{"place":14,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1775},{"place":15,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1769},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1765},{"place":17,"model":"gemini-2.5-pro-preview-03-25","company":"google","family":"Gemini","version":"Gemini 2.5","score":1694},{"place":18,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":1688},{"place":19,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1673},{"place":20,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1603},{"place":21,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1418},{"place":22,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1418},{"place":23,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1412},{"place":24,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1364},{"place":25,"model":"gemini-2.5-flash-preview-04-17","company":"google","family":"Gemini","version":"Gemini 2.5","score":1334},{"place":26,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1299},{"place":27,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1288},{"place":28,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1284},{"place":29,"model":"seed1.6-thinking","company":"bytedance","family":"Seed","version":"Seed 1.6","score":1270},{"place":30,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":1226},{"place":31,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":1206},{"place":32,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1161},{"place":33,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1143},{"place":34,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1124},{"place":35,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":1030},{"place":36,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1012},{"place":37,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":1010},{"place":38,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":981},{"place":39,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":962},{"place":40,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":941},{"place":41,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":923},{"place":42,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":875},{"place":43,"model":"gpt-4.5-preview-2025-02-27","company":"openai","family":"GPT","version":"GPT-4.5","score":864},{"place":44,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":770},{"place":45,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":672},{"place":46,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":671},{"place":47,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":606},{"place":48,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":572},{"place":49,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":528},{"place":50,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":504},{"place":51,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":402},{"place":52,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":210}]},{"id":"livecodebench-pro-25q2-easy","name":"LCB Pro 25Q2 (Easy)","topic":"Code generation","description":"LiveCodeBench Pro 2025 Q2 easy subset.","url":"https://livecodebench.github.io/","leaderboard":"https://livecodebench.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":94.8,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":39,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":94.8},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":94.8},{"place":3,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":94.8},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":92.8},{"place":5,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":91.8},{"place":6,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":87},{"place":7,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":85.6},{"place":8,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":84.5},{"place":9,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":81.7},{"place":10,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":81.4},{"place":11,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.1},{"place":12,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":74.2},{"place":13,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":70.1},{"place":14,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":68.9},{"place":15,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":68},{"place":16,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":65.7},{"place":17,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":64.8},{"place":18,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":63.9},{"place":19,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60.8},{"place":20,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":59.3},{"place":21,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.3},{"place":22,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.7},{"place":23,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":54.6},{"place":24,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":54.5},{"place":25,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.6},{"place":26,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":51.6},{"place":27,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.4},{"place":28,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.1},{"place":29,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.8},{"place":30,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":42.3},{"place":31,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":41.2},{"place":32,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":40.2},{"place":33,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":40.2},{"place":34,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":33},{"place":35,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":30.9},{"place":36,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":27.8},{"place":37,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.1},{"place":38,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":22.68},{"place":39,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":10.3},{"place":40,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":6.19},{"place":41,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.12},{"place":42,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0}]},{"id":"livecodebench-pro-25q2-med","name":"LCB Pro 25Q2 (Med)","topic":"Code generation","description":"LiveCodeBench Pro 2025 Q2 medium subset.","url":"https://livecodebench.github.io/","leaderboard":"https://livecodebench.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Deep Think","top_percent":86,"top_model_id":"gemini-3-deep-think","top_generation":"Gemini 3","top_model_base":"Gemini 3 Deep Think","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":39,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":86},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.9},{"place":3,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":59.6},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":50.9},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.6},{"place":6,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":43.9},{"place":7,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":35.4},{"place":8,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":29.8},{"place":9,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":28.1},{"place":10,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":27.9},{"place":11,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":27.6},{"place":12,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":25.9},{"place":13,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":23.2},{"place":14,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":17.8},{"place":15,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":17.5},{"place":16,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":16},{"place":17,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":10.5},{"place":18,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":10.5},{"place":19,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":7},{"place":20,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":7},{"place":21,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":6.4},{"place":22,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":6.1},{"place":23,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":5.3},{"place":24,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":5.3},{"place":25,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":5.3},{"place":26,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":5.3},{"place":27,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":4.8},{"place":28,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":4.8},{"place":29,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.5},{"place":30,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.5},{"place":31,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":3.5},{"place":32,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.5},{"place":33,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.6},{"place":34,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.2},{"place":35,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":1.8},{"place":36,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":1.8},{"place":37,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1.8},{"place":38,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":0},{"place":39,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0},{"place":40,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0},{"place":41,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":0}]},{"id":"livecodebench-v3","name":"LiveCodeBench v3","topic":"Code generation","description":"LiveCodeBench v3 snapshot measuring pass rates on streaming coding tasks.","url":"https://livecodebench.github.io/","leaderboard":"https://livecodebench.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-32B","top_percent":90.2,"top_model_id":"qwen3-32b","top_generation":"Qwen3","top_model_base":"Qwen3 32B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":45,"total_models":3854,"placements":[{"place":1,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":90.2},{"place":2,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.2},{"place":3,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":86.2},{"place":4,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.5},{"place":5,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.8},{"place":6,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":83.5},{"place":7,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":83.4},{"place":8,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":83.3},{"place":9,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":82.3},{"place":10,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.9},{"place":11,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":79.5},{"place":12,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.8},{"place":13,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.2},{"place":14,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.1},{"place":15,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.2},{"place":16,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":68},{"place":17,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.8},{"place":18,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":65.5},{"place":19,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":58.8},{"place":20,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":57.5},{"place":21,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.9},{"place":22,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":54.7},{"place":23,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.2},{"place":24,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.9},{"place":25,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":49.6},{"place":26,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39},{"place":27,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":35.4},{"place":28,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.5},{"place":29,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":29.5},{"place":30,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":28.7},{"place":31,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":24},{"place":32,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":22.6},{"place":33,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":22.2},{"place":34,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":22},{"place":35,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":21.3},{"place":36,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":20.4},{"place":37,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":20.2},{"place":38,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":20},{"place":39,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":19.6},{"place":40,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":19.2},{"place":41,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":18.8},{"place":42,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":11.5},{"place":43,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":10.6},{"place":44,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":9.7},{"place":45,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":7.8},{"place":46,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":7.2}]},{"id":"livecodebench-v5","name":"LiveCodeBench v5 (2024.10-2025.02)","topic":"Code generation","description":"LiveCodeBench v5 snapshot covering Oct 2024-Feb 2025.","url":"https://livecodebench.github.io/","leaderboard":"https://livecodebench.github.io/leaderboard.html","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro Preview","top_percent":91.7,"top_model_id":"gemini-3-pro-preview","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro Preview","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":147,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":91.7},{"place":2,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":88},{"place":3,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":86.8},{"place":4,"model":"iquest-coder-v1-40b-loop-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":86.2},{"place":5,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":84.6},{"place":6,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":83.8},{"place":7,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":83.8},{"place":8,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.1},{"place":9,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":81.19},{"place":10,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":81.1},{"place":11,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.2},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.1},{"place":13,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.93},{"place":14,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":77.5},{"place":15,"model":"kimi-k1.6-ioi-high","company":"moonshotai","family":"Kimi","version":"Kimi k1.6","score":76.5},{"place":16,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":74.8},{"place":17,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":74.7},{"place":18,"model":"grok-3-mini-high","company":"xai","family":"Grok","version":"Grok 3","score":74.7},{"place":19,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":74.6},{"place":20,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":74.5},{"place":21,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":74.3},{"place":22,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":74.1},{"place":23,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":72.9},{"place":24,"model":"nemotron-labs-3-elastic-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.7},{"place":25,"model":"iquest-coder-v1-14b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":72.5},{"place":26,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.75},{"place":27,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.4},{"place":28,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":71},{"place":29,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.7},{"place":30,"model":"grok-3-beta-think","company":"xai","family":"Grok","version":"Grok 3","score":70.6},{"place":31,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.4},{"place":32,"model":"gka-primed-hqwen3-32b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":70.24},{"place":33,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.9},{"place":34,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.5},{"place":35,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":68.7},{"place":36,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":68.26},{"place":37,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.25},{"place":38,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":68.2},{"place":39,"model":"kimi-k1.6-ioi","company":"moonshotai","family":"Kimi","version":"Kimi k1.6","score":67.8},{"place":40,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":67.66},{"place":41,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":66.9},{"place":42,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":66.3},{"place":43,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":66.3},{"place":44,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":66.3},{"place":45,"model":"o3-mini-2025-01-31-med","company":"openai","family":"o3","version":"o3","score":66.3},{"place":46,"model":"deepseek-r1-0120","company":"deepseek","family":"DeepSeek","version":"0120","score":65.9},{"place":47,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":65.87},{"place":48,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.7},{"place":49,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.2},{"place":50,"model":"qwq-max-preview","company":"qwen","family":"Qwen","version":"QwQ","score":65.1},{"place":51,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":65},{"place":52,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":64.9},{"place":53,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64.44},{"place":54,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":64.3},{"place":55,"model":"deepseek-r1-preview","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":64.3},{"place":56,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":63.9},{"place":57,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.4},{"place":58,"model":"simplesd-4b-thinking","company":"apple","family":"SimpleSD","version":"SimpleSD","score":63.1},{"place":59,"model":"gka-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":63.1},{"place":60,"model":"gdn-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":62.94},{"place":61,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":62.8},{"place":62,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":62.3},{"place":63,"model":"o3-mini-2025-01-31-low","company":"openai","family":"o3","version":"o3","score":62},{"place":64,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.5},{"place":65,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.4},{"place":66,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.2},{"place":67,"model":"ring-lite","company":"antgroup","family":"Ring","version":"Ring Lite","score":60.7},{"place":68,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":60.48},{"place":69,"model":"deepcoder-14b-preview","company":"deepcoder","family":"Deepcoder","version":"Deepcoder","score":60.2},{"place":70,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":60.1},{"place":71,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":72,"model":"o1-2024-12-17-low","company":"openai","family":"GPT","version":"o1","score":59.6},{"place":73,"model":"magistral-medium","company":"magistral","family":"Magistral","version":"Magistral","score":59.4},{"place":74,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":59.4},{"place":75,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":57.94},{"place":76,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":57.8},{"place":77,"model":"deepseek-r1-distill-llama-70b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":57.5},{"place":78,"model":"acereason-nemotron-1.1","company":"nvidia","family":"AceReason","version":"1.1","score":57.2},{"place":79,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.89},{"place":80,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":56.89},{"place":81,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":56.6},{"place":82,"model":"vibethinker-1.5b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":55.9},{"place":83,"model":"magistral-small-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":55.8},{"place":84,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":55.7},{"place":85,"model":"simplesd-30b-instruct","company":"apple","family":"SimpleSD","version":"SimpleSD","score":54.3},{"place":86,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":53.9},{"place":87,"model":"phi-4-reasoning","company":"microsoft","family":"Phi","version":"Phi 4","score":53.8},{"place":88,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":52.1},{"place":89,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":51.8},{"place":90,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":51.5},{"place":91,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":50.8},{"place":92,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":50.3},{"place":93,"model":"llama-4-behemoth","company":"meta","family":"Llama","version":"Llama 4","score":49.4},{"place":94,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":49.4},{"place":95,"model":"glm-z1","company":"zai","family":"GLM","version":"GLM Z1","score":49.1},{"place":96,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":48.6},{"place":97,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":48.6},{"place":98,"model":"skywork-or1-7b","company":"skywork","family":"Skywork OR1","version":"Skywork OR1","score":47.6},{"place":99,"model":"deepseek-r1-lite-preview","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":47.5},{"place":100,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":47.2},{"place":101,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":46.1},{"place":102,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":45.8},{"place":103,"model":"simplesd-4b-instruct","company":"apple","family":"SimpleSD","version":"SimpleSD","score":45.7},{"place":104,"model":"llama-nemotron-super-v1","company":"nvidia","family":"Llama","version":"Llama Nemotron v1","score":45.5},{"place":105,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":44.6},{"place":106,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":43.1},{"place":107,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":42.8},{"place":108,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":41.6},{"place":109,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":40.2},{"place":110,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":38.64},{"place":111,"model":"iquest-coder-v1-14b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":37.7},{"place":112,"model":"iquest-coder-v1-7b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":37.7},{"place":113,"model":"metastone-l1-7b","company":"metastone","family":"MetaStone","version":"MetaStone-L1","score":37.4},{"place":114,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":36},{"place":115,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":34.3},{"place":116,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":34.2},{"place":117,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":33.2},{"place":118,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":33.1},{"place":119,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":33.1},{"place":120,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":32.9},{"place":121,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":32.7},{"place":122,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":32.3},{"place":123,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":31.7},{"place":124,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":30.7},{"place":125,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":30.5},{"place":126,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":29.7},{"place":127,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":29.1},{"place":128,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":27.8},{"place":129,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":27.6},{"place":130,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":27.27},{"place":131,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":26.7},{"place":132,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":26.6},{"place":133,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.48},{"place":134,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":24.7},{"place":135,"model":"iquest-coder-v1-7b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":24.6},{"place":136,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.5},{"place":137,"model":"stable-diffcoder-8b-instruct","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":23.5},{"place":138,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":22.8},{"place":139,"model":"codestral-2501","company":"mistral","family":"Codestral","version":"Codestral","score":21.7},{"place":140,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":21.36},{"place":141,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":19.2},{"place":142,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":19.2},{"place":143,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":19.09},{"place":144,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":18},{"place":145,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":17.5},{"place":146,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":17.3},{"place":147,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":17.1},{"place":148,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":14.43},{"place":149,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":14.4},{"place":150,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":13.8},{"place":151,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":13.2},{"place":152,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":12.3},{"place":153,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":11.5},{"place":154,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":11.48},{"place":155,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":10.57},{"place":156,"model":"azerogpt-64b","company":"soundai","family":"AzeroGPT","version":"AzeroGPT","score":10.5},{"place":157,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":9.6},{"place":158,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":4.43},{"place":159,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":3.64},{"place":160,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":3.6},{"place":161,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":3}]},{"id":"livemathematicianbench","name":"LiveMathematicianBench","topic":"Research math","description":"Live benchmark of research-level mathematics problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":50.8,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":50.8},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":43.5},{"place":3,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":36.7},{"place":4,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":27.7},{"place":5,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":20.9}]},{"id":"livemcp-101","name":"LiveMCP-101","topic":"Agent real-time eval","description":"A novel real-time evaluation framework and benchmark to stress‑test agents on complex, real‑world tasks.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/pdf/2508.15760","metric":"percent","stars":"","top_model":"GPT-5","top_percent":58.42,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":58.42},{"place":2,"model":"o3","company":"openai","family":"o3","version":"o3","score":46.53},{"place":3,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":43.56},{"place":4,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":43.56},{"place":5,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":41.58},{"place":6,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":40.59},{"place":7,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":35.64},{"place":8,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":29.7},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":27.72},{"place":10,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":22.77},{"place":11,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":21.78},{"place":12,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":18.81},{"place":13,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":17.82},{"place":14,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":10.89},{"place":15,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":8.91},{"place":16,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.96},{"place":17,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":1.98},{"place":18,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":0.99}]},{"id":"livesports-3k","name":"LiveSports-3K","topic":"Sports video","description":"Live sports video understanding benchmark (3K).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":89,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89},{"place":2,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":86.5},{"place":3,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":78.1},{"place":4,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":78},{"place":5,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.8},{"place":6,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":77.5},{"place":7,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":77.1},{"place":8,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":76.8},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.8},{"place":10,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":74.9},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.5},{"place":12,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":73.3},{"place":13,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":73.2}]},{"id":"livesqlbench","name":"LiveSQLBench","topic":"Text-to-SQL","description":"LiveSQLBench (Base-Full v1): contamination-free text-to-SQL / database tasks over PostgreSQL databases, solved agentically.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":41,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":41},{"place":2,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":40.2},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":40.2},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":39.8},{"place":5,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":33.2}]},{"id":"llava-bench-in-the-wild","name":"LLaVA-Bench (In-the-Wild)","topic":"Visual chat","description":"GPT-4-judged open-ended visual conversation, detailed description and complex reasoning on 60 in-the-wild images; relative score vs. GPT-4 reference.","url":"https://huggingface.co/datasets/liuhaotian/llava-bench-in-the-wild","leaderboard":"","github":"https://github.com/haotian-liu/LLaVA","paper":"https://arxiv.org/abs/2304.08485","metric":"percent","stars":"","top_model":"GPT-4 Vision Preview (1106)","top_percent":93.1,"top_model_id":"gpt-4-1106-vision-preview","top_generation":"GPT-4","top_model_base":"GPT-4V","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":93.1},{"place":2,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":93.1},{"place":3,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":86.7},{"place":4,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":83},{"place":5,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":82},{"place":6,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":81.8},{"place":7,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":81.8},{"place":8,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":80.1},{"place":9,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":79.9},{"place":10,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":79.9},{"place":11,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":77.8},{"place":12,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":77.8},{"place":13,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":73.9},{"place":14,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":73.9},{"place":15,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":73.7},{"place":16,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":72.6},{"place":17,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":71},{"place":18,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":70.7},{"place":19,"model":"llava-llama-3-8b","company":"llava","family":"LLaVA","version":"LLaVA-LLaMA-3","score":69.2},{"place":20,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":69.2},{"place":21,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":67.7},{"place":22,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":64.6},{"place":23,"model":"phi-3-vision-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":64.2},{"place":24,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":63.7},{"place":25,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":63},{"place":26,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":62.3},{"place":27,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":61.2},{"place":28,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":60.9},{"place":29,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":60.7},{"place":30,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":59.8},{"place":31,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":56.9},{"place":32,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":56.4},{"place":33,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":53.8},{"place":34,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":51.9},{"place":35,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":51.3},{"place":36,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":51.1},{"place":37,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":49.1},{"place":38,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":45.1},{"place":39,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":34.2},{"place":40,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":33.5},{"place":41,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":25}]},{"id":"lmarena-text","name":"LMArena Text","topic":"Crowd eval (text)","description":"Chatbot Arena text evaluation (average win rate).","url":"","leaderboard":"https://lmarena.ai/leaderboard/text","github":"","paper":"","metric":"elo","stars":"","top_model":"Gemini 4 Argon (high)","top_percent":1524,"top_model_id":"gemini-4-argon-high","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":440,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":1524},{"place":2,"model":"muse-wonder-max","company":"meta","family":"Muse","version":"Muse Wonder","score":1509},{"place":3,"model":"claude-opus-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1508},{"place":4,"model":"claude-fable-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1504},{"place":5,"model":"claude-opus-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1503},{"place":6,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":1502},{"place":7,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1501},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1497},{"place":9,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":1496},{"place":10,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1494},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1494},{"place":12,"model":"muse-spark-1.2-xhigh","company":"meta","family":"Muse","version":"Muse Spark","score":1493},{"place":13,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":1490},{"place":14,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":1490},{"place":15,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1490},{"place":16,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":1489},{"place":17,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":1488},{"place":18,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":1487},{"place":19,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1487},{"place":20,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":1485},{"place":21,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1485},{"place":22,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":1484},{"place":23,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":1483},{"place":24,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1482},{"place":25,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1481},{"place":26,"model":"gpt-5.5-high","company":"openai","family":"GPT","version":"GPT-5.5","score":1481},{"place":27,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1479},{"place":28,"model":"glm-5.3-max","company":"zai","family":"GLM","version":"GLM 5.3","score":1479},{"place":29,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":1477},{"place":30,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":1477},{"place":31,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1477},{"place":32,"model":"glm-5.2-max","company":"zai","family":"GLM","version":"GLM 5.2","score":1476},{"place":33,"model":"gemini-3.5-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.5","score":1476},{"place":34,"model":"gpt-5.2-instant","company":"openai","family":"GPT","version":"GPT-5.2","score":1476},{"place":35,"model":"gpt-5.4-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1475},{"place":36,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1475},{"place":37,"model":"grok-4.2-beta1","company":"xai","family":"Grok","version":"Grok 4.2","score":1475},{"place":38,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1475},{"place":39,"model":"qwen3.7-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1474},{"place":40,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1474},{"place":41,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":1474},{"place":42,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1474},{"place":43,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":1473},{"place":44,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":1473},{"place":45,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1472},{"place":46,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":1472},{"place":47,"model":"grok-4.2-multi-agent","company":"xai","family":"Grok","version":"Grok 4.20","score":1470},{"place":48,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1470},{"place":49,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1467},{"place":50,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":1467},{"place":51,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1466},{"place":52,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":1466},{"place":53,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1465},{"place":54,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":1465},{"place":55,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":1465},{"place":56,"model":"deepseek-v4-pro-0813-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1465},{"place":57,"model":"qwen3.5-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1464},{"place":58,"model":"claude-sonnet-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1461},{"place":59,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":1461},{"place":60,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1461},{"place":61,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":1459},{"place":62,"model":"grok-4.1","company":"xai","family":"Grok","version":"Grok 4.1","score":1459},{"place":63,"model":"gemini-3-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3","score":1458},{"place":64,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1458},{"place":65,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":1457},{"place":66,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1456},{"place":67,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":1456},{"place":68,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":1456},{"place":69,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1456},{"place":70,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1455},{"place":71,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1455},{"place":72,"model":"deepseek-v4-pro-preview-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1455},{"place":73,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":1455},{"place":74,"model":"grok-4.6-high","company":"xai","family":"Grok","version":"Grok 4.6","score":1454},{"place":75,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1453},{"place":76,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":1453},{"place":77,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1453},{"place":78,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1452},{"place":79,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1451},{"place":80,"model":"mimo-v2.6-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1451},{"place":81,"model":"grok-4.2-0309","company":"xai","family":"Grok","version":"Grok 4.2","score":1451},{"place":82,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":1450},{"place":83,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1450},{"place":84,"model":"claude-opus-4-1-20250805-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1450},{"place":85,"model":"ernie-5.0-preview-1203","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1449},{"place":86,"model":"claude-opus-4-1-20250805-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1448},{"place":87,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1448},{"place":88,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1448},{"place":89,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":1447},{"place":90,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1447},{"place":91,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1446},{"place":92,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1445},{"place":93,"model":"gpt-4.5-preview-2025-02-27","company":"openai","family":"GPT","version":"GPT-4.5","score":1445},{"place":94,"model":"o3","company":"openai","family":"o3","version":"o3","score":1444},{"place":95,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":1444},{"place":96,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1443},{"place":97,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":1443},{"place":98,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":1443},{"place":99,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":1442},{"place":100,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":1442},{"place":101,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1442},{"place":102,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":1441},{"place":103,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":1441},{"place":104,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":1441},{"place":105,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1441},{"place":106,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":1440},{"place":107,"model":"gpt-4.5-preview-2025-02-27","company":"openai","family":"GPT","version":"GPT-4.5","score":1440},{"place":108,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":1440},{"place":109,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":1439},{"place":110,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1439},{"place":111,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1439},{"place":112,"model":"deepseek-v4-flash-preview-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1439},{"place":113,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":1439},{"place":114,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1438},{"place":115,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":1438},{"place":116,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":1437},{"place":117,"model":"longcat-flash-chat-2602-exp","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":1436},{"place":118,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1436},{"place":119,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":1435},{"place":120,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1435},{"place":121,"model":"qwen3-max-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":1434},{"place":122,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1434},{"place":123,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":1434},{"place":124,"model":"qwen3-max-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":1433},{"place":125,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":1433},{"place":126,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":1432},{"place":127,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":1432},{"place":128,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1431},{"place":129,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1431},{"place":130,"model":"grok-4.1-fast-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1430},{"place":131,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1430},{"place":132,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":1428},{"place":133,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":1426},{"place":134,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":1426},{"place":135,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":1426},{"place":136,"model":"amazon-nova-experimental-chat-26-02-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1426},{"place":137,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1426},{"place":138,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":1426},{"place":139,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":1425},{"place":140,"model":"deepseek-v3.2-exp-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1425},{"place":141,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1425},{"place":142,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":1425},{"place":143,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":1424},{"place":144,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1424},{"place":145,"model":"qwen3-max-2025-09-23","company":"qwen","family":"Qwen","version":"Qwen3","score":1423},{"place":146,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":1422},{"place":147,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1422},{"place":148,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1422},{"place":149,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1422},{"place":150,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1421},{"place":151,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1421},{"place":152,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1420},{"place":153,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1420},{"place":154,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":1420},{"place":155,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":1419},{"place":156,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1419},{"place":157,"model":"qwen3-max-2025-09-23","company":"qwen","family":"Qwen","version":"Qwen3","score":1418},{"place":158,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":1418},{"place":159,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1418},{"place":160,"model":"ernie-5.0-preview-1022","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1418},{"place":161,"model":"kimi-k2-0711-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1418},{"place":162,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1417},{"place":163,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1417},{"place":164,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1416},{"place":165,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1416},{"place":166,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1416},{"place":167,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1416},{"place":168,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1416},{"place":169,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1415},{"place":170,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1415},{"place":171,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1415},{"place":172,"model":"kimi-k2-0711-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1415},{"place":173,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":1415},{"place":174,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1415},{"place":175,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1414},{"place":176,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1414},{"place":177,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1414},{"place":178,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1414},{"place":179,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1413},{"place":180,"model":"amazon-nova-experimental-chat-26-01-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1413},{"place":181,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1411},{"place":182,"model":"grok-3-preview-02-24","company":"xai","family":"Grok","version":"Grok 3","score":1411},{"place":183,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":1411},{"place":184,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1411},{"place":185,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1410},{"place":186,"model":"grok-3-preview-02-24","company":"xai","family":"Grok","version":"Grok 3","score":1410},{"place":187,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1409},{"place":188,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1409},{"place":189,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":1409},{"place":190,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1409},{"place":191,"model":"mistral-medium-2508","company":"mistral","family":"Mistral","version":"Mistral","score":1408},{"place":192,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1407},{"place":193,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1407},{"place":194,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":1405},{"place":195,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1404},{"place":196,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1403},{"place":197,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1402},{"place":198,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":1402},{"place":199,"model":"qwen3-235b-a22b-no-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":1402},{"place":200,"model":"claude-sonnet-4-20250514-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4","score":1402},{"place":201,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1401},{"place":202,"model":"longcat-flash-chat","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":1401},{"place":203,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1401},{"place":204,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1400},{"place":205,"model":"longcat-flash-chat","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":1399},{"place":206,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":1399},{"place":207,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1399},{"place":208,"model":"claude-sonnet-4-20250514-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4","score":1398},{"place":209,"model":"qwen3-235b-a22b-no-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":1398},{"place":210,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1398},{"place":211,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1397},{"place":212,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1396},{"place":213,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1395},{"place":214,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1395},{"place":215,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1394},{"place":216,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1394},{"place":217,"model":"hunyuan-vision-1.5-thinking","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1394},{"place":218,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":1393},{"place":219,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":1393},{"place":220,"model":"amazon-nova-experimental-chat-12-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1393},{"place":221,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":1393},{"place":222,"model":"mai-1-preview","company":"microsoft","family":"MAI","version":"MAI-1 Preview","score":1392},{"place":223,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1392},{"place":224,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":1391},{"place":225,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1391},{"place":226,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1391},{"place":227,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":1391},{"place":228,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":1390},{"place":229,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":1389},{"place":230,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1388},{"place":231,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1388},{"place":232,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1388},{"place":233,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1387},{"place":234,"model":"mistral-medium-2505","company":"mistral","family":"Mistral","version":"Mistral","score":1387},{"place":235,"model":"hunyuan-t1-20250711","company":"tencent","family":"Hunyuan","version":"Hunyuan T1","score":1387},{"place":236,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":1386},{"place":237,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":1386},{"place":238,"model":"mimo-v2-flash-thinking","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1386},{"place":239,"model":"hunyuan-t1-20250711","company":"tencent","family":"Hunyuan","version":"Hunyuan T1","score":1385},{"place":240,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1385},{"place":241,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":1384},{"place":242,"model":"gemini-2.5-flash-lite-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1383},{"place":243,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1383},{"place":244,"model":"hunyuan-turbos-20250416","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":1383},{"place":245,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1383},{"place":246,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1382},{"place":247,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1381},{"place":248,"model":"mistral-medium-2505","company":"mistral","family":"Mistral","version":"Mistral","score":1380},{"place":249,"model":"hunyuan-turbos-20250416","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":1379},{"place":250,"model":"gemini-2.5-flash-lite-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1379},{"place":251,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":1379},{"place":252,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":1378},{"place":253,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1377},{"place":254,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1375},{"place":255,"model":"gemini-2.5-flash-lite-preview-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":1375},{"place":256,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1374},{"place":257,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1374},{"place":258,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1373},{"place":259,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1373},{"place":260,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1372},{"place":261,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1371},{"place":262,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1370},{"place":263,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1370},{"place":264,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1369},{"place":265,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":1369},{"place":266,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1369},{"place":267,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1369},{"place":268,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":1367},{"place":269,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1365},{"place":270,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":1365},{"place":271,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":1364},{"place":272,"model":"amazon-nova-experimental-chat-11-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1364},{"place":273,"model":"grok-3-mini-high","company":"xai","family":"Grok","version":"Grok 3","score":1364},{"place":274,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":1364},{"place":275,"model":"grok-3-mini-high","company":"xai","family":"Grok","version":"Grok 3","score":1362},{"place":276,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1362},{"place":277,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":1361},{"place":278,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1360},{"place":279,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":1360},{"place":280,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1358},{"place":281,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":1358},{"place":282,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":1357},{"place":283,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1356},{"place":284,"model":"mistral-small-2506","company":"mistral","family":"Mistral","version":"Mistral","score":1356},{"place":285,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":1356},{"place":286,"model":"command-a-03-2025","company":"cohere","family":"Command","version":"Command","score":1354},{"place":287,"model":"gemini-2.0-flash-lite-preview-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":1354},{"place":288,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":1352},{"place":289,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1352},{"place":290,"model":"mistral-small-2506","company":"mistral","family":"Mistral","version":"Mistral","score":1351},{"place":291,"model":"gemini-2.0-flash-lite-preview-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":1351},{"place":292,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1351},{"place":293,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1351},{"place":294,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1350},{"place":295,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":1349},{"place":296,"model":"hunyuan-turbos-20250226","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":1349},{"place":297,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":1348},{"place":298,"model":"amazon-nova-experimental-chat-10-20","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1348},{"place":299,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1348},{"place":300,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":1347},{"place":301,"model":"command-a-03-2025","company":"cohere","family":"Command","version":"Command","score":1347},{"place":302,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":1347},{"place":303,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":1346},{"place":304,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":1346},{"place":305,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1346},{"place":306,"model":"amazon-nova-experimental-chat-10-09","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1346},{"place":307,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":1346},{"place":308,"model":"qwen-plus-0125","company":"qwen","family":"Qwen","version":"Qwen","score":1346},{"place":309,"model":"hunyuan-turbos-20250226","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":1344},{"place":310,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1344},{"place":311,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":1343},{"place":312,"model":"qwen-plus-0125","company":"qwen","family":"Qwen","version":"Qwen","score":1343},{"place":313,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":1343},{"place":314,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":1343},{"place":315,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1343},{"place":316,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":1343},{"place":317,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":1343},{"place":318,"model":"nvidia-llama-3.3-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama 3.3","score":1343},{"place":319,"model":"glm-4-plus-0111","company":"zai","family":"GLM","version":"GLM 4","score":1343},{"place":320,"model":"glm-4-plus-0111","company":"zai","family":"GLM","version":"GLM 4","score":1342},{"place":321,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1342},{"place":322,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":1341},{"place":323,"model":"hunyuan-turbo-0110","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbo","score":1341},{"place":324,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1340},{"place":325,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":1340},{"place":326,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1339},{"place":327,"model":"nvidia-llama-3.3-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama 3.3","score":1339},{"place":328,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":1338},{"place":329,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":1338},{"place":330,"model":"hunyuan-turbo-0110","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbo","score":1337},{"place":331,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":1337},{"place":332,"model":"gemini-advanced-0514","company":"google","family":"Gemini","version":"Gemini","score":1336},{"place":333,"model":"grok-2-2024-08-13","company":"xai","family":"Grok","version":"Grok 2","score":1336},{"place":334,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":1336},{"place":335,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":1336},{"place":336,"model":"llama-3.1-405b-instruct-bf16","company":"meta","family":"Llama","version":"Llama 3.1","score":1335},{"place":337,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":1335},{"place":338,"model":"llama-3.1-405b-instruct-bf16","company":"meta","family":"Llama","version":"Llama 3.1","score":1334},{"place":339,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":1334},{"place":340,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":1333},{"place":341,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":1333},{"place":342,"model":"step-2-16k-exp-202412","company":"stepfun","family":"Step","version":"Step 2 16K EXP 202412","score":1333},{"place":343,"model":"gemini-advanced-0514","company":"google","family":"Gemini","version":"Gemini","score":1332},{"place":344,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":1332},{"place":345,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":1332},{"place":346,"model":"grok-2-2024-08-13","company":"xai","family":"Grok","version":"Grok 2","score":1332},{"place":347,"model":"step-2-16k-exp-202412","company":"stepfun","family":"Step","version":"Step 2 16K EXP 202412","score":1331},{"place":348,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":1329},{"place":349,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":1328},{"place":350,"model":"llama-3.3-nemotron-49b-super-v1","company":"nvidia","family":"Llama","version":"Llama 3.3","score":1328},{"place":351,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":1327},{"place":352,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1327},{"place":353,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":1327},{"place":354,"model":"hunyuan-large-2025-02-10","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1326},{"place":355,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1325},{"place":356,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1325},{"place":357,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":1325},{"place":358,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":1324},{"place":359,"model":"gemini-1.5-pro-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1324},{"place":360,"model":"llama-3.3-nemotron-49b-super-v1","company":"nvidia","family":"Llama","version":"Llama 3.3","score":1323},{"place":361,"model":"hunyuan-large-2025-02-10","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1323},{"place":362,"model":"deepseek-v2.5-1210","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1323},{"place":363,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":1323},{"place":364,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":1322},{"place":365,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1322},{"place":366,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1322},{"place":367,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":1322},{"place":368,"model":"llama-4-scout-17b-16e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1322},{"place":369,"model":"deepseek-v2.5-1210","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1320},{"place":370,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":1320},{"place":371,"model":"llama-4-scout-17b-16e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1320},{"place":372,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1320},{"place":373,"model":"gemini-1.5-pro-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1320},{"place":374,"model":"step-1o-turbo-202506","company":"stepfun","family":"Step","version":"Step 1O Turbo 202506","score":1320},{"place":375,"model":"step-1o-turbo-202506","company":"stepfun","family":"Step","version":"Step 1O Turbo 202506","score":1319},{"place":376,"model":"glm-4-plus","company":"zai","family":"GLM","version":"GLM 4","score":1319},{"place":377,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1318},{"place":378,"model":"amazon-nova-experimental-chat-05-14","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1318},{"place":379,"model":"gemma-3n-e4b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":1318},{"place":380,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1318},{"place":381,"model":"qwen-max-0919","company":"qwen","family":"Qwen","version":"Qwen","score":1318},{"place":382,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":1318},{"place":383,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":1318},{"place":384,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":1317},{"place":385,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":1317},{"place":386,"model":"glm-4-plus","company":"zai","family":"GLM","version":"GLM 4","score":1316},{"place":387,"model":"qwen-max-0919","company":"qwen","family":"Qwen","version":"Qwen","score":1315},{"place":388,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1315},{"place":389,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":1314},{"place":390,"model":"mistral-large-2407","company":"mistral","family":"Mistral","version":"Mistral","score":1314},{"place":391,"model":"athene-v2-chat","company":"nvidia","family":"Athene","version":"Athene V2","score":1314},{"place":392,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1314},{"place":393,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":1313},{"place":394,"model":"gpt-4-0125-preview","company":"openai","family":"GPT","version":"GPT-4","score":1313},{"place":395,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1312},{"place":396,"model":"gpt-4-0125-preview","company":"openai","family":"GPT","version":"GPT-4","score":1312},{"place":397,"model":"athene-v2-chat","company":"nvidia","family":"Athene","version":"Athene V2","score":1311},{"place":398,"model":"mistral-large-2407","company":"mistral","family":"Mistral","version":"Mistral","score":1311},{"place":399,"model":"hunyuan-standard-2025-02-10","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1311},{"place":400,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1310},{"place":401,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1309},{"place":402,"model":"hunyuan-standard-2025-02-10","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1308},{"place":403,"model":"grok-2-mini-2024-08-13","company":"xai","family":"Grok","version":"Grok 2","score":1308},{"place":404,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":1307},{"place":405,"model":"athene-70b-0725","company":"nexusflow","family":"Athene","version":"Athene","score":1307},{"place":406,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":1306},{"place":407,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":1306},{"place":408,"model":"grok-2-mini-2024-08-13","company":"xai","family":"Grok","version":"Grok 2","score":1305},{"place":409,"model":"mercury","company":"inception","family":"Mercury","version":"Mercury","score":1305},{"place":410,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":1305},{"place":411,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":1304},{"place":412,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":1304},{"place":413,"model":"athene-70b-0725","company":"nexusflow","family":"Athene","version":"Athene","score":1303},{"place":414,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":1303},{"place":415,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1303},{"place":416,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1303},{"place":417,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1303},{"place":418,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1302},{"place":419,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1300},{"place":420,"model":"llama-3.1-nemotron-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1299},{"place":421,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":1297},{"place":422,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1297},{"place":423,"model":"llama-3.1-nemotron-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1296},{"place":424,"model":"hunyuan-large-vision","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1294},{"place":425,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1293},{"place":426,"model":"hunyuan-large-vision","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1292},{"place":427,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1292},{"place":428,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":1290},{"place":429,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1290},{"place":430,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":1290},{"place":431,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1290},{"place":432,"model":"jamba-1.5-large","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":1289},{"place":433,"model":"reka-core-20240904","company":"reka","family":"Reka","version":"Reka Core 20240904","score":1288},{"place":434,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":1288},{"place":435,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":1287},{"place":436,"model":"llama-3.1-nemotron-51b-instruct","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1287},{"place":437,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":1287},{"place":438,"model":"gemini-1.5-flash-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1287},{"place":439,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":1287},{"place":440,"model":"jamba-1.5-large","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":1286},{"place":441,"model":"reka-core-20240904","company":"reka","family":"Reka","version":"Reka Core 20240904","score":1286},{"place":442,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1286},{"place":443,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":1286},{"place":444,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":1285},{"place":445,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":1285},{"place":446,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1285},{"place":447,"model":"llama-3.1-nemotron-51b-instruct","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1284},{"place":448,"model":"gemini-1.5-flash-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1282},{"place":449,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1281},{"place":450,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1280},{"place":451,"model":"gemma-2-9b-it-simpo","company":"princeton","family":"Gemma","version":"Gemma 2","score":1280},{"place":452,"model":"gemma-2-9b-it-simpo","company":"princeton","family":"Gemma","version":"Gemma 2","score":1277},{"place":453,"model":"nemotron-4-340b-instruct","company":"nvidia","family":"Nemotron","version":"Nemotron-4","score":1277},{"place":454,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":1277},{"place":455,"model":"command-r-plus-08-2024","company":"cohere","family":"Command","version":"Command","score":1276},{"place":456,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":1276},{"place":457,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":1274},{"place":458,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":1274},{"place":459,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":1273},{"place":460,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":1273},{"place":461,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":1272},{"place":462,"model":"reka-flash-20240904","company":"reka","family":"Reka","version":"Reka Flash 20240904","score":1272},{"place":463,"model":"reka-flash-20240904","company":"reka","family":"Reka","version":"Reka Flash 20240904","score":1271},{"place":464,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":1271},{"place":465,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1271},{"place":466,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1267},{"place":467,"model":"c4ai-aya-expanse-32b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1267},{"place":468,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1267},{"place":469,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":1266},{"place":470,"model":"c4ai-aya-expanse-32b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1265},{"place":471,"model":"deepseek-coder-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1265},{"place":472,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":1262},{"place":473,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1262},{"place":474,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":1262},{"place":475,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":1262},{"place":476,"model":"deepseek-coder-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1261},{"place":477,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":1261},{"place":478,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1260},{"place":479,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":1259},{"place":480,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1259},{"place":481,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1258},{"place":482,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1258},{"place":483,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":1256},{"place":484,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":1253},{"place":485,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":1252},{"place":486,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":1251},{"place":487,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":1250},{"place":488,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":1243},{"place":489,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":1243},{"place":490,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":1241},{"place":491,"model":"amazon-nova-micro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1241},{"place":492,"model":"amazon-nova-micro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1240},{"place":493,"model":"jamba-1.5-mini","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":1240},{"place":494,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":1238},{"place":495,"model":"jamba-1.5-mini","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":1237},{"place":496,"model":"gemini-pro-dev-api","company":"google","family":"Gemini","version":"Gemini","score":1237},{"place":497,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":1235},{"place":498,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1234},{"place":499,"model":"reka-flash-21b-20240226-online","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226 Online","score":1234},{"place":500,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1234},{"place":501,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1233},{"place":502,"model":"hunyuan-standard-256k","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1233},{"place":503,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1232},{"place":504,"model":"reka-flash-21b-20240226-online","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226 Online","score":1232},{"place":505,"model":"gemini-pro-dev-api","company":"google","family":"Gemini","version":"Gemini","score":1232},{"place":506,"model":"hunyuan-standard-256k","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1231},{"place":507,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":1230},{"place":508,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":1229},{"place":509,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":1227},{"place":510,"model":"reka-flash-21b-20240226","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226","score":1227},{"place":511,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":1226},{"place":512,"model":"reka-flash-21b-20240226","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226","score":1225},{"place":513,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":1224},{"place":514,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":1224},{"place":515,"model":"aya-expanse-32b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1224},{"place":516,"model":"mistral-medium","company":"mistral","family":"Mistral","version":"Mistral","score":1223},{"place":517,"model":"c4ai-aya-expanse-8b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1223},{"place":518,"model":"c4ai-aya-expanse-8b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1222},{"place":519,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":1222},{"place":520,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":1222},{"place":521,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":1221},{"place":522,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":1219},{"place":523,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":1213},{"place":524,"model":"zephyr-orpo-141b-a35b-v0.1","company":"huggingface","family":"Zephyr","version":"Zephyr ORPO 141B A35B v0.1","score":1213},{"place":525,"model":"zephyr-orpo-141b-a35b-v0.1","company":"huggingface","family":"Zephyr","version":"Zephyr ORPO 141B A35B v0.1","score":1212},{"place":526,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1211},{"place":527,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1210},{"place":528,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1209},{"place":529,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1204},{"place":530,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":1204},{"place":531,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1200},{"place":532,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":1199},{"place":533,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":1198},{"place":534,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":1197},{"place":535,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":1197},{"place":536,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1196},{"place":537,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":1196},{"place":538,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":1194},{"place":539,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":1192},{"place":540,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1192},{"place":541,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1191},{"place":542,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":1191},{"place":543,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":1185},{"place":544,"model":"wizardlm-70b","company":"wizardlm","family":"WizardLM","version":"WizardLM-70B","score":1185},{"place":545,"model":"aya-expanse-8b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1185},{"place":546,"model":"wizardlm-70b","company":"wizardlm","family":"WizardLM","version":"WizardLM-70B","score":1184},{"place":547,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":1184},{"place":548,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":1183},{"place":549,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":1183},{"place":550,"model":"granite-3.0-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1183},{"place":551,"model":"openchat-3.5","company":"openchat","family":"OpenChat","version":"OpenChat 3.5","score":1183},{"place":552,"model":"openchat-3.5-0106","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":1183},{"place":553,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":1183},{"place":554,"model":"openchat-3.5-0106","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":1181},{"place":555,"model":"granite-3.0-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1181},{"place":556,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1180},{"place":557,"model":"openchat-3.5","company":"openchat","family":"OpenChat","version":"OpenChat 3.5","score":1180},{"place":558,"model":"snowflake-arctic-instruct","company":"snowflake","family":"Arctic","version":"Arctic Instruct","score":1180},{"place":559,"model":"snowflake-arctic-instruct","company":"snowflake","family":"Arctic","version":"Arctic Instruct","score":1179},{"place":560,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1179},{"place":561,"model":"tulu-2-dpo-70b","company":"ai2","family":"Tulu","version":"Tulu 2 DPO 70B","score":1178},{"place":562,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":1177},{"place":563,"model":"openhermes-2.5-mistral-7b","company":"openhermes","family":"OpenHermes","version":"OpenHermes 2.5","score":1176},{"place":564,"model":"openhermes-2.5-mistral-7b","company":"openhermes","family":"OpenHermes","version":"OpenHermes 2.5","score":1175},{"place":565,"model":"vicuna-33b","company":"lmsys","family":"Vicuna","version":"Vicuna-33B","score":1173},{"place":566,"model":"vicuna-33b","company":"lmsys","family":"Vicuna","version":"Vicuna-33B","score":1172},{"place":567,"model":"starling-lm-7b-beta","company":"berkeley","family":"Starling","version":"Starling LM","score":1172},{"place":568,"model":"phi-3-small-8k-instruct","company":"microsoft","family":"Phi","version":"Phi-3","score":1171},{"place":569,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1171},{"place":570,"model":"starling-lm-7b-beta","company":"berkeley","family":"Starling","version":"Starling LM","score":1171},{"place":571,"model":"starling-lm-7b-alpha","company":"berkeley","family":"Starling","version":"Starling LM","score":1168},{"place":572,"model":"starling-lm-7b-alpha","company":"berkeley","family":"Starling","version":"Starling LM","score":1167},{"place":573,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1167},{"place":574,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1166},{"place":575,"model":"nous-hermes-2-mixtral-8x7b-dpo","company":"nousresearch","family":"Nous Hermes","version":"Nous Hermes 2","score":1165},{"place":576,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":1161},{"place":577,"model":"llama2-70b-steerlm-chat","company":"nvidia","family":"Llama","version":"Llama 2","score":1157},{"place":578,"model":"granite-3.0-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.0","score":1157},{"place":579,"model":"granite-3.0-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.0","score":1155},{"place":580,"model":"llama2-70b-steerlm-chat","company":"nvidia","family":"Llama","version":"Llama 2","score":1155},{"place":581,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":1154},{"place":582,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":1153},{"place":583,"model":"dolphin-2.2.1-mistral-7b","company":"cognitivecomputations","family":"Dolphin","version":"Dolphin","score":1152},{"place":584,"model":"dolphin-2.2.1-mistral-7b","company":"cognitivecomputations","family":"Dolphin","version":"Dolphin","score":1151},{"place":585,"model":"mpt-30b-chat","company":"mosaicml","family":"MPT","version":"MPT","score":1151},{"place":586,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":1150},{"place":587,"model":"wizardlm-13b","company":"wizardlm","family":"WizardLM","version":"WizardLM-13B","score":1150},{"place":588,"model":"mpt-30b-chat","company":"mosaicml","family":"MPT","version":"MPT","score":1149},{"place":589,"model":"wizardlm-13b","company":"wizardlm","family":"WizardLM","version":"WizardLM-13B","score":1149},{"place":590,"model":"falcon-180b-chat","company":"tii","family":"Falcon","version":"Falcon","score":1148},{"place":591,"model":"falcon-180b-chat","company":"tii","family":"Falcon","version":"Falcon","score":1145},{"place":592,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1144},{"place":593,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1143},{"place":594,"model":"phi-3-mini-4k-instruct-june-2024","company":"microsoft","family":"Phi","version":"Phi-3","score":1143},{"place":595,"model":"phi-3-mini-4k-instruct-june-2024","company":"microsoft","family":"Phi","version":"Phi-3","score":1142},{"place":596,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1142},{"place":597,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":1142},{"place":598,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":1140},{"place":599,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":1139},{"place":600,"model":"palm-2","company":"google","family":"PaLM","version":"PaLM 2","score":1139},{"place":601,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":1138},{"place":602,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":1137},{"place":603,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":1137},{"place":604,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":1136},{"place":605,"model":"palm-2","company":"google","family":"PaLM","version":"PaLM 2","score":1134},{"place":606,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":1132},{"place":607,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":1131},{"place":608,"model":"phi-3-mini-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":1130},{"place":609,"model":"zephyr-7b-alpha","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Alpha","score":1128},{"place":610,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":1128},{"place":611,"model":"guanaco-33b","company":"timdettmers","family":"Guanaco","version":"Guanaco-33B","score":1128},{"place":612,"model":"guanaco-33b","company":"timdettmers","family":"Guanaco","version":"Guanaco-33B","score":1127},{"place":613,"model":"zephyr-7b-alpha","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Alpha","score":1127},{"place":614,"model":"stripedhyena-nous-7b","company":"togethercomputer","family":"StripedHyena","version":"StripedHyena Nous 7B","score":1122},{"place":615,"model":"stripedhyena-nous-7b","company":"togethercomputer","family":"StripedHyena","version":"StripedHyena Nous 7B","score":1119},{"place":616,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":1119},{"place":617,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":1118},{"place":618,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1117},{"place":619,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":1117},{"place":620,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":1117},{"place":621,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":1115},{"place":622,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1115},{"place":623,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":1114},{"place":624,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1112},{"place":625,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":1111},{"place":626,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1111},{"place":627,"model":"mistral-7b-instruct","company":"mistral","family":"Mistral","version":"Mistral","score":1110},{"place":628,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":1110},{"place":629,"model":"mistral-7b-instruct","company":"mistral","family":"Mistral","version":"Mistral","score":1109},{"place":630,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1108},{"place":631,"model":"gemma-2b-it","company":"google","family":"Gemma","version":"Gemma","score":1094},{"place":632,"model":"qwen1.5-4b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1091},{"place":633,"model":"qwen1.5-4b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1089},{"place":634,"model":"gemma-2b-it","company":"google","family":"Gemma","version":"Gemma","score":1088},{"place":635,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1077},{"place":636,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":1075},{"place":637,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":1074},{"place":638,"model":"koala-13b","company":"ucberkeley","family":"Koala","version":"Koala","score":1071},{"place":639,"model":"alpaca-13b","company":"stanford","family":"Alpaca","version":"Alpaca","score":1070},{"place":640,"model":"koala-13b","company":"ucberkeley","family":"Koala","version":"Koala","score":1069},{"place":641,"model":"gpt4all-13b-snoozy","company":"nomic","family":"GPT4All","version":"GPT4All","score":1068},{"place":642,"model":"mpt-7b-chat","company":"mosaicml","family":"MPT","version":"MPT","score":1064},{"place":643,"model":"alpaca-13b","company":"stanford","family":"Alpaca","version":"Alpaca","score":1063},{"place":644,"model":"gpt4all-13b-snoozy","company":"nomic","family":"GPT4All","version":"GPT4All","score":1062},{"place":645,"model":"mpt-7b-chat","company":"mosaicml","family":"MPT","version":"MPT","score":1059},{"place":646,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":1057},{"place":647,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":1056},{"place":648,"model":"rwkv-4-raven-14b","company":"rwkv","family":"RWKV","version":"RWKV-4 Raven","score":1042},{"place":649,"model":"rwkv-4-raven-14b","company":"rwkv","family":"RWKV","version":"RWKV-4 Raven","score":1040},{"place":650,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":1025},{"place":651,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":1024},{"place":652,"model":"oasst-pythia-12b","company":"oasst","family":"OASST","version":"OASST-Pythia","score":1024},{"place":653,"model":"oasst-pythia-12b","company":"oasst","family":"OASST","version":"OASST-Pythia","score":1019},{"place":654,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":996},{"place":655,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":994},{"place":656,"model":"fastchat-t5-3b","company":"lmsys","family":"FastChat","version":"FastChat","score":993},{"place":657,"model":"fastchat-t5-3b","company":"lmsys","family":"FastChat","version":"FastChat","score":989},{"place":658,"model":"dolly-v2-12b","company":"databricks","family":"Dolly","version":"Dolly v2","score":983},{"place":659,"model":"dolly-v2-12b","company":"databricks","family":"Dolly","version":"Dolly v2","score":975},{"place":660,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":975},{"place":661,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":966},{"place":662,"model":"stablelm-tuned-alpha-7b","company":"stabilityai","family":"StableLM","version":"Tuned Alpha 7B","score":953},{"place":663,"model":"stablelm-tuned-alpha-7b","company":"stabilityai","family":"StableLM","version":"Tuned Alpha 7B","score":950},{"place":664,"model":"llama-13b","company":"meta","family":"Llama","version":"LLaMA","score":833}]},{"id":"lmarena-text-coding","name":"LMArena Text (Coding)","topic":"Crowd eval (coding)","description":"LMArena text leaderboard, coding prompt category (Elo).","url":"https://lmarena.ai/","leaderboard":"https://lmarena.ai/leaderboard/text","github":"","paper":"","metric":"elo","stars":"","top_model":"Claude Opus 5.5 (high)","top_percent":1545,"top_model_id":"claude-opus-5.5-high","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":412,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1545},{"place":2,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":1539},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1534},{"place":4,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1533},{"place":5,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1533},{"place":6,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":1532},{"place":7,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":1531},{"place":8,"model":"claude-opus-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1531},{"place":9,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1518},{"place":10,"model":"claude-fable-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1518},{"place":11,"model":"muse-wonder-max","company":"meta","family":"Muse","version":"Muse Wonder","score":1518},{"place":12,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1515},{"place":13,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1511},{"place":14,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1510},{"place":15,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":1508},{"place":16,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":1508},{"place":17,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":1508},{"place":18,"model":"muse-spark-1.2-xhigh","company":"meta","family":"Muse","version":"Muse Spark","score":1505},{"place":19,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1503},{"place":20,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1503},{"place":21,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1503},{"place":22,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1501},{"place":23,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1501},{"place":24,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":1501},{"place":25,"model":"mimo-v2.6-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1499},{"place":26,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1498},{"place":27,"model":"glm-5.3-max","company":"zai","family":"GLM","version":"GLM 5.3","score":1498},{"place":28,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":1498},{"place":29,"model":"qwen3.7-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1497},{"place":30,"model":"gpt-5.4-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1497},{"place":31,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1496},{"place":32,"model":"gpt-5.5-high","company":"openai","family":"GPT","version":"GPT-5.5","score":1494},{"place":33,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":1493},{"place":34,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":1491},{"place":35,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1491},{"place":36,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":1489},{"place":37,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":1488},{"place":38,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1488},{"place":39,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":1487},{"place":40,"model":"gemini-3.5-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.5","score":1487},{"place":41,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1487},{"place":42,"model":"glm-5.2-max","company":"zai","family":"GLM","version":"GLM 5.2","score":1487},{"place":43,"model":"qwen3.5-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1487},{"place":44,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1486},{"place":45,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":1486},{"place":46,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1485},{"place":47,"model":"amazon-nova-experimental-chat-26-02-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1484},{"place":48,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1484},{"place":49,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":1484},{"place":50,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1484},{"place":51,"model":"claude-sonnet-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1483},{"place":52,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1483},{"place":53,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1483},{"place":54,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":1482},{"place":55,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":1481},{"place":56,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":1481},{"place":57,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":1480},{"place":58,"model":"claude-opus-4-1-20250805-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1479},{"place":59,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":1478},{"place":60,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1476},{"place":61,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":1474},{"place":62,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1474},{"place":63,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1473},{"place":64,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1473},{"place":65,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":1472},{"place":66,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":1472},{"place":67,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1472},{"place":68,"model":"longcat-flash-chat-2602-exp","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":1471},{"place":69,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":1470},{"place":70,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1469},{"place":71,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1469},{"place":72,"model":"deepseek-v4-pro-0813-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1469},{"place":73,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1467},{"place":74,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1467},{"place":75,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1467},{"place":76,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":1467},{"place":77,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":1466},{"place":78,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1466},{"place":79,"model":"longcat-flash-chat","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":1466},{"place":80,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1466},{"place":81,"model":"grok-4.6-high","company":"xai","family":"Grok","version":"Grok 4.6","score":1465},{"place":82,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1465},{"place":83,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":1461},{"place":84,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":1461},{"place":85,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":1460},{"place":86,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1459},{"place":87,"model":"grok-4.2-0309","company":"xai","family":"Grok","version":"Grok 4.2","score":1459},{"place":88,"model":"grok-4.2-multi-agent","company":"xai","family":"Grok","version":"Grok 4.20","score":1457},{"place":89,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1457},{"place":90,"model":"qwen3-max-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":1456},{"place":91,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1455},{"place":92,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":1454},{"place":93,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":1454},{"place":94,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1454},{"place":95,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1453},{"place":96,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1453},{"place":97,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":1453},{"place":98,"model":"deepseek-v4-pro-preview-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1453},{"place":99,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":1453},{"place":100,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1451},{"place":101,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1450},{"place":102,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1449},{"place":103,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1449},{"place":104,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1449},{"place":105,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":1449},{"place":106,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":1448},{"place":107,"model":"amazon-nova-experimental-chat-26-01-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1447},{"place":108,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":1446},{"place":109,"model":"grok-4.2-beta1","company":"xai","family":"Grok","version":"Grok 4.2","score":1446},{"place":110,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":1446},{"place":111,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1445},{"place":112,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1445},{"place":113,"model":"grok-4.1","company":"xai","family":"Grok","version":"Grok 4.1","score":1444},{"place":114,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1443},{"place":115,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":1442},{"place":116,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":1442},{"place":117,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1441},{"place":118,"model":"deepseek-v4-flash-preview-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1440},{"place":119,"model":"qwen3-max-2025-09-23","company":"qwen","family":"Qwen","version":"Qwen3","score":1439},{"place":120,"model":"deepseek-v3.2-exp-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1439},{"place":121,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1438},{"place":122,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1438},{"place":123,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":1438},{"place":124,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":1438},{"place":125,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":1437},{"place":126,"model":"gemini-3-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3","score":1436},{"place":127,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1436},{"place":128,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1436},{"place":129,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":1436},{"place":130,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1435},{"place":131,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1434},{"place":132,"model":"amazon-nova-experimental-chat-11-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1433},{"place":133,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1433},{"place":134,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":1433},{"place":135,"model":"grok-3-preview-02-24","company":"xai","family":"Grok","version":"Grok 3","score":1432},{"place":136,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1431},{"place":137,"model":"amazon-nova-experimental-chat-12-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1430},{"place":138,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":1429},{"place":139,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":1427},{"place":140,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1427},{"place":141,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1427},{"place":142,"model":"ernie-5.0-preview-1203","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1427},{"place":143,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1425},{"place":144,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1425},{"place":145,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1424},{"place":146,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1423},{"place":147,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":1421},{"place":148,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":1421},{"place":149,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":1420},{"place":150,"model":"hunyuan-vision-1.5-thinking","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1420},{"place":151,"model":"mimo-v2-flash-thinking","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1418},{"place":152,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1417},{"place":153,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1416},{"place":154,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":1416},{"place":155,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":1414},{"place":156,"model":"claude-sonnet-4-20250514-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4","score":1414},{"place":157,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1414},{"place":158,"model":"amazon-nova-experimental-chat-10-20","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1413},{"place":159,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":1413},{"place":160,"model":"ernie-5.0-preview-1022","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1412},{"place":161,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1412},{"place":162,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1412},{"place":163,"model":"grok-4.1-fast-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1412},{"place":164,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1410},{"place":165,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":1408},{"place":166,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":1407},{"place":167,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":1407},{"place":168,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1407},{"place":169,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":1406},{"place":170,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1405},{"place":171,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1404},{"place":172,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1402},{"place":173,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1400},{"place":174,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":1400},{"place":175,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1399},{"place":176,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":1398},{"place":177,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":1398},{"place":178,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1397},{"place":179,"model":"gpt-4.5-preview-2025-02-27","company":"openai","family":"GPT","version":"GPT-4.5","score":1396},{"place":180,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":1396},{"place":181,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1391},{"place":182,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1391},{"place":183,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":1390},{"place":184,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":1389},{"place":185,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":1389},{"place":186,"model":"hunyuan-t1-20250711","company":"tencent","family":"Hunyuan","version":"Hunyuan T1","score":1389},{"place":187,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1385},{"place":188,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":1385},{"place":189,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1384},{"place":190,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":1382},{"place":191,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":1381},{"place":192,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":1380},{"place":193,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1379},{"place":194,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1379},{"place":195,"model":"grok-3-mini-high","company":"xai","family":"Grok","version":"Grok 3","score":1379},{"place":196,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1379},{"place":197,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1378},{"place":198,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":1378},{"place":199,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":1378},{"place":200,"model":"kimi-k2-0711-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1377},{"place":201,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":1375},{"place":202,"model":"gemini-2.5-flash-lite-preview-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":1373},{"place":203,"model":"gemini-2.5-flash-lite-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1372},{"place":204,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1371},{"place":205,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":1371},{"place":206,"model":"amazon-nova-experimental-chat-10-09","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1370},{"place":207,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":1368},{"place":208,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1368},{"place":209,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1367},{"place":210,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":1367},{"place":211,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":1367},{"place":212,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":1367},{"place":213,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":1366},{"place":214,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":1366},{"place":215,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":1363},{"place":216,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":1362},{"place":217,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":1362},{"place":218,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":1362},{"place":219,"model":"hunyuan-turbos-20250416","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":1361},{"place":220,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1360},{"place":221,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1359},{"place":222,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":1359},{"place":223,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":1357},{"place":224,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":1357},{"place":225,"model":"nvidia-llama-3.3-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama 3.3","score":1355},{"place":226,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":1351},{"place":227,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":1350},{"place":228,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":1348},{"place":229,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":1347},{"place":230,"model":"hunyuan-turbos-20250226","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":1342},{"place":231,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1342},{"place":232,"model":"step-1o-turbo-202506","company":"stepfun","family":"Step","version":"Step 1O Turbo 202506","score":1339},{"place":233,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1339},{"place":234,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":1337},{"place":235,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":1333},{"place":236,"model":"command-a-03-2025","company":"cohere","family":"Command","version":"Command","score":1330},{"place":237,"model":"qwen-plus-0125","company":"qwen","family":"Qwen","version":"Qwen","score":1328},{"place":238,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1325},{"place":239,"model":"mercury","company":"inception","family":"Mercury","version":"Mercury","score":1323},{"place":240,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1322},{"place":241,"model":"gemini-2.0-flash-lite-preview-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":1322},{"place":242,"model":"hunyuan-turbo-0110","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbo","score":1319},{"place":243,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":1319},{"place":244,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":1319},{"place":245,"model":"step-2-16k-exp-202412","company":"stepfun","family":"Step","version":"Step 2 16K EXP 202412","score":1316},{"place":246,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1314},{"place":247,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":1312},{"place":248,"model":"athene-v2-chat","company":"nvidia","family":"Athene","version":"Athene V2","score":1312},{"place":249,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1312},{"place":250,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":1312},{"place":251,"model":"deepseek-v2.5-1210","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1309},{"place":252,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1309},{"place":253,"model":"hunyuan-large-vision","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1308},{"place":254,"model":"hunyuan-large-2025-02-10","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1307},{"place":255,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":1306},{"place":256,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1306},{"place":257,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1305},{"place":258,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1301},{"place":259,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":1301},{"place":260,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":1297},{"place":261,"model":"llama-3.3-nemotron-49b-super-v1","company":"nvidia","family":"Llama","version":"Llama 3.3","score":1295},{"place":262,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1294},{"place":263,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1292},{"place":264,"model":"llama-3.1-405b-instruct-bf16","company":"meta","family":"Llama","version":"Llama 3.1","score":1291},{"place":265,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":1291},{"place":266,"model":"glm-4-plus","company":"zai","family":"GLM","version":"GLM 4","score":1290},{"place":267,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":1289},{"place":268,"model":"qwen-max-0919","company":"qwen","family":"Qwen","version":"Qwen","score":1288},{"place":269,"model":"grok-2-2024-08-13","company":"xai","family":"Grok","version":"Grok 2","score":1287},{"place":270,"model":"glm-4-plus-0111","company":"zai","family":"GLM","version":"GLM 4","score":1286},{"place":271,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1286},{"place":272,"model":"llama-4-scout-17b-16e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1286},{"place":273,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":1283},{"place":274,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":1283},{"place":275,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1281},{"place":276,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":1276},{"place":277,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1275},{"place":278,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":1275},{"place":279,"model":"llama-3.1-nemotron-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1272},{"place":280,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1270},{"place":281,"model":"hunyuan-standard-2025-02-10","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1269},{"place":282,"model":"grok-2-mini-2024-08-13","company":"xai","family":"Grok","version":"Grok 2","score":1268},{"place":283,"model":"gemma-3n-e4b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":1268},{"place":284,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":1268},{"place":285,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":1268},{"place":286,"model":"athene-70b-0725","company":"nexusflow","family":"Athene","version":"Athene","score":1267},{"place":287,"model":"gemini-1.5-pro-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1266},{"place":288,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1264},{"place":289,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1261},{"place":290,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1259},{"place":291,"model":"gemini-advanced-0514","company":"google","family":"Gemini","version":"Gemini","score":1255},{"place":292,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":1254},{"place":293,"model":"deepseek-coder-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1251},{"place":294,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":1249},{"place":295,"model":"gpt-4-0125-preview","company":"openai","family":"GPT","version":"GPT-4","score":1249},{"place":296,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":1246},{"place":297,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1239},{"place":298,"model":"gemini-1.5-flash-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1235},{"place":299,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":1235},{"place":300,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":1231},{"place":301,"model":"hunyuan-standard-256k","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1231},{"place":302,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1230},{"place":303,"model":"reka-core-20240904","company":"reka","family":"Reka","version":"Reka Core 20240904","score":1230},{"place":304,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":1227},{"place":305,"model":"jamba-1.5-large","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":1227},{"place":306,"model":"llama-3.1-nemotron-51b-instruct","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1223},{"place":307,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1223},{"place":308,"model":"amazon-nova-micro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1218},{"place":309,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1217},{"place":310,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1211},{"place":311,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":1210},{"place":312,"model":"nemotron-4-340b-instruct","company":"nvidia","family":"Nemotron","version":"Nemotron-4","score":1209},{"place":313,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":1208},{"place":314,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":1206},{"place":315,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":1202},{"place":316,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":1199},{"place":317,"model":"aya-expanse-32b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1196},{"place":318,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":1196},{"place":319,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1195},{"place":320,"model":"gemma-2-9b-it-simpo","company":"princeton","family":"Gemma","version":"Gemma 2","score":1191},{"place":321,"model":"reka-flash-20240904","company":"reka","family":"Reka","version":"Reka Flash 20240904","score":1190},{"place":322,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":1187},{"place":323,"model":"command-r-plus-08-2024","company":"cohere","family":"Command","version":"Command","score":1187},{"place":324,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1186},{"place":325,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1184},{"place":326,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":1183},{"place":327,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":1183},{"place":328,"model":"jamba-1.5-mini","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":1178},{"place":329,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1173},{"place":330,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":1172},{"place":331,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":1169},{"place":332,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":1169},{"place":333,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":1165},{"place":334,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1165},{"place":335,"model":"reka-flash-21b-20240226-online","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226 Online","score":1164},{"place":336,"model":"mistral-medium","company":"mistral","family":"Mistral","version":"Mistral","score":1162},{"place":337,"model":"aya-expanse-8b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1160},{"place":338,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":1159},{"place":339,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":1155},{"place":340,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1154},{"place":341,"model":"reka-flash-21b-20240226","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226","score":1153},{"place":342,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":1151},{"place":343,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1149},{"place":344,"model":"starling-lm-7b-beta","company":"berkeley","family":"Starling","version":"Starling LM","score":1142},{"place":345,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1138},{"place":346,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":1136},{"place":347,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":1132},{"place":348,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":1130},{"place":349,"model":"zephyr-orpo-141b-a35b-v0.1","company":"huggingface","family":"Zephyr","version":"Zephyr ORPO 141B A35B v0.1","score":1129},{"place":350,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":1127},{"place":351,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":1126},{"place":352,"model":"tulu-2-dpo-70b","company":"ai2","family":"Tulu","version":"Tulu 2 DPO 70B","score":1116},{"place":353,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":1116},{"place":354,"model":"openchat-3.5-0106","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":1113},{"place":355,"model":"granite-3.0-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1112},{"place":356,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1112},{"place":357,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":1112},{"place":358,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":1108},{"place":359,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1107},{"place":360,"model":"gemini-pro-dev-api","company":"google","family":"Gemini","version":"Gemini","score":1104},{"place":361,"model":"phi-3-small-8k-instruct","company":"microsoft","family":"Phi","version":"Phi-3","score":1101},{"place":362,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1097},{"place":363,"model":"starling-lm-7b-alpha","company":"berkeley","family":"Starling","version":"Starling LM","score":1097},{"place":364,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":1095},{"place":365,"model":"phi-3-mini-4k-instruct-june-2024","company":"microsoft","family":"Phi","version":"Phi-3","score":1093},{"place":366,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":1092},{"place":367,"model":"granite-3.0-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.0","score":1090},{"place":368,"model":"snowflake-arctic-instruct","company":"snowflake","family":"Arctic","version":"Arctic Instruct","score":1089},{"place":369,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":1084},{"place":370,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":1081},{"place":371,"model":"wizardlm-70b","company":"wizardlm","family":"WizardLM","version":"WizardLM-70B","score":1081},{"place":372,"model":"nous-hermes-2-mixtral-8x7b-dpo","company":"nousresearch","family":"Nous Hermes","version":"Nous Hermes 2","score":1079},{"place":373,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1079},{"place":374,"model":"vicuna-33b","company":"lmsys","family":"Vicuna","version":"Vicuna-33B","score":1078},{"place":375,"model":"openchat-3.5","company":"openchat","family":"OpenChat","version":"OpenChat 3.5","score":1074},{"place":376,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":1071},{"place":377,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1070},{"place":378,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":1067},{"place":379,"model":"openhermes-2.5-mistral-7b","company":"openhermes","family":"OpenHermes","version":"OpenHermes 2.5","score":1064},{"place":380,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1062},{"place":381,"model":"zephyr-7b-alpha","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Alpha","score":1053},{"place":382,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":1048},{"place":383,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1048},{"place":384,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":1046},{"place":385,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":1044},{"place":386,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":1040},{"place":387,"model":"phi-3-mini-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":1039},{"place":388,"model":"mpt-30b-chat","company":"mosaicml","family":"MPT","version":"MPT","score":1039},{"place":389,"model":"wizardlm-13b","company":"wizardlm","family":"WizardLM","version":"WizardLM-13B","score":1035},{"place":390,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":1034},{"place":391,"model":"llama2-70b-steerlm-chat","company":"nvidia","family":"Llama","version":"Llama 2","score":1025},{"place":392,"model":"mistral-7b-instruct","company":"mistral","family":"Mistral","version":"Mistral","score":1018},{"place":393,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":1015},{"place":394,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":1010},{"place":395,"model":"gemma-2b-it","company":"google","family":"Gemma","version":"Gemma","score":1009},{"place":396,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1002},{"place":397,"model":"stripedhyena-nous-7b","company":"togethercomputer","family":"StripedHyena","version":"StripedHyena Nous 7B","score":1001},{"place":398,"model":"qwen1.5-4b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":999},{"place":399,"model":"guanaco-33b","company":"timdettmers","family":"Guanaco","version":"Guanaco-33B","score":995},{"place":400,"model":"palm-2","company":"google","family":"PaLM","version":"PaLM 2","score":994},{"place":401,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":964},{"place":402,"model":"koala-13b","company":"ucberkeley","family":"Koala","version":"Koala","score":945},{"place":403,"model":"rwkv-4-raven-14b","company":"rwkv","family":"RWKV","version":"RWKV-4 Raven","score":928},{"place":404,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":919},{"place":405,"model":"mpt-7b-chat","company":"mosaicml","family":"MPT","version":"MPT","score":913},{"place":406,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":902},{"place":407,"model":"oasst-pythia-12b","company":"oasst","family":"OASST","version":"OASST-Pythia","score":900},{"place":408,"model":"stablelm-tuned-alpha-7b","company":"stabilityai","family":"StableLM","version":"Tuned Alpha 7B","score":886},{"place":409,"model":"alpaca-13b","company":"stanford","family":"Alpaca","version":"Alpaca","score":799},{"place":410,"model":"dolly-v2-12b","company":"databricks","family":"Dolly","version":"Dolly v2","score":776},{"place":411,"model":"fastchat-t5-3b","company":"lmsys","family":"FastChat","version":"FastChat","score":764},{"place":412,"model":"llama-13b","company":"meta","family":"Llama","version":"LLaMA","score":683}]},{"id":"lmarena-text-math","name":"LMArena Text (Math)","topic":"Crowd eval (math)","description":"LMArena text leaderboard, math prompt category (Elo).","url":"https://lmarena.ai/","leaderboard":"https://lmarena.ai/leaderboard/text","github":"","paper":"","metric":"elo","stars":"","top_model":"Gemini 4 Argon (high)","top_percent":1538,"top_model_id":"gemini-4-argon-high","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":403,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":1538},{"place":2,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":1533},{"place":3,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":1532},{"place":4,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":1532},{"place":5,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1531},{"place":6,"model":"claude-opus-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1518},{"place":7,"model":"claude-opus-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1518},{"place":8,"model":"claude-fable-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1516},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1511},{"place":10,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":1510},{"place":11,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":1507},{"place":12,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":1504},{"place":13,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1502},{"place":14,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":1502},{"place":15,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1501},{"place":16,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1500},{"place":17,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1498},{"place":18,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1498},{"place":19,"model":"glm-5.3-max","company":"zai","family":"GLM","version":"GLM 5.3","score":1498},{"place":20,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":1493},{"place":21,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":1490},{"place":22,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1489},{"place":23,"model":"qwen3.7-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1488},{"place":24,"model":"gpt-5.4-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1488},{"place":25,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1487},{"place":26,"model":"gemini-3.5-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.5","score":1487},{"place":27,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1486},{"place":28,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1486},{"place":29,"model":"glm-5.2-max","company":"zai","family":"GLM","version":"GLM 5.2","score":1484},{"place":30,"model":"muse-wonder-max","company":"meta","family":"Muse","version":"Muse Wonder","score":1484},{"place":31,"model":"muse-spark-1.2-xhigh","company":"meta","family":"Muse","version":"Muse Spark","score":1483},{"place":32,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":1481},{"place":33,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":1481},{"place":34,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1481},{"place":35,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1480},{"place":36,"model":"gpt-5.5-high","company":"openai","family":"GPT","version":"GPT-5.5","score":1479},{"place":37,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1479},{"place":38,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":1476},{"place":39,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":1476},{"place":40,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":1474},{"place":41,"model":"qwen3.5-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1474},{"place":42,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":1474},{"place":43,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1473},{"place":44,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":1473},{"place":45,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1471},{"place":46,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1470},{"place":47,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":1470},{"place":48,"model":"mimo-v2.6-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1470},{"place":49,"model":"claude-sonnet-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1467},{"place":50,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1467},{"place":51,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":1467},{"place":52,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1466},{"place":53,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":1466},{"place":54,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1465},{"place":55,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1464},{"place":56,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1463},{"place":57,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1462},{"place":58,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":1460},{"place":59,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":1460},{"place":60,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1459},{"place":61,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1459},{"place":62,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1458},{"place":63,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":1458},{"place":64,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1457},{"place":65,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":1456},{"place":66,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1455},{"place":67,"model":"grok-4.2-0309","company":"xai","family":"Grok","version":"Grok 4.2","score":1455},{"place":68,"model":"deepseek-v4-pro-preview-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1455},{"place":69,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1454},{"place":70,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":1453},{"place":71,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1450},{"place":72,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1450},{"place":73,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1449},{"place":74,"model":"gemini-3-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3","score":1448},{"place":75,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1447},{"place":76,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":1446},{"place":77,"model":"qwen3-max-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":1446},{"place":78,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1443},{"place":79,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1442},{"place":80,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":1442},{"place":81,"model":"longcat-flash-chat","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":1441},{"place":82,"model":"grok-4.2-multi-agent","company":"xai","family":"Grok","version":"Grok 4.20","score":1441},{"place":83,"model":"deepseek-v4-pro-0813-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1441},{"place":84,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1440},{"place":85,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":1440},{"place":86,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":1439},{"place":87,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":1439},{"place":88,"model":"amazon-nova-experimental-chat-26-02-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1437},{"place":89,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1437},{"place":90,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1436},{"place":91,"model":"qwen3-max-2025-09-23","company":"qwen","family":"Qwen","version":"Qwen3","score":1436},{"place":92,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1435},{"place":93,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":1435},{"place":94,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":1435},{"place":95,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":1432},{"place":96,"model":"longcat-flash-chat-2602-exp","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":1432},{"place":97,"model":"grok-4.2-beta1","company":"xai","family":"Grok","version":"Grok 4.2","score":1432},{"place":98,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":1432},{"place":99,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1432},{"place":100,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1431},{"place":101,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1431},{"place":102,"model":"claude-opus-4-1-20250805-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1431},{"place":103,"model":"amazon-nova-experimental-chat-11-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1431},{"place":104,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1429},{"place":105,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1429},{"place":106,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":1429},{"place":107,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":1428},{"place":108,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1427},{"place":109,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":1426},{"place":110,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1426},{"place":111,"model":"amazon-nova-experimental-chat-10-20","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1425},{"place":112,"model":"deepseek-v4-flash-preview-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1425},{"place":113,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1425},{"place":114,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":1424},{"place":115,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":1424},{"place":116,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":1422},{"place":117,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1422},{"place":118,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1422},{"place":119,"model":"deepseek-v3.2-exp-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1422},{"place":120,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1422},{"place":121,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1422},{"place":122,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":1421},{"place":123,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":1420},{"place":124,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1419},{"place":125,"model":"amazon-nova-experimental-chat-12-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1419},{"place":126,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":1419},{"place":127,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1418},{"place":128,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1418},{"place":129,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":1417},{"place":130,"model":"grok-4.6-high","company":"xai","family":"Grok","version":"Grok 4.6","score":1416},{"place":131,"model":"grok-4.1","company":"xai","family":"Grok","version":"Grok 4.1","score":1416},{"place":132,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":1416},{"place":133,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1416},{"place":134,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1415},{"place":135,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1414},{"place":136,"model":"hunyuan-t1-20250711","company":"tencent","family":"Hunyuan","version":"Hunyuan T1","score":1414},{"place":137,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1413},{"place":138,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1413},{"place":139,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":1413},{"place":140,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1412},{"place":141,"model":"gpt-4.5-preview-2025-02-27","company":"openai","family":"GPT","version":"GPT-4.5","score":1412},{"place":142,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1411},{"place":143,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1410},{"place":144,"model":"ernie-5.0-preview-1203","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1410},{"place":145,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":1410},{"place":146,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":1409},{"place":147,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1408},{"place":148,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":1408},{"place":149,"model":"grok-4.1-fast-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1408},{"place":150,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1407},{"place":151,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":1407},{"place":152,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":1407},{"place":153,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":1406},{"place":154,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1406},{"place":155,"model":"ernie-5.0-preview-1022","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1405},{"place":156,"model":"amazon-nova-experimental-chat-26-01-10","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1404},{"place":157,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1404},{"place":158,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":1404},{"place":159,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1402},{"place":160,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1400},{"place":161,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":1399},{"place":162,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1398},{"place":163,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":1398},{"place":164,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1398},{"place":165,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1397},{"place":166,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":1397},{"place":167,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":1396},{"place":168,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":1396},{"place":169,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1396},{"place":170,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1396},{"place":171,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1395},{"place":172,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1395},{"place":173,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1392},{"place":174,"model":"nvidia-llama-3.3-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama 3.3","score":1392},{"place":175,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":1391},{"place":176,"model":"grok-3-preview-02-24","company":"xai","family":"Grok","version":"Grok 3","score":1391},{"place":177,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":1389},{"place":178,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":1389},{"place":179,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1389},{"place":180,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":1388},{"place":181,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":1387},{"place":182,"model":"grok-3-mini-high","company":"xai","family":"Grok","version":"Grok 3","score":1386},{"place":183,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1380},{"place":184,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":1378},{"place":185,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":1378},{"place":186,"model":"mimo-v2-flash-thinking","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1377},{"place":187,"model":"claude-sonnet-4-20250514-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4","score":1375},{"place":188,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":1374},{"place":189,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":1374},{"place":190,"model":"gemini-2.5-flash-lite-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1373},{"place":191,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":1373},{"place":192,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1373},{"place":193,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1373},{"place":194,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":1372},{"place":195,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1371},{"place":196,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1369},{"place":197,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1369},{"place":198,"model":"kimi-k2-0711-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1367},{"place":199,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":1367},{"place":200,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1366},{"place":201,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":1365},{"place":202,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1365},{"place":203,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":1364},{"place":204,"model":"gemini-2.5-flash-lite-preview-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":1362},{"place":205,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":1361},{"place":206,"model":"llama-3.1-nemotron-ultra-253b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1360},{"place":207,"model":"hunyuan-turbos-20250416","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":1359},{"place":208,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":1359},{"place":209,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1359},{"place":210,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":1359},{"place":211,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":1358},{"place":212,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":1355},{"place":213,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":1355},{"place":214,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":1354},{"place":215,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1353},{"place":216,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":1352},{"place":217,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":1351},{"place":218,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":1349},{"place":219,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1343},{"place":220,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":1341},{"place":221,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1336},{"place":222,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":1336},{"place":223,"model":"qwen-plus-0125","company":"qwen","family":"Qwen","version":"Qwen","score":1326},{"place":224,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1319},{"place":225,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":1318},{"place":226,"model":"step-1o-turbo-202506","company":"stepfun","family":"Step","version":"Step 1O Turbo 202506","score":1318},{"place":227,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":1317},{"place":228,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":1316},{"place":229,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1315},{"place":230,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":1314},{"place":231,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1312},{"place":232,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1311},{"place":233,"model":"gemini-2.0-flash-lite-preview-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":1309},{"place":234,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1307},{"place":235,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1307},{"place":236,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":1305},{"place":237,"model":"step-2-16k-exp-202412","company":"stepfun","family":"Step","version":"Step 2 16K EXP 202412","score":1304},{"place":238,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":1304},{"place":239,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1303},{"place":240,"model":"athene-v2-chat","company":"nvidia","family":"Athene","version":"Athene V2","score":1300},{"place":241,"model":"command-a-03-2025","company":"cohere","family":"Command","version":"Command","score":1300},{"place":242,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":1300},{"place":243,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1299},{"place":244,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1297},{"place":245,"model":"hunyuan-turbos-20250226","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":1294},{"place":246,"model":"deepseek-v2.5-1210","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1288},{"place":247,"model":"glm-4-plus-0111","company":"zai","family":"GLM","version":"GLM 4","score":1287},{"place":248,"model":"llama-4-scout-17b-16e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1287},{"place":249,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":1285},{"place":250,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":1284},{"place":251,"model":"grok-2-2024-08-13","company":"xai","family":"Grok","version":"Grok 2","score":1283},{"place":252,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1283},{"place":253,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":1281},{"place":254,"model":"hunyuan-large-2025-02-10","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1281},{"place":255,"model":"llama-3.1-405b-instruct-bf16","company":"meta","family":"Llama","version":"Llama 3.1","score":1278},{"place":256,"model":"qwen-max-0919","company":"qwen","family":"Qwen","version":"Qwen","score":1275},{"place":257,"model":"glm-4-plus","company":"zai","family":"GLM","version":"GLM 4","score":1275},{"place":258,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1274},{"place":259,"model":"hunyuan-standard-2025-02-10","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1274},{"place":260,"model":"hunyuan-turbo-0110","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbo","score":1273},{"place":261,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1273},{"place":262,"model":"gemini-advanced-0514","company":"google","family":"Gemini","version":"Gemini","score":1272},{"place":263,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":1272},{"place":264,"model":"llama-3.1-nemotron-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1271},{"place":265,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":1271},{"place":266,"model":"gemini-1.5-pro-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1269},{"place":267,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":1269},{"place":268,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1269},{"place":269,"model":"hunyuan-large-vision","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1268},{"place":270,"model":"gpt-4-0125-preview","company":"openai","family":"GPT","version":"GPT-4","score":1268},{"place":271,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":1267},{"place":272,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":1267},{"place":273,"model":"grok-2-mini-2024-08-13","company":"xai","family":"Grok","version":"Grok 2","score":1265},{"place":274,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":1261},{"place":275,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":1261},{"place":276,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1261},{"place":277,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":1252},{"place":278,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1252},{"place":279,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1252},{"place":280,"model":"gemma-3n-e4b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":1251},{"place":281,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":1251},{"place":282,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":1250},{"place":283,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":1246},{"place":284,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1244},{"place":285,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":1242},{"place":286,"model":"deepseek-coder-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":1241},{"place":287,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":1240},{"place":288,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1239},{"place":289,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":1235},{"place":290,"model":"hunyuan-standard-256k","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":1235},{"place":291,"model":"athene-70b-0725","company":"nexusflow","family":"Athene","version":"Athene","score":1231},{"place":292,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":1230},{"place":293,"model":"llama-3.1-nemotron-51b-instruct","company":"nvidia","family":"Llama","version":"Llama 3.1","score":1230},{"place":294,"model":"gemini-1.5-flash-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1229},{"place":295,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1227},{"place":296,"model":"reka-core-20240904","company":"reka","family":"Reka","version":"Reka Core 20240904","score":1222},{"place":297,"model":"jamba-1.5-large","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":1221},{"place":298,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":1218},{"place":299,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":1218},{"place":300,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":1217},{"place":301,"model":"nemotron-4-340b-instruct","company":"nvidia","family":"Nemotron","version":"Nemotron-4","score":1216},{"place":302,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":1213},{"place":303,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1213},{"place":304,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1212},{"place":305,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":1208},{"place":306,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1207},{"place":307,"model":"amazon-nova-micro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1206},{"place":308,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":1200},{"place":309,"model":"aya-expanse-32b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1200},{"place":310,"model":"reka-flash-20240904","company":"reka","family":"Reka","version":"Reka Flash 20240904","score":1195},{"place":311,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":1195},{"place":312,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":1188},{"place":313,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":1188},{"place":314,"model":"command-r-plus-08-2024","company":"cohere","family":"Command","version":"Command","score":1188},{"place":315,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1185},{"place":316,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":1184},{"place":317,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1183},{"place":318,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":1182},{"place":319,"model":"mistral-medium","company":"mistral","family":"Mistral","version":"Mistral","score":1180},{"place":320,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":1180},{"place":321,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1179},{"place":322,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":1173},{"place":323,"model":"gemma-2-9b-it-simpo","company":"princeton","family":"Gemma","version":"Gemma 2","score":1173},{"place":324,"model":"aya-expanse-8b","company":"cohere","family":"Aya","version":"Aya Expanse","score":1168},{"place":325,"model":"reka-flash-21b-20240226-online","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226 Online","score":1168},{"place":326,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":1164},{"place":327,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1164},{"place":328,"model":"jamba-1.5-mini","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":1160},{"place":329,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1159},{"place":330,"model":"reka-flash-21b-20240226","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226","score":1156},{"place":331,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1155},{"place":332,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":1155},{"place":333,"model":"phi-3-mini-4k-instruct-june-2024","company":"microsoft","family":"Phi","version":"Phi-3","score":1152},{"place":334,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1152},{"place":335,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":1151},{"place":336,"model":"phi-3-small-8k-instruct","company":"microsoft","family":"Phi","version":"Phi-3","score":1151},{"place":337,"model":"zephyr-orpo-141b-a35b-v0.1","company":"huggingface","family":"Zephyr","version":"Zephyr ORPO 141B A35B v0.1","score":1148},{"place":338,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":1147},{"place":339,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":1145},{"place":340,"model":"granite-3.0-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":1143},{"place":341,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":1142},{"place":342,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":1141},{"place":343,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":1135},{"place":344,"model":"gemini-pro-dev-api","company":"google","family":"Gemini","version":"Gemini","score":1132},{"place":345,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":1129},{"place":346,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1126},{"place":347,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1125},{"place":348,"model":"starling-lm-7b-beta","company":"berkeley","family":"Starling","version":"Starling LM","score":1124},{"place":349,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":1120},{"place":350,"model":"granite-3.0-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.0","score":1117},{"place":351,"model":"wizardlm-70b","company":"wizardlm","family":"WizardLM","version":"WizardLM-70B","score":1116},{"place":352,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":1114},{"place":353,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":1111},{"place":354,"model":"snowflake-arctic-instruct","company":"snowflake","family":"Arctic","version":"Arctic Instruct","score":1109},{"place":355,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":1108},{"place":356,"model":"tulu-2-dpo-70b","company":"ai2","family":"Tulu","version":"Tulu 2 DPO 70B","score":1107},{"place":357,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":1107},{"place":358,"model":"openchat-3.5-0106","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":1107},{"place":359,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1105},{"place":360,"model":"openhermes-2.5-mistral-7b","company":"openhermes","family":"OpenHermes","version":"OpenHermes 2.5","score":1098},{"place":361,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1091},{"place":362,"model":"phi-3-mini-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":1089},{"place":363,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1086},{"place":364,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":1085},{"place":365,"model":"starling-lm-7b-alpha","company":"berkeley","family":"Starling","version":"Starling LM","score":1081},{"place":366,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1080},{"place":367,"model":"dolphin-2.2.1-mistral-7b","company":"cognitivecomputations","family":"Dolphin","version":"Dolphin","score":1077},{"place":368,"model":"llama2-70b-steerlm-chat","company":"nvidia","family":"Llama","version":"Llama 2","score":1072},{"place":369,"model":"openchat-3.5","company":"openchat","family":"OpenChat","version":"OpenChat 3.5","score":1071},{"place":370,"model":"vicuna-33b","company":"lmsys","family":"Vicuna","version":"Vicuna-33B","score":1071},{"place":371,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":1068},{"place":372,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":1066},{"place":373,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1065},{"place":374,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":1064},{"place":375,"model":"nous-hermes-2-mixtral-8x7b-dpo","company":"nousresearch","family":"Nous Hermes","version":"Nous Hermes 2","score":1061},{"place":376,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":1056},{"place":377,"model":"palm-2","company":"google","family":"PaLM","version":"PaLM 2","score":1049},{"place":378,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":1047},{"place":379,"model":"mpt-30b-chat","company":"mosaicml","family":"MPT","version":"MPT","score":1047},{"place":380,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1042},{"place":381,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":1041},{"place":382,"model":"stripedhyena-nous-7b","company":"togethercomputer","family":"StripedHyena","version":"StripedHyena Nous 7B","score":1033},{"place":383,"model":"guanaco-33b","company":"timdettmers","family":"Guanaco","version":"Guanaco-33B","score":1033},{"place":384,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":1030},{"place":385,"model":"mistral-7b-instruct","company":"mistral","family":"Mistral","version":"Mistral","score":1027},{"place":386,"model":"qwen1.5-4b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":1026},{"place":387,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":1018},{"place":388,"model":"wizardlm-13b","company":"wizardlm","family":"WizardLM","version":"WizardLM-13B","score":1017},{"place":389,"model":"gemma-2b-it","company":"google","family":"Gemma","version":"Gemma","score":1009},{"place":390,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":994},{"place":391,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":989},{"place":392,"model":"gpt4all-13b-snoozy","company":"nomic","family":"GPT4All","version":"GPT4All","score":941},{"place":393,"model":"koala-13b","company":"ucberkeley","family":"Koala","version":"Koala","score":932},{"place":394,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":926},{"place":395,"model":"rwkv-4-raven-14b","company":"rwkv","family":"RWKV","version":"RWKV-4 Raven","score":922},{"place":396,"model":"mpt-7b-chat","company":"mosaicml","family":"MPT","version":"MPT","score":919},{"place":397,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":915},{"place":398,"model":"alpaca-13b","company":"stanford","family":"Alpaca","version":"Alpaca","score":908},{"place":399,"model":"oasst-pythia-12b","company":"oasst","family":"OASST","version":"OASST-Pythia","score":892},{"place":400,"model":"dolly-v2-12b","company":"databricks","family":"Dolly","version":"Dolly v2","score":871},{"place":401,"model":"fastchat-t5-3b","company":"lmsys","family":"FastChat","version":"FastChat","score":862},{"place":402,"model":"stablelm-tuned-alpha-7b","company":"stabilityai","family":"StableLM","version":"Tuned Alpha 7B","score":839},{"place":403,"model":"llama-13b","company":"meta","family":"Llama","version":"LLaMA","score":838}]},{"id":"lmarena-vision","name":"LMArena Vision","topic":"Crowd eval (vision)","description":"Chatbot Arena vision evaluation leaderboard (ELO ratings).","url":"","leaderboard":"https://lmarena.ai/leaderboard/vision","github":"","paper":"","metric":"elo","stars":"","top_model":"Claude Fable 5 (high)","top_percent":1308,"top_model_id":"claude-fable-5-high","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":168,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1308},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1301},{"place":3,"model":"claude-opus-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1299},{"place":4,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1298},{"place":5,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1298},{"place":6,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":1297},{"place":7,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1294},{"place":8,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":1294},{"place":9,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":1294},{"place":10,"model":"muse-spark-1.2-xhigh","company":"meta","family":"Muse","version":"Muse Spark","score":1293},{"place":11,"model":"claude-opus-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1293},{"place":12,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1290},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":1289},{"place":14,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":1289},{"place":15,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1287},{"place":16,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1287},{"place":17,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":1286},{"place":18,"model":"muse-spark-1.3-xhigh","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1286},{"place":19,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":1286},{"place":20,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1286},{"place":21,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1286},{"place":22,"model":"gemini-3.5-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.5","score":1285},{"place":23,"model":"gpt-5.4-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1285},{"place":24,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":1284},{"place":25,"model":"gpt-5.5-high","company":"openai","family":"GPT","version":"GPT-5.5","score":1281},{"place":26,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":1281},{"place":27,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":1280},{"place":28,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":1280},{"place":29,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1280},{"place":30,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1279},{"place":31,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":1279},{"place":32,"model":"gpt-5.2-instant","company":"openai","family":"GPT","version":"GPT-5.2","score":1278},{"place":33,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":1276},{"place":34,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1275},{"place":35,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":1273},{"place":36,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":1273},{"place":37,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":1272},{"place":38,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":1270},{"place":39,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1268},{"place":40,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1266},{"place":41,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":1266},{"place":42,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":1265},{"place":43,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1264},{"place":44,"model":"claude-sonnet-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1263},{"place":45,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1262},{"place":46,"model":"grok-4.6-high","company":"xai","family":"Grok","version":"Grok 4.6","score":1262},{"place":47,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1260},{"place":48,"model":"gemini-3-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3","score":1260},{"place":49,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1258},{"place":50,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":1256},{"place":51,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":1256},{"place":52,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1252},{"place":53,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":1251},{"place":54,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1251},{"place":55,"model":"grok-4.2-multi-agent","company":"xai","family":"Grok","version":"Grok 4.20","score":1250},{"place":56,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":1250},{"place":57,"model":"mimo-v2.6-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1248},{"place":58,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1248},{"place":59,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":1248},{"place":60,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1246},{"place":61,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1246},{"place":62,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1244},{"place":63,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":1243},{"place":64,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":1243},{"place":65,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1242},{"place":66,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":1242},{"place":67,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":1241},{"place":68,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":1240},{"place":69,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":1239},{"place":70,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1236},{"place":71,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":1236},{"place":72,"model":"chatgpt-4o-latest-20250326","company":"openai","family":"GPT","version":"GPT-4o","score":1235},{"place":73,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":1235},{"place":74,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1234},{"place":75,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":1231},{"place":76,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1229},{"place":77,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":1229},{"place":78,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1226},{"place":79,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":1226},{"place":80,"model":"gpt-4.5-preview-2025-02-27","company":"openai","family":"GPT","version":"GPT-4.5","score":1225},{"place":81,"model":"gpt-4.5-preview-2025-02-27","company":"openai","family":"GPT","version":"GPT-4.5","score":1222},{"place":82,"model":"ernie-5.0-preview-1220","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":1219},{"place":83,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":1217},{"place":84,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1217},{"place":85,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1216},{"place":86,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":1216},{"place":87,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1215},{"place":88,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1215},{"place":89,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1214},{"place":90,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":1213},{"place":91,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1210},{"place":92,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1210},{"place":93,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1208},{"place":94,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1208},{"place":95,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":1208},{"place":96,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1207},{"place":97,"model":"claude-sonnet-4-20250514-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4","score":1206},{"place":98,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1205},{"place":99,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1205},{"place":100,"model":"claude-opus-4-20250514-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4","score":1204},{"place":101,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1201},{"place":102,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":1201},{"place":103,"model":"claude-sonnet-4-20250514-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4","score":1200},{"place":104,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":1200},{"place":105,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1200},{"place":106,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1199},{"place":107,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":1196},{"place":108,"model":"grok-4.1-fast-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1196},{"place":109,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1195},{"place":110,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1193},{"place":111,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1193},{"place":112,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":1193},{"place":113,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1191},{"place":114,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":1189},{"place":115,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1189},{"place":116,"model":"gemini-2.5-flash-lite-preview-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":1188},{"place":117,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1188},{"place":118,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1188},{"place":119,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":1185},{"place":120,"model":"qwen-vl-max-2025-08-13","company":"qwen","family":"Qwen","version":"Qwen VL Max","score":1185},{"place":121,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1184},{"place":122,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":1184},{"place":123,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":1183},{"place":124,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1182},{"place":125,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":1179},{"place":126,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1179},{"place":127,"model":"gemini-2.5-flash-lite-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":1175},{"place":128,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1175},{"place":129,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":1174},{"place":130,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1174},{"place":131,"model":"qwen-vl-max-2025-08-13","company":"qwen","family":"Qwen","version":"Qwen VL Max","score":1173},{"place":132,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":1172},{"place":133,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":1162},{"place":134,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":1161},{"place":135,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1160},{"place":136,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1160},{"place":137,"model":"mistral-medium-2508","company":"mistral","family":"Mistral","version":"Mistral","score":1159},{"place":138,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":1158},{"place":139,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1157},{"place":140,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":1156},{"place":141,"model":"step-1o-turbo-202506","company":"stepfun","family":"Step","version":"Step 1O Turbo 202506","score":1156},{"place":142,"model":"mistral-medium-2505","company":"mistral","family":"Mistral","version":"Mistral","score":1155},{"place":143,"model":"hunyuan-vision-1.5-thinking","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1155},{"place":144,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":1153},{"place":145,"model":"step-1o-turbo-202506","company":"stepfun","family":"Step","version":"Step 1O Turbo 202506","score":1149},{"place":146,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":1149},{"place":147,"model":"hunyuan-large-vision","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1149},{"place":148,"model":"mistral-medium-2505","company":"mistral","family":"Mistral","version":"Mistral","score":1148},{"place":149,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":1146},{"place":150,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1145},{"place":151,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":1145},{"place":152,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1145},{"place":153,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":1144},{"place":154,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1143},{"place":155,"model":"hunyuan-large-vision","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1141},{"place":156,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1141},{"place":157,"model":"mistral-small-2506","company":"mistral","family":"Mistral","version":"Mistral","score":1140},{"place":158,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":1139},{"place":159,"model":"mistral-medium-2508","company":"mistral","family":"Mistral","version":"Mistral","score":1138},{"place":160,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1138},{"place":161,"model":"gemini-2.0-flash-lite-preview-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":1136},{"place":162,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":1134},{"place":163,"model":"mistral-small-2506","company":"mistral","family":"Mistral","version":"Mistral","score":1132},{"place":164,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1129},{"place":165,"model":"gemini-2.0-flash-lite-preview-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":1129},{"place":166,"model":"llama-4-scout-17b-16e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1127},{"place":167,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1127},{"place":168,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1127},{"place":169,"model":"step-1o-vision-32k-highres","company":"stepfun","family":"Step","version":"Step 1O Vision","score":1124},{"place":170,"model":"llama-4-scout-17b-16e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1122},{"place":171,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":1121},{"place":172,"model":"gemini-1.5-pro-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1120},{"place":173,"model":"step-1o-vision-32k-highres","company":"stepfun","family":"Step","version":"Step 1O Vision","score":1119},{"place":174,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":1119},{"place":175,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":1118},{"place":176,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":1118},{"place":177,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":1117},{"place":178,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":1115},{"place":179,"model":"gemini-1.5-pro-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1113},{"place":180,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":1112},{"place":181,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":1112},{"place":182,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":1111},{"place":183,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":1109},{"place":184,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":1097},{"place":185,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":1095},{"place":186,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":1093},{"place":187,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":1089},{"place":188,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1089},{"place":189,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1085},{"place":190,"model":"qwen-vl-max-1119","company":"qwen","family":"Qwen","version":"Qwen VL Max","score":1085},{"place":191,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1084},{"place":192,"model":"qwen-vl-max-1119","company":"qwen","family":"Qwen","version":"Qwen VL Max","score":1081},{"place":193,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1081},{"place":194,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1071},{"place":195,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1066},{"place":196,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":1064},{"place":197,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1061},{"place":198,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1060},{"place":199,"model":"gemini-1.5-flash-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1059},{"place":200,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":1057},{"place":201,"model":"gemini-1.5-flash-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":1056},{"place":202,"model":"molmo-72b-0924","company":"allenai","family":"Molmo","version":"Molmo","score":1045},{"place":203,"model":"molmo-72b-0924","company":"allenai","family":"Molmo","version":"Molmo","score":1044},{"place":204,"model":"hunyuan-standard-vision-2024-12-31","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1041},{"place":205,"model":"hunyuan-standard-vision-2024-12-31","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":1040},{"place":206,"model":"llama-3.2-vision-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1032},{"place":207,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1031},{"place":208,"model":"llama-3.2-vision-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":1028},{"place":209,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1028},{"place":210,"model":"pixtral-12b-2409","company":"mistral","family":"Pixtral","version":"Pixtral","score":1025},{"place":211,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":1025},{"place":212,"model":"pixtral-12b-2409","company":"mistral","family":"Pixtral","version":"Pixtral","score":1020},{"place":213,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":1020},{"place":214,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1019},{"place":215,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1018},{"place":216,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1017},{"place":217,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":1016},{"place":218,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":1016},{"place":219,"model":"yi-vision","company":"01ai","family":"Yi","version":"Yi Vision","score":1002},{"place":220,"model":"yi-vision","company":"01ai","family":"Yi","version":"Yi Vision","score":1000},{"place":221,"model":"c4ai-aya-vision-32b","company":"cohere","family":"Aya","version":"Aya Vision","score":1000},{"place":222,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":1000},{"place":223,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":1000},{"place":224,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":999},{"place":225,"model":"c4ai-aya-vision-32b","company":"cohere","family":"Aya","version":"Aya Vision","score":996},{"place":226,"model":"molmo-7b-d-0924","company":"allenai","family":"Molmo","version":"Molmo","score":993},{"place":227,"model":"llama-3.2-vision-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":993},{"place":228,"model":"molmo-7b-d-0924","company":"allenai","family":"Molmo","version":"Molmo","score":992},{"place":229,"model":"llama-3.2-vision-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":987},{"place":230,"model":"nvila-internal-15b-v1","company":"nvidia","family":"NVILA","version":"NVILA","score":985},{"place":231,"model":"nvila-internal-15b-v1","company":"nvidia","family":"NVILA","version":"NVILA","score":984},{"place":232,"model":"llava-onevision-qwen2-72b-ov","company":"llava","family":"LLaVA","version":"LLaVA OneVision","score":978},{"place":233,"model":"llava-onevision-qwen2-72b-ov","company":"llava","family":"LLaVA","version":"LLaVA OneVision","score":977},{"place":234,"model":"llava-1.6-34b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":964},{"place":235,"model":"llava-1.6-34b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":963},{"place":236,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":963},{"place":237,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":962},{"place":238,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":961},{"place":239,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":960},{"place":240,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":958},{"place":241,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":953},{"place":242,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":919},{"place":243,"model":"phi-3-vision-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":881}]},{"id":"loca-bench","name":"LOCA-Bench","topic":"Long-context agents","description":"LOCA-Bench long-context agent benchmark (environment description length 256K).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":57,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":57},{"place":2,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":49.3}]},{"id":"local-agent-bench","name":"Local Agent Bench","topic":"Tool calling judgment","description":"Tests whether small open-weight models can reliably decide when to call tools and when not to. Agent Score = (Action x 0.4) + (Restraint x 0.3) + (Wrong-Tool-Avoidance x 0.3).","url":"","leaderboard":"","github":"https://github.com/MikeVeerman/tool-calling-benchmark","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 1.2B Instruct","top_percent":88,"top_model_id":"lfm2.5-1.2b-instruct","top_generation":"LFM2.5","top_model_base":"LFM2.5 1.2B Instruct","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":88},{"place":2,"model":"phi-4-mini-3.8b","company":"microsoft","family":"Phi","version":"Phi 4 mini","score":88},{"place":3,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":88},{"place":4,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":88},{"place":5,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84},{"place":6,"model":"bitnet-2b-4t","company":"microsoft","family":"BitNet","version":"BitNet b1.58","score":81},{"place":7,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":80},{"place":8,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":74},{"place":9,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":72},{"place":10,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":71},{"place":11,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67},{"place":12,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":67},{"place":13,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":67},{"place":14,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":66},{"place":15,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":64},{"place":16,"model":"functiongemma","company":"meetkai","family":"Gemma","version":"FunctionGemma","score":64},{"place":17,"model":"bitnet-3b","company":"microsoft","family":"BitNet","version":"BitNet b1.58","score":60},{"place":18,"model":"jan-v3","company":"menlo","family":"Jan","version":"Jan v3","score":56},{"place":19,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":55},{"place":20,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":48},{"place":21,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":43}]},{"id":"locomo","name":"LoCoMo","topic":"Long-term memory","description":"Very long-term conversational memory: QA over multi-session dialogues.","url":"https://snap-research.github.io/locomo/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2402.17753","metric":"percent","stars":"","top_model":"MemT-1.0-Flash","top_percent":65.1,"top_model_id":"memt-1.0-flash","top_generation":"MemT-1.0","top_model_base":"MemT-1.0-Flash","top_model_family":"MemT","top_company":"memtensor","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"memt-1.0-flash","company":"memtensor","family":"MemT","version":"MemT-1.0","score":65.1},{"place":2,"model":"memt-1.0-nano","company":"memtensor","family":"MemT","version":"MemT-1.0","score":57.5}]},{"id":"logicvista","name":"LogicVista","topic":"Visual logical reasoning","description":"Visual logic and pattern reasoning tasks requiring compositional and spatial understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":91.9,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":65,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.9},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":89.7},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85.7},{"place":4,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":84.3},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82.6},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80.8},{"place":7,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":76.7},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.8},{"place":10,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":73.8},{"place":11,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":73.4},{"place":12,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":73.4},{"place":13,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.2},{"place":14,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":71.8},{"place":15,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":71.6},{"place":16,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.9},{"place":17,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":70.3},{"place":18,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70},{"place":19,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":69.35},{"place":20,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":69.12},{"place":21,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":69.1},{"place":22,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.7},{"place":23,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":67.56},{"place":24,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":66.9},{"place":25,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.3},{"place":26,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":64.88},{"place":27,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":64},{"place":28,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.75},{"place":29,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":63.53},{"place":30,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":62.4},{"place":31,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":60.4},{"place":32,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":60.2},{"place":33,"model":"r-4b-base","company":"tencent","family":"R","version":"R","score":59.1},{"place":34,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":58.61},{"place":35,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":58.39},{"place":36,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57.3},{"place":37,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":56.4},{"place":38,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.3},{"place":39,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":53.8},{"place":40,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":53.47},{"place":41,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.2},{"place":42,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":52.4},{"place":43,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":51.4},{"place":44,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":50.6},{"place":45,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":48.32},{"place":46,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":47.7},{"place":47,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":47.7},{"place":48,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":47.43},{"place":49,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":47.42},{"place":50,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":47.3},{"place":51,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.5},{"place":52,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":44.51},{"place":53,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":44.5},{"place":54,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":43.6},{"place":55,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":43.4},{"place":56,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":41.8},{"place":57,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":41.3},{"place":58,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":40.5},{"place":59,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.6},{"place":60,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":37.4},{"place":61,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":36.2},{"place":62,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":35.8},{"place":63,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":35.57},{"place":64,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":35.57},{"place":65,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.4},{"place":66,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.5},{"place":67,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34},{"place":68,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":33.9},{"place":69,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":32.2},{"place":70,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":30.9},{"place":71,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":29.5},{"place":72,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":28.6},{"place":73,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":24.8}]},{"id":"logiqa","name":"LogiQA","topic":"Logical reasoning","description":"Reading comprehension with logical reasoning.","url":"https://github.com/lgw863/LogiQA-dataset","leaderboard":"","github":"","paper":"","metric":"percent","stars":"138","top_model":"Pythia 70M","top_percent":23.5,"top_model_id":"pythia-70m","top_generation":"Pythia","top_model_base":"Pythia 70M","top_model_family":"Pythia","top_company":"eleutherai","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"pythia-70m","company":"eleutherai","family":"Pythia","version":"Pythia","score":23.5},{"place":2,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":22.4},{"place":3,"model":"pythia-1.4b","company":"eleutherai","family":"Pythia","version":"Pythia","score":22.1},{"place":4,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":21.5},{"place":5,"model":"pythia-2.8b","company":"eleutherai","family":"Pythia","version":"Pythia","score":21.4},{"place":6,"model":"pythia-1b","company":"eleutherai","family":"Pythia","version":"Pythia","score":21.2},{"place":7,"model":"pythia-160m","company":"eleutherai","family":"Pythia","version":"Pythia","score":21},{"place":8,"model":"pythia-410m","company":"eleutherai","family":"Pythia","version":"Pythia","score":20.9}]},{"id":"longbench","name":"LongBench","topic":"Long-context eval","description":"Long-context understanding across tasks.","url":"https://github.com/THUDM/LongBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"957","top_model":"Qwen3.6-27B","top_percent":60.9,"top_model_id":"qwen3.6-27b","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 27B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":37,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":60.9},{"place":2,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":60},{"place":3,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":56.9},{"place":4,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":56},{"place":5,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.9},{"place":6,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":53.7},{"place":7,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":53.5},{"place":8,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":52.62},{"place":9,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":52.3},{"place":10,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.87},{"place":11,"model":"chatglm3-6b-32k","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":50.2},{"place":12,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":48.4},{"place":13,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":48.1},{"place":14,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":46.8},{"place":15,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":46.1},{"place":16,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":44.8},{"place":17,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":43.85},{"place":18,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":42.81},{"place":19,"model":"chatglm2-6b-32k","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":41.5},{"place":20,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.96},{"place":21,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":38.3},{"place":22,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":37},{"place":23,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":32},{"place":24,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":31.05},{"place":25,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":30.9},{"place":26,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":29.93},{"place":27,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":29.7},{"place":28,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":29.57},{"place":29,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":25.9},{"place":30,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":21.47},{"place":31,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":20.58},{"place":32,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":20.4},{"place":33,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":17.7},{"place":34,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":17.5},{"place":35,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":14.3},{"place":36,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":13.6},{"place":37,"model":"command-r7b","company":"cohere","family":"Command","version":"Command","score":2}]},{"id":"longbench-v2","name":"longbench-v2","topic":"Long-context eval","description":"Next-generation LongBench v2 long-context evaluation benchmark.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2412.15204","metric":"percent","stars":"","top_model":"Claude Opus 4.8","top_percent":69.1,"top_model_id":"claude-opus-4.8","top_generation":"Claude 4.8","top_model_base":"Claude Opus 4.8","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":141,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.1},{"place":2,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.9},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68.2},{"place":4,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":67.5},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":67.4},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":67.4},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":67.1},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":67.1},{"place":9,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.3},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.72},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65.6},{"place":12,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":65.6},{"place":13,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":65.5},{"place":14,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":65.4},{"place":15,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":65.3},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":65},{"place":17,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65},{"place":18,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.4},{"place":19,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.4},{"place":20,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.3},{"place":21,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":64},{"place":22,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":64},{"place":23,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.8},{"place":24,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":63.2},{"place":25,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.2},{"place":26,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":62.82},{"place":27,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":62.5},{"place":28,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.1},{"place":29,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62},{"place":30,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62},{"place":31,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":62},{"place":32,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":61.9},{"place":33,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.8},{"place":34,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":61.5},{"place":35,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":61},{"place":36,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":61},{"place":37,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":61},{"place":38,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":60.9},{"place":39,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":60.8},{"place":40,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":60.6},{"place":41,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":60.6},{"place":42,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.6},{"place":43,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.2},{"place":44,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":60.2},{"place":45,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.93},{"place":46,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":59.8},{"place":47,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":59.64},{"place":48,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":59.6},{"place":49,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":59.6},{"place":50,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":59.6},{"place":51,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.48},{"place":52,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.44},{"place":53,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":54,"model":"o3","company":"openai","family":"o3","version":"o3","score":58.8},{"place":55,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":58.4},{"place":56,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":58.3},{"place":57,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.28},{"place":58,"model":"qwen3-max-thinking-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":57.89},{"place":59,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57.7},{"place":60,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":57.5},{"place":61,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":57.46},{"place":62,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57},{"place":63,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":56.8},{"place":64,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.77},{"place":65,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":56.7},{"place":66,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":56.4},{"place":67,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":55.9},{"place":68,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":55.8},{"place":69,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":55.6},{"place":70,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.5},{"place":71,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":55.3},{"place":72,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.2},{"place":73,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":55.2},{"place":74,"model":"golongrl-30b-a3b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":55.1},{"place":75,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.8},{"place":76,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":54.5},{"place":77,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.5},{"place":78,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":54.3},{"place":79,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":53.68},{"place":80,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":53.3},{"place":81,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":52.9},{"place":82,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":52.88},{"place":83,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":52.5},{"place":84,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":52.5},{"place":85,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":52.5},{"place":86,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":52.3},{"place":87,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":52.1},{"place":88,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":52.1},{"place":89,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":51.89},{"place":90,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.5},{"place":91,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":51.1},{"place":92,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":50.5},{"place":93,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":50.3},{"place":94,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.1},{"place":95,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.1},{"place":96,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50},{"place":97,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":49.4},{"place":98,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":49.34},{"place":99,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":49.3},{"place":100,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":49.1},{"place":101,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48.7},{"place":102,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":48.7},{"place":103,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":48.7},{"place":104,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":48.67},{"place":105,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":48.31},{"place":106,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":48.3},{"place":107,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":48.2},{"place":108,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":48.1},{"place":109,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":48},{"place":110,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.3},{"place":111,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.2},{"place":112,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":47.1},{"place":113,"model":"golongrl-4b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":47.1},{"place":114,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":47.01},{"place":115,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":46.4},{"place":116,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.92},{"place":117,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":45.7},{"place":118,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":45.6},{"place":119,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":45.3},{"place":120,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.3},{"place":121,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":45.2},{"place":122,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":45.1},{"place":123,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":44.8},{"place":124,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.7},{"place":125,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":44.1},{"place":126,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":43.74},{"place":127,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":43.7},{"place":128,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":43.54},{"place":129,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":42.8},{"place":130,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":42.8},{"place":131,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.7},{"place":132,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":42.6},{"place":133,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":41.3},{"place":134,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":41},{"place":135,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":40.7},{"place":136,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":40.3},{"place":137,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.2},{"place":138,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":40.2},{"place":139,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":39.6},{"place":140,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39.4},{"place":141,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.7},{"place":142,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":37.42},{"place":143,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":36.6},{"place":144,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":36.1},{"place":145,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":36},{"place":146,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":35.4},{"place":147,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":34.99},{"place":148,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":34.19},{"place":149,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":34},{"place":150,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":33.4},{"place":151,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":33.4},{"place":152,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.2},{"place":153,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":32},{"place":154,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":31.6},{"place":155,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":31.4},{"place":156,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":30.4},{"place":157,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":30.4},{"place":158,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":30.3},{"place":159,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":30.02},{"place":160,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":30},{"place":161,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":29},{"place":162,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.8},{"place":163,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":26.5},{"place":164,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.1},{"place":165,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.9},{"place":166,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":15.51},{"place":167,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":12.13}]},{"id":"longcodebench","name":"LongCodeBench","topic":"Long-context code understanding","description":"Long-context code comprehension and repair benchmark (reported at 1M-token context).","url":"https://arxiv.org/abs/2505.07897","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nova 2 Lite","top_percent":84,"top_model_id":"nova-2-lite","top_generation":"Nova 2","top_model_base":"Nova 2 Lite","top_model_family":"Nova","top_company":"amazon","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":84},{"place":2,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":84},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82},{"place":4,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":82},{"place":5,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":78},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74},{"place":7,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":42}]},{"id":"longfact-concepts","name":"LongFact-Concepts","topic":"Factuality on open-source prompts","description":"Long-context factuality eval focused on conceptual statements; scored as 100 - hallucination rate, higher is better.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2 (high)","top_percent":99.7,"top_model_id":"gpt-5.2-high","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":99.7},{"place":2,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":99.5},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":99.3},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.8},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":98.6},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.5},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":98.5},{"place":8,"model":"o3","company":"openai","family":"o3","version":"o3","score":95.5},{"place":9,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":92.8},{"place":10,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":92.4},{"place":11,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":91.4}]},{"id":"longfact-objects","name":"LongFact-Objects","topic":"Factuality on open-source prompts","description":"Long-context factuality eval focused on object/entity references; scored as 100 - hallucination rate, higher is better.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":99.2,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":99.2},{"place":2,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":99.2},{"place":3,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":99.2},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":99},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.8},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":98.1},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":97.9},{"place":8,"model":"o3","company":"openai","family":"o3","version":"o3","score":94.9},{"place":9,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":92.9},{"place":10,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":92.2},{"place":11,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":87}]},{"id":"longmemeval","name":"LongMemEval","topic":"Long-term memory","description":"Evaluates LLMs' long-term memory and retrieval over extended contexts and multi-session interactions.","url":"https://xiaowu0162.github.io/long-mem-eval/","leaderboard":"","github":"https://github.com/xiaowu0162/LongMemEval","paper":"https://arxiv.org/abs/2410.10813","metric":"percent","stars":"","top_model":"Qwen3.5-4B-Q4_K_M","top_percent":76.6,"top_model_id":"qwen3.5-4b-q4-k-m","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.6},{"place":2,"model":"golongrl-30b-a3b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":75.2},{"place":3,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":72.2},{"place":4,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":72.1},{"place":5,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":71.1},{"place":6,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":70.95},{"place":7,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":69.92},{"place":8,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":68},{"place":9,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":67.95},{"place":10,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.85},{"place":11,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64.8},{"place":12,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":64.6},{"place":13,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":61.6},{"place":14,"model":"golongrl-4b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":61.2},{"place":15,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.6},{"place":16,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":50.6},{"place":17,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.6},{"place":18,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":27.15},{"place":19,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":25.2}]},{"id":"longtext-bench-en","name":"LongText-Bench EN","topic":"Text rendering","description":"LongText-Bench English subset score for text rendering.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Seedream 4.5","top_percent":0.989,"top_model_id":"seedream-4.5","top_generation":"Seedream","top_model_base":"Seedream 4.5","top_model_family":"Seedream","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":0.989},{"place":2,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":0.981},{"place":3,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":0.956},{"place":4,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.956},{"place":5,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":0.952},{"place":6,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.943},{"place":7,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":0.935},{"place":8,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":0.921},{"place":9,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":0.917}]},{"id":"longtext-bench-zh","name":"LongText-Bench ZH","topic":"Text rendering","description":"LongText-Bench Chinese subset score for text rendering.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Seedream 4.5","top_percent":0.987,"top_model_id":"seedream-4.5","top_generation":"Seedream","top_model_base":"Seedream 4.5","top_model_family":"Seedream","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":0.987},{"place":2,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":0.979},{"place":3,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.965},{"place":4,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":0.949},{"place":5,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.946},{"place":6,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":0.936},{"place":7,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":0.926},{"place":8,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":0.926},{"place":9,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":0.619}]},{"id":"longvideobench","name":"LongVideoBench","topic":"Long video QA","description":"Long video understanding and QA benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Turbo","top_percent":80.6,"top_model_id":"seed2.1-turbo","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Turbo","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":87,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.6},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.6},{"place":3,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.3},{"place":4,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.3},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.2},{"place":6,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":79.8},{"place":7,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":79.2},{"place":8,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":79},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78.2},{"place":10,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":77.8},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77.7},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.6},{"place":13,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":77.6},{"place":14,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":77.4},{"place":15,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.3},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.8},{"place":17,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":76.8},{"place":18,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.7},{"place":19,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":76.5},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.5},{"place":21,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":75.9},{"place":22,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":74.8},{"place":23,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":74.5},{"place":24,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":74.1},{"place":25,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":74},{"place":26,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.1},{"place":27,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":72.6},{"place":28,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.5},{"place":29,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":69.7},{"place":30,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":68.9},{"place":31,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":68},{"place":32,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.7},{"place":33,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":67.5},{"place":34,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":67.3},{"place":35,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.2},{"place":36,"model":"internvl3.5-241b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":67.1},{"place":37,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":67},{"place":38,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":66.94},{"place":39,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":66.9},{"place":40,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":66.7},{"place":41,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.6},{"place":42,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":66.4},{"place":43,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":66},{"place":44,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":66},{"place":45,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":65.7},{"place":46,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.6},{"place":47,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.1},{"place":48,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":64.7},{"place":49,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":64},{"place":50,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":63.9},{"place":51,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":63.7},{"place":52,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":63.6},{"place":53,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":63.35},{"place":54,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":63.3},{"place":55,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.1},{"place":56,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":62.9},{"place":57,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.8},{"place":58,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.6},{"place":59,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.4},{"place":60,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":62.1},{"place":61,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.6},{"place":62,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":61.3},{"place":63,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":61.3},{"place":64,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":61.1},{"place":65,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":60.9},{"place":66,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":60.8},{"place":67,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":60.7},{"place":68,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":60.6},{"place":69,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":60.51},{"place":70,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":60},{"place":71,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":59.9},{"place":72,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":59.5},{"place":73,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":59.1},{"place":74,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":58.2},{"place":75,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":57.9},{"place":76,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.7},{"place":77,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57.4},{"place":78,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":56.9},{"place":79,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":56.1},{"place":80,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":55.6},{"place":81,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":55.2},{"place":82,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":54.9},{"place":83,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":54.6},{"place":84,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":54},{"place":85,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":53.8},{"place":86,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":53.4},{"place":87,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":53},{"place":88,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.1},{"place":89,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":52},{"place":90,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":51.2},{"place":91,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":49.7},{"place":92,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":47.9},{"place":93,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.2},{"place":94,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.4},{"place":95,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":46},{"place":96,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":43.3},{"place":97,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":43},{"place":98,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":41.14},{"place":99,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":38.1},{"place":100,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":30.4}]},{"id":"lpfqa","name":"LPFQA","topic":"Finance QA","description":"Long-form financial question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.5","top_percent":54.9,"top_model_id":"claude-sonnet-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Sonnet 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.9},{"place":2,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":54.4},{"place":3,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":54.4},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":52.6},{"place":5,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":52.6},{"place":6,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":51.6},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.2},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.1},{"place":9,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":50.9},{"place":10,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":50.7},{"place":11,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":49.5},{"place":12,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":49.1},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.7},{"place":14,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":47.2}]},{"id":"lvbench","name":"LVBench","topic":"Video understanding","description":"Long video understanding benchmark (LVBench).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":91.7,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":101,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":91.7},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":87.5},{"place":3,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":87.1},{"place":4,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":85.4},{"place":5,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":84.2},{"place":6,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":83.7},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":82.1},{"place":8,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.8},{"place":9,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":79.7},{"place":10,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":78.9},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":78.8},{"place":12,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":78},{"place":13,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":77.4},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77},{"place":15,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":76.9},{"place":16,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":76.8},{"place":17,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.6},{"place":18,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":76.4},{"place":19,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":76.4},{"place":20,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":76.3},{"place":21,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.2},{"place":22,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":76.2},{"place":23,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":75.9},{"place":24,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":75.9},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.7},{"place":26,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.5},{"place":27,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":75.4},{"place":28,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":75.1},{"place":29,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.8},{"place":30,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.4},{"place":31,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":73.7},{"place":32,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.6},{"place":33,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.5},{"place":34,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":73.5},{"place":35,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73},{"place":36,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":73},{"place":37,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":73},{"place":38,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":72.4},{"place":39,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.4},{"place":40,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":71.4},{"place":41,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":71.2},{"place":42,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70},{"place":43,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68.5},{"place":44,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":68},{"place":45,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":67.3},{"place":46,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":66.6},{"place":47,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.4},{"place":48,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":66.2},{"place":49,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":65.7},{"place":50,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65.2},{"place":51,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.9},{"place":52,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":64.6},{"place":53,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":64.6},{"place":54,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.8},{"place":55,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.6},{"place":56,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.6},{"place":57,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":63},{"place":58,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.5},{"place":59,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.2},{"place":60,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":60.9},{"place":61,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":59.5},{"place":62,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.2},{"place":63,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58},{"place":64,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.3},{"place":65,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.1},{"place":66,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.2},{"place":67,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":54.7},{"place":68,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":53.9},{"place":69,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":53.8},{"place":70,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.5},{"place":71,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":52.8},{"place":72,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":52.5},{"place":73,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":50.9},{"place":74,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":50.9},{"place":75,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":50.6},{"place":76,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.5},{"place":77,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":50.4},{"place":78,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":50.2},{"place":79,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":49.6},{"place":80,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":49.5},{"place":81,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":48.2},{"place":82,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":47.6},{"place":83,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.6},{"place":84,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.4},{"place":85,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":47.3},{"place":86,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":45.9},{"place":87,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.1},{"place":88,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":44.5},{"place":89,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":44.2},{"place":90,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":44},{"place":91,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":44},{"place":92,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":43.4},{"place":93,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":43.2},{"place":94,"model":"videotemp-o3-7b","company":"kuaishou","family":"Keye-VL","version":"VideoTemp-o3","score":43},{"place":95,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":42.8},{"place":96,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":42},{"place":97,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":41.8},{"place":98,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":40.4},{"place":99,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":39.2},{"place":100,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":39.2},{"place":101,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":38.3},{"place":102,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.8},{"place":103,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":34.7},{"place":104,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":34.4},{"place":105,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.3},{"place":106,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":33.1},{"place":107,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":30.8},{"place":108,"model":"cogvlm2-video-llama3-chat","company":"zai","family":"CogVLM2","version":"CogVLM2","score":28.1},{"place":109,"model":"pllava-34b","company":"bytedance","family":"PLLaVA","version":"PLLaVA","score":26.1},{"place":110,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":25.4},{"place":111,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":25.31}]},{"id":"lvis-det-f1","name":"LVIS Detection (F1)","topic":"Object detection","description":"LVIS object detection with an MLLM; F1 averaged over IoU 0.5:0.95.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":55.3,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":55.3},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":53.3},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":50.7},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":46.9},{"place":5,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.7},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.9},{"place":7,"model":"groundingdino-t","company":"idea-research","family":"GroundingDINO","version":"GroundingDINO","score":38.8}]},{"id":"lvis-pointing","name":"LVIS Pointing","topic":"Object pointing","description":"LVIS object pointing accuracy.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":79.5,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":79.5},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":78.9},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":76.6},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":70.8},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.7}]},{"id":"m-ifeval-ja","name":"M-IFEval (Japanese)","topic":"Instruction following (Japanese)","description":"Japanese split of M-IFEval multilingual instruction-following benchmark.","url":"https://arxiv.org/abs/2502.04688","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 1.2B JP 202606","top_percent":79.08,"top_model_id":"lfm2.5-1.2b-jp-202606","top_generation":"LFM2.5","top_model_base":"LFM2.5 1.2B JP","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":79.08},{"place":2,"model":"nemotron-nano-9b-v2-japanese","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":63.2},{"place":3,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.9},{"place":4,"model":"lfm2.5-1.2b-jp","company":"liquidai","family":"LFM","version":"LFM2.5","score":58.1},{"place":5,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":41.8},{"place":6,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":40.44},{"place":7,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.3},{"place":8,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.29},{"place":9,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":39.3},{"place":10,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":36.6},{"place":11,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":36.55},{"place":12,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":36.5},{"place":13,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":33.77},{"place":14,"model":"gemma-2-llama-swallow-2b-it-v0.1","company":"tokyotech","family":"Swallow","version":"Gemma-2-Llama Swallow","score":33.4},{"place":15,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":28.06},{"place":16,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":27.56},{"place":17,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":26.31},{"place":18,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":26.3},{"place":19,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":24.1},{"place":20,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":21.9}]},{"id":"m3gia-cn","name":"M3GIA (CN)","topic":"Chinese multimodal QA","description":"Chinese-language M3GIA benchmark covering grounded multimodal question answering.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.5-VL-Thinking","top_percent":91.2,"top_model_id":"seed1.5-vl-thinking","top_generation":"Seed 1.5","top_model_base":"Seed 1.5 VL","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":91.2},{"place":2,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":90.85},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.54},{"place":4,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.24}]},{"id":"machiavelli","name":"Machiavelli","topic":"Deception / safety","description":"Benchmark for deceptive or manipulative behavior in social interactions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Haiku 4.5","top_percent":52.2,"top_model_id":"claude-4.5-haiku","top_generation":"Claude 4.5","top_model_base":"Claude Haiku 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":true,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":52.2},{"place":2,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":52.6},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.3},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.7},{"place":5,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":54.2},{"place":6,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":55.4},{"place":7,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":56.1},{"place":8,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":57.1},{"place":9,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.7},{"place":10,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":57.9},{"place":11,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":58.6},{"place":12,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":62.4},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.8},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.8},{"place":15,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.8}]},{"id":"makemesay","name":"MakeMeSay","topic":"Adversarial robustness","description":"Adversarial benchmark testing model robustness against manipulation attempts. Lower is better.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Grok 4.1 (Thinking)","top_percent":0,"top_model_id":"grok-4.1-thinking","top_generation":"Grok 4.1","top_model_base":"Grok 4.1","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":0},{"place":2,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":13}]},{"id":"mantis","name":"Mantis","topic":"Multimodal reasoning","description":"Multimodal reasoning and instruction following benchmark (Mantis).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"dots.vlm1","top_percent":86.18,"top_model_id":"dots-vlm1","top_generation":"dots.vlm1","top_model_base":"dots.vlm1","top_model_family":"dots","top_company":"rednote","top_open_source":1,"lower_is_better":false,"bench_models":42,"total_models":3854,"placements":[{"place":1,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":86.18},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.33},{"place":3,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":82.3},{"place":4,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":79.7},{"place":5,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":79.26},{"place":6,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":78.8},{"place":7,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":78.3},{"place":8,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":78.3},{"place":9,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":78.3},{"place":10,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":77.6},{"place":11,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":77},{"place":12,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":75.6},{"place":13,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":75.6},{"place":14,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":75.1},{"place":15,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":74.7},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.2},{"place":17,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":73.7},{"place":18,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":72.8},{"place":19,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.8},{"place":20,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":71.4},{"place":21,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":70.5},{"place":22,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":70.1},{"place":23,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":70},{"place":24,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":69.6},{"place":25,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":69.1},{"place":26,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":69},{"place":27,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":67.7},{"place":28,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":66.8},{"place":29,"model":"llava-next-interleave-14b","company":"llava","family":"LLaVA","version":"LLaVA-Next-Interleave","score":66.4},{"place":30,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":65.4},{"place":31,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":62.7},{"place":32,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":62.7},{"place":33,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":62.7},{"place":34,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":61.3},{"place":35,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":59},{"place":36,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":54.8},{"place":37,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":53.1},{"place":38,"model":"vpg-c-7b","company":"zju","family":"VPG-C","version":"VPG-C","score":52.4},{"place":39,"model":"llama-3-vila1.5-8b","company":"nvidia","family":"LLaVA","version":"Llama-3-VILA1.5","score":51.2},{"place":40,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":51.2},{"place":41,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":48.4},{"place":42,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":46.1},{"place":43,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":45.2},{"place":44,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":39.6},{"place":45,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":37.8}]},{"id":"marena-hard","name":"mArenaHard","topic":"Chat ability (multilingual)","description":"Multilingual variant of Arena-Hard evaluating chat quality across languages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-4B","top_percent":70.1,"top_model_id":"qwen3-4b","top_generation":"Qwen3","top_model_base":"Qwen3 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.1},{"place":2,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":67.4},{"place":3,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":65.8},{"place":4,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":63.7}]},{"id":"mars-bench","name":"MARS-Bench","topic":"Instruction following","description":"Instruction-following benchmark with complex tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2 (high)","top_percent":87.9,"top_model_id":"gpt-5.2-high","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":87.9},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.7},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85.6},{"place":4,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":85.6},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":84.6},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80.8},{"place":7,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.5},{"place":8,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":77.2},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.6},{"place":10,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.9},{"place":11,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.5},{"place":12,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":70.1},{"place":13,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":66.1},{"place":14,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":62.4}]},{"id":"mask","name":"MASK","topic":"Safety / red teaming","description":"Model behavior safety assessment via red-teaming scenarios.","url":"https://github.com/centerforaisafety/mask","leaderboard":"https://scale.com/leaderboard/mask","github":"https://github.com/centerforaisafety/mask","paper":"https://arxiv.org/html/2503.03750v1","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":96.28,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":79,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":96.28},{"place":2,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":96.13},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":96.1},{"place":4,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":95.33},{"place":5,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":94.5},{"place":6,"model":"claude-opus-4-1-20250805-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":94.2},{"place":7,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":94.1},{"place":8,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.53},{"place":9,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":92},{"place":10,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":91.73},{"place":11,"model":"gpt-5.4-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":89.67},{"place":12,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":89.27},{"place":13,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":88},{"place":14,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":87.87},{"place":15,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":87.7},{"place":16,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":87.4},{"place":17,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.13},{"place":18,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":87.1},{"place":19,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.67},{"place":20,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":86.46},{"place":21,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":86.4},{"place":22,"model":"gpt-5.1-thinking","company":"openai","family":"GPT","version":"GPT-5.1","score":86.33},{"place":23,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":85.99},{"place":24,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":85.4},{"place":25,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":84.47},{"place":26,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":82.6},{"place":27,"model":"gpt-5-mini-2025-08","company":"openai","family":"GPT","version":"GPT-5","score":82.6},{"place":28,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.6},{"place":29,"model":"o3-pro-high","company":"openai","family":"o3","version":"o3","score":82.5},{"place":30,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":82.13},{"place":31,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":80.28},{"place":32,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":79.33},{"place":33,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":79},{"place":34,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":78.6},{"place":35,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":72.93},{"place":36,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":72.33},{"place":37,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":72.27},{"place":38,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":70.47},{"place":39,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":63.33},{"place":40,"model":"o1-pro","company":"openai","family":"o1","version":"o1","score":61.6},{"place":41,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":61.46},{"place":42,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":61.4},{"place":43,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":61.4},{"place":44,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":60.8},{"place":45,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":60.07},{"place":46,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":59.27},{"place":47,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":58.3},{"place":48,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":57.32},{"place":49,"model":"gpt-4.5-preview","company":"openai","family":"GPT","version":"GPT-4.5","score":56.93},{"place":50,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":56.5},{"place":51,"model":"magistral-medium-2506","company":"mistral","family":"Magistral","version":"Magistral 2506","score":56.5},{"place":52,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.4},{"place":53,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.93},{"place":54,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.7},{"place":55,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.67},{"place":56,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":54.07},{"place":57,"model":"gemini-2.5-pro-preview-05-06","company":"google","family":"Gemini","version":"Gemini 2.5","score":53.07},{"place":58,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":53},{"place":59,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":53},{"place":60,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":51.93},{"place":61,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":51.13},{"place":62,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":50},{"place":63,"model":"o3-mini-2025-01-31-low","company":"openai","family":"o3","version":"o3","score":49.73},{"place":64,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":49.73},{"place":65,"model":"gemini-2.0-flash-thinking-exp-01-21","company":"google","family":"Gemini","version":"Gemini 2.0","score":49.53},{"place":66,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.13},{"place":67,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.1},{"place":68,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":49.07},{"place":69,"model":"o3-mini-2025-01-31-med","company":"openai","family":"o3","version":"o3","score":48.93},{"place":70,"model":"gemini-2.0-pro-exp-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":48.67},{"place":71,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":48.4},{"place":72,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":47.53},{"place":73,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":46.8},{"place":74,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":46.67},{"place":75,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":46.27},{"place":76,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":46},{"place":77,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":44.53},{"place":78,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":42.6},{"place":79,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":42.6},{"place":80,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":42.4},{"place":81,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":42},{"place":82,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":38.3},{"place":83,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":29}]},{"id":"massive-intent","name":"MASSIVE intent","topic":"Intent classification","description":"Amazon MASSIVE intent classification (English).","url":"https://github.com/alexa/massive","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Decider 4B (Mapika)","top_percent":88.3,"top_model_id":"mapika-decider-4b","top_generation":"Decider","top_model_base":"Decider","top_model_family":"Decider","top_company":"mapika","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"mapika-decider-4b","company":"mapika","family":"Decider","version":"Decider","score":88.3},{"place":2,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":87.3},{"place":3,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":86.1},{"place":4,"model":"mapika-decider-2b","company":"mapika","family":"Decider","version":"Decider","score":81.1}]},{"id":"matbench","name":"MatBench","topic":"Materials property prediction","description":"Materials property prediction benchmark for scientific AI models.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-S1-Pro","top_percent":72.8,"top_model_id":"intern-s1-pro","top_generation":"Intern-S1","top_model_base":"Intern-S1-Pro","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":72.8},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":64.9},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":60},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":53.6},{"place":5,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.7}]},{"id":"math","name":"MATH","topic":"Math (competition)","description":"Competition-level mathematics across algebra, geometry, number theory, combinatorics.","url":"https://github.com/hendrycks/math","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2103.03874","metric":"percent","stars":"1185","top_model":"o3 mini","top_percent":97.9,"top_model_id":"o3-mini","top_generation":"o3","top_model_base":"o3 Mini","top_model_family":"o3","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":526,"total_models":3854,"placements":[{"place":1,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":97.9},{"place":2,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":97},{"place":3,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":96.7},{"place":4,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":96.7},{"place":5,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":96.2},{"place":6,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":96.1},{"place":7,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":96.1},{"place":8,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":95.9},{"place":9,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":95.6},{"place":10,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":95.48},{"place":11,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":95.44},{"place":12,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.4},{"place":13,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":95.4},{"place":14,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":95.24},{"place":15,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.2},{"place":16,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.1},{"place":17,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":95.1},{"place":18,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":95.1},{"place":19,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":95.07},{"place":20,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":94.92},{"place":21,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":94.8},{"place":22,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":94.67},{"place":23,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":94.67},{"place":24,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94.6},{"place":25,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":94.6},{"place":26,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":94.5},{"place":27,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":94.4},{"place":28,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":94.4},{"place":29,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":93.8},{"place":30,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":93.4},{"place":31,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.4},{"place":32,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":92.6},{"place":33,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":92.52},{"place":34,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":92.4},{"place":35,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":91.8},{"place":36,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":91.8},{"place":37,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.6},{"place":38,"model":"deepseek-r1-lite-preview","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":91.6},{"place":39,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":91.4},{"place":40,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":90.96},{"place":41,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":90.9},{"place":42,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":90.4},{"place":43,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":90.19},{"place":44,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90},{"place":45,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":89},{"place":46,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":89},{"place":47,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":88.56},{"place":48,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":87.9},{"place":49,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":87.6},{"place":50,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":87.4},{"place":51,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":87.3},{"place":52,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.2},{"place":53,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":87},{"place":54,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":86.65},{"place":55,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":86.6},{"place":56,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":86.5},{"place":57,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":86.26},{"place":58,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":86.2},{"place":59,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":86.2},{"place":60,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":85.9},{"place":61,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.67},{"place":62,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":85.5},{"place":63,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":85.4},{"place":64,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.84},{"place":65,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.7},{"place":66,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.3},{"place":67,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":84.26},{"place":68,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":84},{"place":69,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":83.9},{"place":70,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":83.8},{"place":71,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":83.8},{"place":72,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":83.6},{"place":73,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":83.2},{"place":74,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.1},{"place":75,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.1},{"place":76,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":83},{"place":77,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.88},{"place":78,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.7},{"place":79,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":82.6},{"place":80,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.3},{"place":81,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82},{"place":82,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.1},{"place":83,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":81.1},{"place":84,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81},{"place":85,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.2},{"place":86,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80},{"place":87,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":79.6},{"place":88,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":79.6},{"place":89,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":78.7},{"place":90,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.6},{"place":91,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":78.6},{"place":92,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":78.3},{"place":93,"model":"joyai-llm-flash-base","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":78.16},{"place":94,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":78.1},{"place":95,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":77.92},{"place":96,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":77.9},{"place":97,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":77.4},{"place":98,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":76.6},{"place":99,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":76.6},{"place":100,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.4},{"place":101,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":76.4},{"place":102,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":76.28},{"place":103,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":76},{"place":104,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":75.9},{"place":105,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":75.8},{"place":106,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":75.7},{"place":107,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":75.7},{"place":108,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":75.6},{"place":109,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.5},{"place":110,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":75.2},{"place":111,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.2},{"place":112,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":75.1},{"place":113,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.9},{"place":114,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":74.9},{"place":115,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":74.7},{"place":116,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":74.4},{"place":117,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.3},{"place":118,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":74.2},{"place":119,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":74},{"place":120,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":74},{"place":121,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74},{"place":122,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":73.9},{"place":123,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":73.8},{"place":124,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":73.8},{"place":125,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.7},{"place":126,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":73.62},{"place":127,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":73.5},{"place":128,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":73.5},{"place":129,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":73.4},{"place":130,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":73.3},{"place":131,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":72.9},{"place":132,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":72.86},{"place":133,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":72.5},{"place":134,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":71.84},{"place":135,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":71.8},{"place":136,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.4},{"place":137,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":71.2},{"place":138,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":71.1},{"place":139,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":71.1},{"place":140,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":71},{"place":141,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71},{"place":142,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":71},{"place":143,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.6},{"place":144,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":70.58},{"place":145,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":70.2},{"place":146,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":70.2},{"place":147,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":70.2},{"place":148,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":69.9},{"place":149,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":69.8},{"place":150,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69.6},{"place":151,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":69.42},{"place":152,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":69.4},{"place":153,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":69.3},{"place":154,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":69},{"place":155,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":68.8},{"place":156,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.5},{"place":157,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":68.4},{"place":158,"model":"step-2","company":"stepfun","family":"Step","version":"Step 2","score":68.4},{"place":159,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":68.3},{"place":160,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":68},{"place":161,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":68},{"place":162,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":67.7},{"place":163,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":67.7},{"place":164,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":67.7},{"place":165,"model":"ministral-3-14b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":67.6},{"place":166,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":67.3},{"place":167,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":67.3},{"place":168,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":67.1},{"place":169,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":66.8},{"place":170,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.8},{"place":171,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.8},{"place":172,"model":"qwen2.5-math-72b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":66.8},{"place":173,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":66.7},{"place":174,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":66.7},{"place":175,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.6},{"place":176,"model":"seed1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":66.18},{"place":177,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.9},{"place":178,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":65.7},{"place":179,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":65.7},{"place":180,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":65.3},{"place":181,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":65.1},{"place":182,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":64.8},{"place":183,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":64.7},{"place":184,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.5},{"place":185,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":64.3},{"place":186,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":63.8},{"place":187,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":63.4},{"place":188,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":63.32},{"place":189,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":63.13},{"place":190,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":63},{"place":191,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":62.88},{"place":192,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":62.62},{"place":193,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":62.6},{"place":194,"model":"ministral-3-8b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":62.6},{"place":195,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":62.6},{"place":196,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":62.6},{"place":197,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":62.6},{"place":198,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":62.6},{"place":199,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.58},{"place":200,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":62.58},{"place":201,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.5},{"place":202,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.5},{"place":203,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":62.3},{"place":204,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.1},{"place":205,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.1},{"place":206,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.02},{"place":207,"model":"qwen3-14b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":62},{"place":208,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":61.8},{"place":209,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.62},{"place":210,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":61.6},{"place":211,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":61.6},{"place":212,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":61.6},{"place":213,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":61.3},{"place":214,"model":"llama-4-maverick-17b-128e-base","company":"meta","family":"Llama","version":"Llama 4","score":61.2},{"place":215,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":61.2},{"place":216,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":61.1},{"place":217,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":61},{"place":218,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":61},{"place":219,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":60.6},{"place":220,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60.5},{"place":221,"model":"qwen2-math-72b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":60.5},{"place":222,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60.12},{"place":223,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":60.1},{"place":224,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":60.1},{"place":225,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":60.1},{"place":226,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":60.1},{"place":227,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":59.9},{"place":228,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":59.9},{"place":229,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":59.7},{"place":230,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":231,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.4},{"place":232,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":59.37},{"place":233,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.04},{"place":234,"model":"apertus-v1.5-70b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":59},{"place":235,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":58.5},{"place":236,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.5},{"place":237,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":58.4},{"place":238,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":58.1},{"place":239,"model":"internlm2-math-plus-mixtral8x22b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":58.1},{"place":240,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":57.9},{"place":241,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":57.7},{"place":242,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":57.6},{"place":243,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":57.58},{"place":244,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.4},{"place":245,"model":"apertus-v1.5-8b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":57.3},{"place":246,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":57.2},{"place":247,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":56.8},{"place":248,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":56.6},{"place":249,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":56.5},{"place":250,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":56.4},{"place":251,"model":"hrm-text-1b","company":"sapient","family":"HRM","version":"HRM-Text","score":56.2},{"place":252,"model":"yuan2.0-m32","company":"yuanlab","family":"Yuan","version":"Yuan2.0-M32","score":55.9},{"place":253,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":55.6},{"place":254,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.6},{"place":255,"model":"qwen2.5-math-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":55.4},{"place":256,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.2},{"place":257,"model":"numinamath-7b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":55.2},{"place":258,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":55},{"place":259,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":54.7},{"place":260,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":54.4},{"place":261,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":54.4},{"place":262,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.4},{"place":263,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":54.4},{"place":264,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":54.4},{"place":265,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":53.9},{"place":266,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":53.8},{"place":267,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":53.8},{"place":268,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":53.7},{"place":269,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":53.7},{"place":270,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":53.5},{"place":271,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":53.4},{"place":272,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":53.3},{"place":273,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":53.2},{"place":274,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":53},{"place":275,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":52.9},{"place":276,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":52.9},{"place":277,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":52.9},{"place":278,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":52.9},{"place":279,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":52.8},{"place":280,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":52.7},{"place":281,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":52.4},{"place":282,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":51.9},{"place":283,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":51.9},{"place":284,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":51.7},{"place":285,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":51.5},{"place":286,"model":"abab6.5","company":"minimax","family":"abab","version":"abab6.5","score":51.3},{"place":287,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":51.2},{"place":288,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":51.1},{"place":289,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":51.1},{"place":290,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":51.1},{"place":291,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":51},{"place":292,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":50.9},{"place":293,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":50.6},{"place":294,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":50.6},{"place":295,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":50.4},{"place":296,"model":"qwen2-math-7b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":50.4},{"place":297,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":50.36},{"place":298,"model":"llama-4-scout-17b-16e-base","company":"meta","family":"Llama","version":"Llama 4","score":50.3},{"place":299,"model":"llama-4-scout-17b-base","company":"meta","family":"Llama","version":"Llama 4","score":50.3},{"place":300,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":50.2},{"place":301,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":50.1},{"place":302,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":50.1},{"place":303,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":50},{"place":304,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":49.9},{"place":305,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":49.8},{"place":306,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.8},{"place":307,"model":"qwen2.5-math-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":49.8},{"place":308,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":49.6},{"place":309,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":49.6},{"place":310,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":49.6},{"place":311,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":49.4},{"place":312,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":49.2},{"place":313,"model":"baichuan-3","company":"baichuan","family":"Baichuan","version":"Baichuan 3","score":49.2},{"place":314,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":49.1},{"place":315,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":49},{"place":316,"model":"eurux-8x22b-nca","company":"openbmb","family":"Eurus","version":"Eurux","score":49},{"place":317,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":48.86},{"place":318,"model":"gemma-3-12b-base","company":"google","family":"Gemma","version":"Gemma 3","score":48.7},{"place":319,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":48.6},{"place":320,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":48.5},{"place":321,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":48.5},{"place":322,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":48.3},{"place":323,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.09},{"place":324,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":48},{"place":325,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":48},{"place":326,"model":"internlm2.5-20b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":48},{"place":327,"model":"glm-4-0116","company":"zai","family":"GLM","version":"GLM 4","score":47.9},{"place":328,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":47.7},{"place":329,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":47.7},{"place":330,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":47.68},{"place":331,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":47.4},{"place":332,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":47.2},{"place":333,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":46.9},{"place":334,"model":"deepseek-math-7b-instruct","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":46.8},{"place":335,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":46.6},{"place":336,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":46.6},{"place":337,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":46.4},{"place":338,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":46.02},{"place":339,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":46},{"place":340,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":45.8},{"place":341,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":45.4},{"place":342,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":45.3},{"place":343,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":44.4},{"place":344,"model":"qwen2-math-1.5b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":44.4},{"place":345,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":44.4},{"place":346,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":44.3},{"place":347,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":44.2},{"place":348,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":43.7},{"place":349,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":43.6},{"place":350,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":43.5},{"place":351,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.4},{"place":352,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":43.4},{"place":353,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":43.3},{"place":354,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":43.3},{"place":355,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":43},{"place":356,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":42.7},{"place":357,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.6},{"place":358,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":42.5},{"place":359,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":42.5},{"place":360,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":42.5},{"place":361,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":42.5},{"place":362,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":42.5},{"place":363,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":42.4},{"place":364,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":42.4},{"place":365,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":42.2},{"place":366,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":42},{"place":367,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":42},{"place":368,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":41.9},{"place":369,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":41.9},{"place":370,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":41.8},{"place":371,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":41.8},{"place":372,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":41.8},{"place":373,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":41.8},{"place":374,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":41.74},{"place":375,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":41.7},{"place":376,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":41.7},{"place":377,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":41.6},{"place":378,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":41.6},{"place":379,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":41.4},{"place":380,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":41.4},{"place":381,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":41.2},{"place":382,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":41.1},{"place":383,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":41},{"place":384,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":41},{"place":385,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":40.6},{"place":386,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":40.5},{"place":387,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":40.5},{"place":388,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":40.2},{"place":389,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":40.2},{"place":390,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":40},{"place":391,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":40},{"place":392,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":40},{"place":393,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":39.6},{"place":394,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":39.5},{"place":395,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":39.5},{"place":396,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":39.2},{"place":397,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":39},{"place":398,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":38.1},{"place":399,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":38},{"place":400,"model":"internlm2-math-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":37.7},{"place":401,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":37.7},{"place":402,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.7},{"place":403,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":37.5},{"place":404,"model":"internlm2-math-plus-1.8b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":37},{"place":405,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":36.7},{"place":406,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":36.6},{"place":407,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36.3},{"place":408,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":36.2},{"place":409,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":36.2},{"place":410,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":36.1},{"place":411,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":36.1},{"place":412,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":35.58},{"place":413,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":35.5},{"place":414,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":35.36},{"place":415,"model":"qwen-72b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":35.2},{"place":416,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":35.08},{"place":417,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":35},{"place":418,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":34.9},{"place":419,"model":"inflection-2","company":"inflection","family":"Inflection","version":"Inflection-2","score":34.8},{"place":420,"model":"internlm2-math-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":34.6},{"place":421,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.4},{"place":422,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.2},{"place":423,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":34.1},{"place":424,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":34.1},{"place":425,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":34.1},{"place":426,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":34.1},{"place":427,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":34.1},{"place":428,"model":"internlm2.5-7b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":34},{"place":429,"model":"minerva-540b","company":"google","family":"Minerva","version":"Minerva","score":33.6},{"place":430,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":33.5},{"place":431,"model":"math-shepherd-mistral-7b","company":"pku","family":"Math-Shepherd","version":"Math-Shepherd","score":33},{"place":432,"model":"wizardmath-7b-v1.1","company":"microsoft","family":"WizardMath","version":"WizardMath V1.1","score":33},{"place":433,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":32.66},{"place":434,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":32.6},{"place":435,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":32.6},{"place":436,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":32.6},{"place":437,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":32.4},{"place":438,"model":"skywork-moe-base","company":"skywork","family":"Skywork","version":"Skywork-MoE","score":31.9},{"place":439,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":31.9},{"place":440,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":31.9},{"place":441,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":31.9},{"place":442,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":31.5},{"place":443,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":31.5},{"place":444,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":31.1},{"place":445,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":30.9},{"place":446,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":30.82},{"place":447,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":30.8},{"place":448,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":30.7},{"place":449,"model":"internlm2-math-base-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":30.4},{"place":450,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":30.4},{"place":451,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":30.1},{"place":452,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":30},{"place":453,"model":"metamath-llemma-7b","company":"metamath","family":"MetaMath","version":"MetaMath","score":30},{"place":454,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.8},{"place":455,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":29.8},{"place":456,"model":"bolmo-7b","company":"allenai","family":"Bolmo","version":"Bolmo 7B","score":29.8},{"place":457,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":29.8},{"place":458,"model":"gemma-3-4b-base","company":"google","family":"Gemma","version":"Gemma 3","score":29.4},{"place":459,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":29.28},{"place":460,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":29.2},{"place":461,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":29.1},{"place":462,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":29.1},{"place":463,"model":"yi-coder-9b","company":"01ai","family":"Yi","version":"Yi-Coder","score":29.1},{"place":464,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.6},{"place":465,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":28.42},{"place":466,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":28.4},{"place":467,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":28.4},{"place":468,"model":"gairmath-abel-70b","company":"gair","family":"Abel","version":"GAIRMath-Abel","score":28.3},{"place":469,"model":"metamath-mistral-7b","company":"metamath","family":"MetaMath","version":"MetaMath","score":28.2},{"place":470,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":28},{"place":471,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":27.9},{"place":472,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":27.9},{"place":473,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":27.8},{"place":474,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":27.8},{"place":475,"model":"minerva-62b","company":"google","family":"Minerva","version":"Minerva","score":27.6},{"place":476,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":27.6},{"place":477,"model":"seallm-7b-v2","company":"damo","family":"SeaLLM","version":"SeaLLM v2","score":27.5},{"place":478,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":27.3},{"place":479,"model":"internlm2-math-base-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":27.3},{"place":480,"model":"internlm2.5-1.8b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":27.28},{"place":481,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":27.2},{"place":482,"model":"mobilellm-r1-950m-base","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":26.8},{"place":483,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":26.8},{"place":484,"model":"mobilellm-r1-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":26.6},{"place":485,"model":"metamath-70b","company":"meta-math","family":"MetaMath","version":"MetaMath","score":26.6},{"place":486,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":26.6},{"place":487,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":26},{"place":488,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":25.8},{"place":489,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":25.7},{"place":490,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":25.7},{"place":491,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":25.6},{"place":492,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":25.5},{"place":493,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":25.3},{"place":494,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":25.3},{"place":495,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":25.2},{"place":496,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":25.1},{"place":497,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":25.1},{"place":498,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":25},{"place":499,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":24.8},{"place":500,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":24.8},{"place":501,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":24.8},{"place":502,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":24.7},{"place":503,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":24.38},{"place":504,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":24.35},{"place":505,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":24.3},{"place":506,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":24.3},{"place":507,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":24.2},{"place":508,"model":"math-qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":24.2},{"place":509,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":24.2},{"place":510,"model":"grok-1","company":"xai","family":"Grok","version":"Grok 1","score":23.9},{"place":511,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":23.7},{"place":512,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":23.6},{"place":513,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":23.2},{"place":514,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":23.2},{"place":515,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":23},{"place":516,"model":"wizardmath-70b-v1.0","company":"microsoft","family":"WizardMath","version":"WizardMath V1.0","score":22.7},{"place":517,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":22.7},{"place":518,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":22.5},{"place":519,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":22.4},{"place":520,"model":"metamath-13b","company":"metamath","family":"MetaMath","version":"MetaMath","score":22.4},{"place":521,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":22},{"place":522,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":21.9},{"place":523,"model":"qwen1.5-moe-a2.7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":21.9},{"place":524,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":21.7},{"place":525,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":21.6},{"place":526,"model":"internlm2-math-base-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":21.5},{"place":527,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":21.4},{"place":528,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":21.2},{"place":529,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":21.2},{"place":530,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":21.2},{"place":531,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":21.16},{"place":532,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":20.8},{"place":533,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":20.76},{"place":534,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":20.7},{"place":535,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":20.5},{"place":536,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":20.4},{"place":537,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":20.3},{"place":538,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":20.3},{"place":539,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":20.2},{"place":540,"model":"metamath-7b","company":"metamath","family":"MetaMath","version":"MetaMath","score":19.8},{"place":541,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":19.5},{"place":542,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":19.2},{"place":543,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":19.2},{"place":544,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":19.2},{"place":545,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":19.2},{"place":546,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":19.05},{"place":547,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":19},{"place":548,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":18.7},{"place":549,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":18.7},{"place":550,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":18.6},{"place":551,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":18.4},{"place":552,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":18.3},{"place":553,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":18.1},{"place":554,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":18},{"place":555,"model":"gair-abel-13b","company":"sjtu","family":"Abel","version":"Abel","score":17.34},{"place":556,"model":"evabyte-6.5b","company":"hku","family":"EvaByte","version":"EvaByte 6.5B","score":17.3},{"place":557,"model":"gairmath-abel-13b","company":"gair","family":"Abel","version":"GAIRMath-Abel","score":17.3},{"place":558,"model":"math-qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":17.2},{"place":559,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":17.1},{"place":560,"model":"skywork-13b-math","company":"skywork","family":"Skywork","version":"Skywork","score":16.98},{"place":561,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":16.9},{"place":562,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":16.8},{"place":563,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":16.4},{"place":564,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":16},{"place":565,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":15.9},{"place":566,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":15.8},{"place":567,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":15.74},{"place":568,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":15.5},{"place":569,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":15.5},{"place":570,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":15.4},{"place":571,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":15.3},{"place":572,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":15.2},{"place":573,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":14.8},{"place":574,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":14.7},{"place":575,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":14.6},{"place":576,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":14.6},{"place":577,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":14.4},{"place":578,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":14.4},{"place":579,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":14.4},{"place":580,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":14.3},{"place":581,"model":"minerva-8b","company":"google","family":"Minerva","version":"Minerva","score":14.1},{"place":582,"model":"wizardmath-13b-v1.0","company":"microsoft","family":"WizardMath","version":"WizardMath V1.0","score":14},{"place":583,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":14},{"place":584,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":13.96},{"place":585,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":13.9},{"place":586,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":13.9},{"place":587,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":13.8},{"place":588,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":13.7},{"place":589,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":13.6},{"place":590,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":13.6},{"place":591,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":13.5},{"place":592,"model":"mobilellm-r1-360m-base","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":13.4},{"place":593,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":13.4},{"place":594,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":13.4},{"place":595,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":13.4},{"place":596,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":13.14},{"place":597,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":13.1},{"place":598,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":13.1},{"place":599,"model":"gairmath-abel-7b","company":"gair","family":"Abel","version":"GAIRMath-Abel","score":13},{"place":600,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":12.7},{"place":601,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":12.7},{"place":602,"model":"huginn-3.5b","company":"tomg-umd","family":"Huginn","version":"Huginn","score":12.6},{"place":603,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":12.5},{"place":604,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":12.12},{"place":605,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":12.1},{"place":606,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":12},{"place":607,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":11.8},{"place":608,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":11.8},{"place":609,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":11.6},{"place":610,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":11.6},{"place":611,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":11.6},{"place":612,"model":"yi-coder-1.5b","company":"01ai","family":"Yi","version":"Yi-Coder","score":11.4},{"place":613,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":11.3},{"place":614,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":11.3},{"place":615,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":11.2},{"place":616,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":11},{"place":617,"model":"tfree-hat-pretrained-7b-base","company":"alephalpha","family":"TFree","version":"TFree Hat","score":10.9},{"place":618,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":10.9},{"place":619,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":10.8},{"place":620,"model":"wizardmath-7b-v1.0","company":"microsoft","family":"WizardMath","version":"WizardMath V1.0","score":10.7},{"place":621,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":10.7},{"place":622,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":10.6},{"place":623,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":10.6},{"place":624,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":10.6},{"place":625,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":10.6},{"place":626,"model":"minicpm-moe-8x2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":10.52},{"place":627,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":10.4},{"place":628,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":10.3},{"place":629,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":10.3},{"place":630,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":10.3},{"place":631,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":10.3},{"place":632,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":10.24},{"place":633,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":10.2},{"place":634,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":10.2},{"place":635,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":10.1},{"place":636,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":10.1},{"place":637,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":10.08},{"place":638,"model":"qwen1.5-4b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":10},{"place":639,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":9.86},{"place":640,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":9.8},{"place":641,"model":"codegeex2-6b","company":"zai","family":"CodeGeeX","version":"CodeGeeX2","score":9.7},{"place":642,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":9.5},{"place":643,"model":"internlm2-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":9.42},{"place":644,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":8.9},{"place":645,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":8.6},{"place":646,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":8.6},{"place":647,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":8.6},{"place":648,"model":"codeshell-7b","company":"wisdomshell","family":"CodeShell","version":"CodeShell","score":8.6},{"place":649,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":8.4},{"place":650,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":8.4},{"place":651,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":8.3},{"place":652,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":7.9},{"place":653,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":7.78},{"place":654,"model":"mobilellm-r1-140m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":7.4},{"place":655,"model":"blt-7b","company":"meta","family":"BLT","version":"BLT 7B","score":7.3},{"place":656,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":7.2},{"place":657,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":7.1},{"place":658,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":7.1},{"place":659,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":7},{"place":660,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":6.9},{"place":661,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":6.9},{"place":662,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":6.9},{"place":663,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":6.8},{"place":664,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":6.8},{"place":665,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":6.6},{"place":666,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":6.5},{"place":667,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":6.5},{"place":668,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":6.4},{"place":669,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":6.4},{"place":670,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":6.32},{"place":671,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":6.3},{"place":672,"model":"llama-2-34b","company":"meta","family":"Llama","version":"Llama 2","score":6.24},{"place":673,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":6.2},{"place":674,"model":"llama-2-34b","company":"meta","family":"Llama","version":"Llama 2","score":6.2},{"place":675,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":6.18},{"place":676,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":6.14},{"place":677,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":6},{"place":678,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":6},{"place":679,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":6},{"place":680,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":5.96},{"place":681,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":5.7},{"place":682,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":5.6},{"place":683,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":5.6},{"place":684,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":5.6},{"place":685,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":5.58},{"place":686,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":5.5},{"place":687,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":5.5},{"place":688,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":5.4},{"place":689,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":5.34},{"place":690,"model":"olmo-2-0425-1b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":5.2},{"place":691,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":5.2},{"place":692,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":5.2},{"place":693,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":5.1},{"place":694,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":5},{"place":695,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":5},{"place":696,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":5},{"place":697,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":4.96},{"place":698,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":4.95},{"place":699,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":4.9},{"place":700,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":4.86},{"place":701,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":4.84},{"place":702,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":4.7},{"place":703,"model":"mobilellm-r1-140m-base","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":4.6},{"place":704,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":4.6},{"place":705,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":4.6},{"place":706,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":4.54},{"place":707,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":4.5},{"place":708,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":4.36},{"place":709,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":4.3},{"place":710,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":4.3},{"place":711,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":4.26},{"place":712,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":4.2},{"place":713,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":4.2},{"place":714,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":4.1},{"place":715,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":3.9},{"place":716,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":3.9},{"place":717,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":3.9},{"place":718,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":3.9},{"place":719,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":3.88},{"place":720,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":3.88},{"place":721,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":3.82},{"place":722,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":3.68},{"place":723,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":3.5},{"place":724,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":3.48},{"place":725,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":3.4},{"place":726,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":3.34},{"place":727,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":3.3},{"place":728,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":3.3},{"place":729,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":3.25},{"place":730,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":3.24},{"place":731,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":3.1},{"place":732,"model":"qwen1.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":3.1},{"place":733,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":3.1},{"place":734,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":3.02},{"place":735,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":3},{"place":736,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":3},{"place":737,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":3},{"place":738,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":2.9},{"place":739,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":2.9},{"place":740,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":2.8},{"place":741,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":2.8},{"place":742,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":2.6},{"place":743,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":2.54},{"place":744,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":2.5},{"place":745,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":2.5},{"place":746,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":2.42},{"place":747,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":2.3},{"place":748,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":2.25},{"place":749,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":2.2},{"place":750,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":2.18},{"place":751,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":2.08},{"place":752,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":1.92},{"place":753,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1.8},{"place":754,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":1.8},{"place":755,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":1.8},{"place":756,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":1.68},{"place":757,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":1.6},{"place":758,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":1.6},{"place":759,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":1.56},{"place":760,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":1.53},{"place":761,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":1.5},{"place":762,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":0.74},{"place":763,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":0.7},{"place":764,"model":"gemma-3-pt-1b","company":"google","family":"Gemma","version":"Gemma 3","score":0.6},{"place":765,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":0.6},{"place":766,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":0.4}]},{"id":"math-100-ja","name":"MATH-100 (Japanese)","topic":"Math (Japanese)","description":"100 MATH problems translated to Japanese (Swallow evaluation suite).","url":"https://swallow-llm.github.io/leaderboard/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-OSS 120B (medium)","top_percent":97,"top_model_id":"gpt-oss-120b-medium","top_generation":"GPT-OSS","top_model_base":"GPT-OSS 120B","top_model_family":"GPT-OSS","top_company":"gpt-oss","top_open_source":1,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":97},{"place":2,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":97},{"place":3,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":97},{"place":4,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":97},{"place":5,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":96},{"place":6,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":96},{"place":7,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":96},{"place":8,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":96},{"place":9,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":96},{"place":10,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":96},{"place":11,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":94.9},{"place":12,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":94.9},{"place":13,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":94.9},{"place":14,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":93.9},{"place":15,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":93.9},{"place":16,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":92.9},{"place":17,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":92.9},{"place":18,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":92.9},{"place":19,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":92.9},{"place":20,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":92.9},{"place":21,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":91.9},{"place":22,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":90.9},{"place":23,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":89.9},{"place":24,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":89.9},{"place":25,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":85.9},{"place":26,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":85.9},{"place":27,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":83.8},{"place":28,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":74.7},{"place":29,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":68.7},{"place":30,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":55.6},{"place":31,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":40.4}]},{"id":"math-ko","name":"MATH-Ko","topic":"Math (Korean)","description":"Korean translation of the MATH competition benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-30B-A3B","top_percent":58.2,"top_model_id":"qwen3-30b-a3b","top_generation":"Qwen3","top_model_base":"Qwen3 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.2},{"place":2,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":54.07},{"place":3,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":47.42},{"place":4,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":45.58}]},{"id":"math-lvl5","name":"MATH Level 5","topic":"Math (competition)","description":"Level 5 subset of the MATH benchmark emphasizing the hardest competition-style problems.","url":"https://github.com/hendrycks/math","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"o1 Mini (2024-09-12)","top_percent":89.32,"top_model_id":"o1-mini-2024-09-12","top_generation":"o1","top_model_base":"o1 Mini","top_model_family":"o1","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":51,"total_models":3854,"placements":[{"place":1,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":89.32},{"place":2,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":84.47},{"place":3,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.62},{"place":4,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70},{"place":5,"model":"gemini-1.5-pro-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":68.1},{"place":6,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":62.38},{"place":7,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":60.89},{"place":8,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.19},{"place":9,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.5},{"place":10,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":59.36},{"place":11,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":55.34},{"place":12,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":54.79},{"place":13,"model":"gemini-1.5-flash-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":54.51},{"place":14,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":54.38},{"place":15,"model":"chatgpt-4o-latest-20240903","company":"openai","family":"GPT","version":"GPT-4o","score":53.12},{"place":16,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":52.18},{"place":17,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":52.15},{"place":18,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":51.93},{"place":19,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.87},{"place":20,"model":"llama-3.1-405b-instruct-bf16","company":"meta","family":"Llama","version":"Llama 3.1","score":51.56},{"place":21,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":51.46},{"place":22,"model":"mistral-large-2407","company":"mistral","family":"Mistral","version":"Mistral","score":48.54},{"place":23,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":46.46},{"place":24,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":46.46},{"place":25,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":44.66},{"place":26,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":43.13},{"place":27,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":39.81},{"place":28,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":39.8},{"place":29,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":38.28},{"place":30,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":36.89},{"place":31,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":36.11},{"place":32,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":34.81},{"place":33,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":26.63},{"place":34,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":26.3},{"place":35,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":26.07},{"place":36,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":25.52},{"place":37,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":25.1},{"place":38,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":24.06},{"place":39,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":23.86},{"place":40,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":22.19},{"place":41,"model":"reka-core-20240501","company":"reka","family":"Reka","version":"Reka Core","score":21.91},{"place":42,"model":"athene-70b","company":"nvidia","family":"Athene","version":"Athene V2","score":20.67},{"place":43,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":19.97},{"place":44,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":19.42},{"place":45,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":18.72},{"place":46,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":18.17},{"place":47,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":16.23},{"place":48,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":15.12},{"place":49,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":13.73},{"place":50,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":7.91},{"place":51,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":4.3}]},{"id":"math500","name":"MATH500","topic":"Math reasoning","description":"500-problem slice of the MATH benchmark for challenging math reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-27B","top_percent":99.8,"top_model_id":"qwen3.8-27b","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 27B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":266,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":99.8},{"place":2,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":99.4},{"place":3,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":99.3},{"place":4,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":99.2},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":99},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":98.8},{"place":7,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":98.8},{"place":8,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":98.8},{"place":9,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":98.6},{"place":10,"model":"cogito-671b-v2.1","company":"deepcogito","family":"Cogito","version":"Cogito 671B v2.1","score":98.57},{"place":11,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":98.2},{"place":12,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":98.2},{"place":13,"model":"o3","company":"openai","family":"o3","version":"o3","score":98.1},{"place":14,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":98.1},{"place":15,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":98},{"place":16,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":98},{"place":17,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":98},{"place":18,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":98},{"place":19,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":98},{"place":20,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":98},{"place":21,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":97.8},{"place":22,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":97.8},{"place":23,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":97.6},{"place":24,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":97.6},{"place":25,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":97.4},{"place":26,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":97.4},{"place":27,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":97.4},{"place":28,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":97.4},{"place":29,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":97.3},{"place":30,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":97.2},{"place":31,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":97.2},{"place":32,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":97.2},{"place":33,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":97.2},{"place":34,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":97.2},{"place":35,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":97.13},{"place":36,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":97.1},{"place":37,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":97.1},{"place":38,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":97},{"place":39,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":97},{"place":40,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":97},{"place":41,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":97},{"place":42,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":97},{"place":43,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":97},{"place":44,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":96.8},{"place":45,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":96.8},{"place":46,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":96.8},{"place":47,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":96.8},{"place":48,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":96.8},{"place":49,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":96.8},{"place":50,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":96.8},{"place":51,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":96.73},{"place":52,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":96.7},{"place":53,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":96.7},{"place":54,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":96.6},{"place":55,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":96.6},{"place":56,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":96.5},{"place":57,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":96.4},{"place":58,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":96.4},{"place":59,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":96.4},{"place":60,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":96.4},{"place":61,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":96.4},{"place":62,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":96.4},{"place":63,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":96.4},{"place":64,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":96.32},{"place":65,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":96.3},{"place":66,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":96.2},{"place":67,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":96.2},{"place":68,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":96.2},{"place":69,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":96.2},{"place":70,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":96.04},{"place":71,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":96},{"place":72,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":96},{"place":73,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":96},{"place":74,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":95.8},{"place":75,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":95.8},{"place":76,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":95.7},{"place":77,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":95.66},{"place":78,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":95.6},{"place":79,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":95.6},{"place":80,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":95.6},{"place":81,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":95.4},{"place":82,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":95.4},{"place":83,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":95.4},{"place":84,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":95.4},{"place":85,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":95.2},{"place":86,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":95.1},{"place":87,"model":"llama-4-behemoth","company":"meta","family":"Llama","version":"Llama 4","score":95},{"place":88,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":95},{"place":89,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":95},{"place":90,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":95},{"place":91,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":94.8},{"place":92,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":94.8},{"place":93,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":94.66},{"place":94,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":94.6},{"place":95,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":94.6},{"place":96,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":94.4},{"place":97,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":94.4},{"place":98,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":94.4},{"place":99,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":94.2},{"place":100,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":94.2},{"place":101,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":94.2},{"place":102,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":94.2},{"place":103,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":94.2},{"place":104,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":94},{"place":105,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":94},{"place":106,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":94},{"place":107,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":93.8},{"place":108,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":93.7},{"place":109,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":93.6},{"place":110,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":93.2},{"place":111,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":93.2},{"place":112,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":92.8},{"place":113,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":92.8},{"place":114,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":92.6},{"place":115,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":92.4},{"place":116,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":92.4},{"place":117,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":92.2},{"place":118,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":92.1},{"place":119,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":91.8},{"place":120,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":91.8},{"place":121,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":91.8},{"place":122,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":91.6},{"place":123,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":91.6},{"place":124,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":91.6},{"place":125,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.6},{"place":126,"model":"aquif-3-moe-17b-a2.8b","company":"aquif","family":"Aquif","version":"Aquif 3","score":91.4},{"place":127,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":91.4},{"place":128,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":91.2},{"place":129,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":91.1},{"place":130,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":91},{"place":131,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":91},{"place":132,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":90.9},{"place":133,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":90.85},{"place":134,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":90.8},{"place":135,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":90.8},{"place":136,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":90.6},{"place":137,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":90.2},{"place":138,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":90.2},{"place":139,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":90},{"place":140,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":90},{"place":141,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":90},{"place":142,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.8},{"place":143,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.8},{"place":144,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.8},{"place":145,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.8},{"place":146,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.73},{"place":147,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":89.6},{"place":148,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":89.6},{"place":149,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.6},{"place":150,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.4},{"place":151,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":89.4},{"place":152,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":89},{"place":153,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":88.76},{"place":154,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.6},{"place":155,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":88.47},{"place":156,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":88.3},{"place":157,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":88.3},{"place":158,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.2},{"place":159,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":88.2},{"place":160,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":88},{"place":161,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":87.96},{"place":162,"model":"magistral-small-2509","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":87.4},{"place":163,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":87.4},{"place":164,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":87.3},{"place":165,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.2},{"place":166,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":87.2},{"place":167,"model":"mobilellm-r1.5-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":86.6},{"place":168,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":86.6},{"place":169,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.48},{"place":170,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":86.2},{"place":171,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":86.2},{"place":172,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.8},{"place":173,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.73},{"place":174,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.6},{"place":175,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":85.5},{"place":176,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.4},{"place":177,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":85},{"place":178,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":84.8},{"place":179,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":84.8},{"place":180,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.8},{"place":181,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.6},{"place":182,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.4},{"place":183,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":84},{"place":184,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":83.8},{"place":185,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.8},{"place":186,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.6},{"place":187,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":83.4},{"place":188,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":83.2},{"place":189,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":83.2},{"place":190,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":83.2},{"place":191,"model":"deepseek-v2.5-1210","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":82.8},{"place":192,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.6},{"place":193,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":82.4},{"place":194,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.2},{"place":195,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":82},{"place":196,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":81.92},{"place":197,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.9},{"place":198,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.8},{"place":199,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":81.56},{"place":200,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":81.47},{"place":201,"model":"phi-4-14b","company":"microsoft","family":"Phi","version":"Phi 4","score":80.8},{"place":202,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":80.8},{"place":203,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.76},{"place":204,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.7},{"place":205,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":80.6},{"place":206,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80},{"place":207,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":79.7},{"place":208,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":79.6},{"place":209,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":79.6},{"place":210,"model":"lfm2-350m-math","company":"liquidai","family":"LFM","version":"LFM2","score":79.4},{"place":211,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":79},{"place":212,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.63},{"place":213,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":78.3},{"place":214,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":78.3},{"place":215,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":77.8},{"place":216,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":77.8},{"place":217,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.2},{"place":218,"model":"joyai-llm-flash-base","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":77},{"place":219,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":77},{"place":220,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":76.6},{"place":221,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":76.4},{"place":222,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.8},{"place":223,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":75.2},{"place":224,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":75},{"place":225,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":74.8},{"place":226,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":74.8},{"place":227,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":74.7},{"place":228,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":74.6},{"place":229,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":74.6},{"place":230,"model":"qwen3-6b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.5},{"place":231,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":74.2},{"place":232,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":74.2},{"place":233,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":74},{"place":234,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":74},{"place":235,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":74},{"place":236,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":73.8},{"place":237,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":73.6},{"place":238,"model":"apertus-v1.5-70b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":73.6},{"place":239,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":73.4},{"place":240,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":73.2},{"place":241,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":73},{"place":242,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":73},{"place":243,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.6},{"place":244,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":72},{"place":245,"model":"apertus-v1.5-8b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":71.4},{"place":246,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70.8},{"place":247,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":70.6},{"place":248,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":249,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":70},{"place":250,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":69.4},{"place":251,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":69.02},{"place":252,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":69},{"place":253,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":68.6},{"place":254,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":68.6},{"place":255,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":68.4},{"place":256,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.8},{"place":257,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":65.6},{"place":258,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":65.2},{"place":259,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65},{"place":260,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":64.2},{"place":261,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64},{"place":262,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":64},{"place":263,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":63.6},{"place":264,"model":"mobilellm-r1.5-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":63.4},{"place":265,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":63.2},{"place":266,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":62.8},{"place":267,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":62.7},{"place":268,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.3},{"place":269,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":61.8},{"place":270,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":61.4},{"place":271,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":61.2},{"place":272,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":61.2},{"place":273,"model":"mobilellm-r1-950m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":60.7},{"place":274,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":60.6},{"place":275,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":60.2},{"place":276,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.6},{"place":277,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":59.2},{"place":278,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":58.4},{"place":279,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":58.2},{"place":280,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":58.09},{"place":281,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":58},{"place":282,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":58},{"place":283,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":56.3},{"place":284,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.2},{"place":285,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":54.47},{"place":286,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":54.2},{"place":287,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54},{"place":288,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":52.9},{"place":289,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":52.8},{"place":290,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":51.8},{"place":291,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":51.2},{"place":292,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":50.47},{"place":293,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":50.4},{"place":294,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.6},{"place":295,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":48.73},{"place":296,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.4},{"place":297,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":48.2},{"place":298,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":47.6},{"place":299,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":47.2},{"place":300,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":46.1},{"place":301,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":46},{"place":302,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":45.8},{"place":303,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":45.4},{"place":304,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":45.2},{"place":305,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":45.2},{"place":306,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":44.8},{"place":307,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":43.2},{"place":308,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.6},{"place":309,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":42.27},{"place":310,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":42.2},{"place":311,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":42},{"place":312,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":41.2},{"place":313,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":41.2},{"place":314,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":41},{"place":315,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":40.8},{"place":316,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":39.4},{"place":317,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":38},{"place":318,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":36},{"place":319,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":35.54},{"place":320,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":35.4},{"place":321,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":35.07},{"place":322,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":34.4},{"place":323,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":33.6},{"place":324,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":31.2},{"place":325,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31},{"place":326,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.4},{"place":327,"model":"mobilellm-r1-360m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":28.4},{"place":328,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27.8},{"place":329,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":26.8},{"place":330,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.8},{"place":331,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":24.8},{"place":332,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":23.4},{"place":333,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":19.8},{"place":334,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":19.6},{"place":335,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":19.6},{"place":336,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":19.2},{"place":337,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":19.2},{"place":338,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":18.8},{"place":339,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":17.6},{"place":340,"model":"mobilellm-r1.5-140m","company":"meta","family":"MobileLLM","version":"MobileLLM R1.5","score":16},{"place":341,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":15.4},{"place":342,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":13.2},{"place":343,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":10.2},{"place":344,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":8.8},{"place":345,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":8.4},{"place":346,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":7.4},{"place":347,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":7.2},{"place":348,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":6.8},{"place":349,"model":"mobilellm-r1-140m","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":6.2},{"place":350,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":3.8},{"place":351,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":3.4},{"place":352,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":3}]},{"id":"math500-es","name":"MATH500 (ES)","topic":"Math (multilingual)","description":"Spanish MATH500 benchmark","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"EXAONE 4.0 1.2B","top_percent":88.8,"top_model_id":"exaone-4.0-1.2b","top_generation":"EXAONE 4.0","top_model_base":"EXAONE 4.0 1.2B","top_model_family":"EXAONE","top_company":"lg","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":88.8},{"place":2,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.9},{"place":3,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":87.5},{"place":4,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":84.5},{"place":5,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.6}]},{"id":"math500-ja","name":"MATH500 (Japanese)","topic":"Math (Japanese)","description":"Japanese translation of MATH500.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 1.2B JP 202606","top_percent":62.8,"top_model_id":"lfm2.5-1.2b-jp-202606","top_generation":"LFM2.5","top_model_base":"LFM2.5 1.2B JP","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":62.8},{"place":2,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.4},{"place":3,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":50},{"place":4,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":25.4},{"place":5,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":24.8},{"place":6,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":22.4},{"place":7,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":17},{"place":8,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":15.6},{"place":9,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":11.4},{"place":10,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":11.4}]},{"id":"matharena-apex","name":"MathArena Apex","topic":"Challenging Math Contest problems","description":"Challenging math contest problems from MathArena Apex benchmark.","url":"","leaderboard":"https://matharena.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":91.4,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":51,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":91.4},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":90},{"place":3,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":89.6},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":85.4},{"place":5,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":82.1},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":81},{"place":7,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":80.1},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":80},{"place":9,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":74.2},{"place":10,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":72.8},{"place":11,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":71.9},{"place":12,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":71.4},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69.8},{"place":14,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":68.4},{"place":15,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":66.3},{"place":16,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":66},{"place":17,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":65.6},{"place":18,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":65.6},{"place":19,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":65.3},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":61},{"place":21,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":60.9},{"place":22,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":58.9},{"place":23,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":58.6},{"place":24,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":54.1},{"place":25,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":52.6},{"place":26,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.4},{"place":27,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":45.8},{"place":28,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":44.5},{"place":29,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":43.4},{"place":30,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":38.7},{"place":31,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.3},{"place":32,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":36.5},{"place":33,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":35.4},{"place":34,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":34.5},{"place":35,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":33},{"place":36,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":31.3},{"place":37,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":31.1},{"place":38,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":28.1},{"place":39,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":28},{"place":40,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":27.4},{"place":41,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":26},{"place":42,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":24},{"place":43,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":23.4},{"place":44,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":22.7},{"place":45,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":20.8},{"place":46,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":19.1},{"place":47,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":17.7},{"place":48,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":16.8},{"place":49,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.5},{"place":50,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":12.6},{"place":51,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":11.5},{"place":52,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":10.4},{"place":53,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":9.4},{"place":54,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":8.8},{"place":55,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.1},{"place":56,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":2.1},{"place":57,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1.6},{"place":58,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":1},{"place":59,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1},{"place":60,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":1},{"place":61,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":1},{"place":62,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":1},{"place":63,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":0.5},{"place":64,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":0.4}]},{"id":"matharena-apex-shortlist","name":"MathArena Apex Shortlist","topic":"Mathematics","description":"Shortlist of candidate hard competition problems considered for MathArena Apex.","url":"https://matharena.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Flash-Next","top_percent":91.8,"top_model_id":"qwen3.8-flash-next","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Flash Next","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":27,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.8},{"place":2,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.2},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89.1},{"place":4,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.7},{"place":5,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":88.6},{"place":6,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":88.36},{"place":7,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":85.9},{"place":9,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.8},{"place":10,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.8},{"place":11,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.7},{"place":12,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.5},{"place":13,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.4},{"place":14,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":78.1},{"place":15,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":77.4},{"place":16,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":77.1},{"place":17,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":75.5},{"place":18,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":75.5},{"place":19,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75},{"place":20,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.9},{"place":21,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":72.6},{"place":22,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":72.4},{"place":23,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72.1},{"place":24,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":72.1},{"place":25,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":71.5},{"place":26,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":71.1},{"place":27,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.4},{"place":28,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.2},{"place":29,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.7},{"place":30,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":50.8},{"place":31,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":45.5},{"place":32,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":44.5},{"place":33,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":32.2},{"place":34,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":30.3},{"place":35,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":28.9},{"place":36,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":16.9},{"place":37,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":9.3},{"place":38,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":9.2},{"place":39,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":6.1}]},{"id":"mathbench-a","name":"MathBench-A","topic":"Math (multi-level)","description":"MathBench application split covering arithmetic, primary, middle, high school and college levels (overall score).","url":"","leaderboard":"","github":"https://github.com/open-compass/MathBench","paper":"https://arxiv.org/abs/2405.12209","metric":"percent","stars":"","top_model":"GPT-4o-2024-05-13","top_percent":70.9,"top_model_id":"gpt-4o-2024-05-13","top_generation":"GPT-4o","top_model_base":"GPT-4o","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":70.9},{"place":2,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":63},{"place":3,"model":"internlm2-math-plus-mixtral8x22b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":62},{"place":4,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":59.9},{"place":5,"model":"qwen-max-0428","company":"qwen","family":"Qwen","version":"Qwen","score":59.2},{"place":6,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":58.4},{"place":7,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":56.5},{"place":8,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":55.5},{"place":9,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":50.9},{"place":10,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":50.3},{"place":11,"model":"internlm2-math-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":42},{"place":12,"model":"internlm2-math-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":37.7},{"place":13,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":36.7},{"place":14,"model":"internlm2-math-plus-1.8b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":27.1}]},{"id":"mathbench-zh","name":"MathBench (ZH)","topic":"Math (Chinese)","description":"Chinese portion of MathBench as reported in the InternLM-Math paper.","url":"","leaderboard":"","github":"https://github.com/open-compass/MathBench","paper":"https://arxiv.org/abs/2405.12209","metric":"percent","stars":"","top_model":"Qwen-72B-Chat","top_percent":47.8,"top_model_id":"qwen-72b-chat","top_generation":"Qwen","top_model_base":"Qwen 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"qwen-72b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":47.8},{"place":2,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":47.2},{"place":3,"model":"internlm2-math-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":45.3},{"place":4,"model":"internlm2-math-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":40},{"place":5,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":37.8},{"place":6,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":33.2},{"place":7,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":29.2},{"place":8,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":25},{"place":9,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":21.5},{"place":10,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":15.2},{"place":11,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":12.7}]},{"id":"matholympiadbench","name":"MathOlympiadBench","topic":"Formal theorem proving","description":"Olympiad-level math problems formalized in Lean 4; score = share of theorems proved (Pass@32 in LongCat-Flash-Prover report).","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2603.21065","metric":"percent","stars":"","top_model":"LongCat-Flash-Prover","top_percent":35.8,"top_model_id":"longcat-flash-prover","top_generation":"LongCat-Flash","top_model_base":"LongCat-Flash-Prover","top_model_family":"LongCat","top_company":"meituan","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":35.8},{"place":2,"model":"goedel-prover-v2-32b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":16.7},{"place":3,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":14.7},{"place":4,"model":"deepseek-prover-v2-671b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":13.9},{"place":5,"model":"kimina-prover-72b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":13.1},{"place":6,"model":"deepseek-prover-v2-7b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":11.1},{"place":7,"model":"goedel-prover-v2-8b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":11.1},{"place":8,"model":"kimina-prover-8b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":8.6},{"place":9,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":7.5},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":3.9}]},{"id":"mathverse","name":"MathVerse","topic":"Math reasoning (multimodal)","description":"Visual math reasoning benchmark combining images and text across diverse mathematical tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":91.62,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.62},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.27},{"place":3,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":85.13},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":84.19},{"place":5,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.96},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.9},{"place":7,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":80.5},{"place":8,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":79.9},{"place":9,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.6},{"place":10,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":78.8},{"place":11,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":76},{"place":12,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.1},{"place":13,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":55.8},{"place":14,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.1},{"place":15,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":50.8},{"place":16,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":39.6},{"place":17,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":35.9},{"place":18,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":27},{"place":19,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":22.5},{"place":20,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":21.5}]},{"id":"mathverse-mini","name":"MathVerse-mini","topic":"Math reasoning (multimodal)","description":"Compact MathVerse split focusing on single-image math puzzles and visual reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniCPM-V 4.7 35B-A3B","top_percent":86.45,"top_model_id":"minicpm-v-4.7-35b-a3b","top_generation":"MiniCPM V 4.7","top_model_base":"MiniCPM-V 4.7 35B A3B","top_model_family":"MiniCPM","top_company":"openbmb","top_open_source":1,"lower_is_better":false,"bench_models":69,"total_models":3854,"placements":[{"place":1,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":86.45},{"place":2,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85},{"place":3,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.37},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.14},{"place":5,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":84.1},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.9},{"place":7,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":82.74},{"place":8,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.88},{"place":9,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.2},{"place":10,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.8},{"place":11,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":76.4},{"place":12,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.58},{"place":13,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":74.6},{"place":14,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.3},{"place":15,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":72.1},{"place":16,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":70.6},{"place":17,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.75},{"place":18,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":65.9},{"place":19,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.9},{"place":20,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.2},{"place":21,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.1},{"place":22,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":61},{"place":23,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":60.41},{"place":24,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60},{"place":25,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":58.3},{"place":26,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":57.6},{"place":27,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.4},{"place":28,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":56.5},{"place":29,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":56.1},{"place":30,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.55},{"place":31,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.1},{"place":32,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":51.7},{"place":33,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":50.2},{"place":34,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":49.4},{"place":35,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.2},{"place":36,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":48.83},{"place":37,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.1},{"place":38,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47.6},{"place":39,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47},{"place":40,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.8},{"place":41,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":45.8},{"place":42,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":44.9},{"place":43,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":42.8},{"place":44,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":41.7},{"place":45,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":40.56},{"place":46,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":40.1},{"place":47,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":39.5},{"place":48,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":39.1},{"place":49,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":37.1},{"place":50,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":37},{"place":51,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":36.5},{"place":52,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":36.3},{"place":53,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":36.02},{"place":54,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":34.77},{"place":55,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":32.8},{"place":56,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":32.4},{"place":57,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":32},{"place":58,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":31.9},{"place":59,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":31.1},{"place":60,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":30.6},{"place":61,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.8},{"place":62,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":28.4},{"place":63,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":28},{"place":64,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":27},{"place":65,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":26.3},{"place":66,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":26.2},{"place":67,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":26},{"place":68,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":25.7},{"place":69,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":25.3},{"place":70,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":24.1},{"place":71,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":21},{"place":72,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":20.1},{"place":73,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":18.4},{"place":74,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":17.9}]},{"id":"mathverse-vision","name":"MathVerse-Vision","topic":"Math reasoning (multimodal)","description":"Multi-image visual mathematical reasoning tasks from the MathVerse ecosystem.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":89.7,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":89.7},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":89.2},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.7},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.6},{"place":5,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":84.1},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.9},{"place":7,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":81},{"place":8,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":77.4},{"place":9,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":75.51},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.09},{"place":11,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":72.8},{"place":12,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":72.1},{"place":13,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":68.4},{"place":14,"model":"r-4b-base","company":"tencent","family":"R","version":"R","score":64.9},{"place":15,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":62.7},{"place":16,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":61.7},{"place":17,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":54.6},{"place":18,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":49.62},{"place":19,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":41.2},{"place":20,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":40.8},{"place":21,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":34},{"place":22,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":32.4}]},{"id":"mathvision","name":"MathVision","topic":"Math reasoning (multimodal)","description":"Visual math reasoning benchmark with problems that combine images (charts, diagrams) and text.","url":"https://mathllm.github.io/mathvision","leaderboard":"https://mathllm.github.io/mathvision/#leaderboard","github":"https://github.com/mathllm/MATH-V","paper":"https://proceedings.neurips.cc/paper_files/paper/2024/file/ad0edc7d5fa1a783f063646968b7315b-Paper-Datasets_and_Benchmarks_Track.pdf","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":98.6,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":246,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":98.6},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":97.8},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":97.7},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":97.1},{"place":5,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":96.2},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":95.8},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":95.7},{"place":8,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":95.7},{"place":9,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":94.8},{"place":10,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.6},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":94.3},{"place":12,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":93.1},{"place":13,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":92.6},{"place":14,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":92.2},{"place":15,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":92},{"place":16,"model":"gpt-5.4-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":92},{"place":17,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":91.6},{"place":18,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":91},{"place":19,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":90.6},{"place":20,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":90.6},{"place":21,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":90.3},{"place":22,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":90.1},{"place":23,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":89.9},{"place":24,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89.8},{"place":25,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":89.8},{"place":26,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89.7},{"place":27,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":89.5},{"place":28,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89.2},{"place":29,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":89},{"place":30,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":88.8},{"place":31,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":88.7},{"place":32,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.6},{"place":33,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":88.4},{"place":34,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":88},{"place":35,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":87.7},{"place":36,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":87.5},{"place":37,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":87.5},{"place":38,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.4},{"place":39,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":87.4},{"place":40,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":87.4},{"place":41,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.27},{"place":42,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":86.7},{"place":43,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.6},{"place":44,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":86.4},{"place":45,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.2},{"place":46,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.1},{"place":47,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86},{"place":48,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.6},{"place":49,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.1},{"place":50,"model":"ling-3.0-flash-vl","company":"antgroup","family":"Ling","version":"Ling 3.0","score":84.87},{"place":51,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.2},{"place":52,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.2},{"place":53,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.9},{"place":54,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":83.36},{"place":55,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.3},{"place":56,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":83.1},{"place":57,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":83},{"place":58,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":83},{"place":59,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":82.5},{"place":60,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.4},{"place":61,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":81.8},{"place":62,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":81.3},{"place":63,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.59},{"place":64,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.7},{"place":65,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":79.24},{"place":66,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.9},{"place":67,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":78.8},{"place":68,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":78.22},{"place":69,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":78.16},{"place":70,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":78.06},{"place":71,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.2},{"place":72,"model":"seed1.6-thinking","company":"bytedance","family":"Seed","version":"Seed 1.6","score":77.2},{"place":73,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.1},{"place":74,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.1},{"place":75,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":75.95},{"place":76,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":75.2},{"place":77,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75.03},{"place":78,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.6},{"place":79,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.6},{"place":80,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.6},{"place":81,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":74.34},{"place":82,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74.3},{"place":83,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":74.24},{"place":84,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.24},{"place":85,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":73.6},{"place":86,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.3},{"place":87,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":73},{"place":88,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":72.43},{"place":89,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.34},{"place":90,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.1},{"place":91,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":72},{"place":92,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":71.91},{"place":93,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":71.9},{"place":94,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":71.9},{"place":95,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.84},{"place":96,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.4},{"place":97,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":71.2},{"place":98,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":71.2},{"place":99,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.1},{"place":100,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":70.9},{"place":101,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":70.81},{"place":102,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":70.81},{"place":103,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.72},{"place":104,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":70.5},{"place":105,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.43},{"place":106,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.43},{"place":107,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.2},{"place":108,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":69.64},{"place":109,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":69.34},{"place":110,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.28},{"place":111,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":69.14},{"place":112,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":68.77},{"place":113,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":68.72},{"place":114,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":68.7},{"place":115,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":68.7},{"place":116,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":68},{"place":117,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":67.1},{"place":118,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":66},{"place":119,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66},{"place":120,"model":"claude-4.1-opus-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":66},{"place":121,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.79},{"place":122,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.7},{"place":123,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":65.6},{"place":124,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":65.59},{"place":125,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":65.5},{"place":126,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":65.4},{"place":127,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":64.8},{"place":128,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":64.7},{"place":129,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":64.7},{"place":130,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":64.3},{"place":131,"model":"internvl3.5-241b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":63.9},{"place":132,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":63.5},{"place":133,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.4},{"place":134,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":62.3},{"place":135,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":62.2},{"place":136,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":61.9},{"place":137,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.9},{"place":138,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":60.85},{"place":139,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":60.4},{"place":140,"model":"o1","company":"openai","family":"o1","version":"o1","score":60.3},{"place":141,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.2},{"place":142,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":59.65},{"place":143,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.6},{"place":144,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":59.53},{"place":145,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":59.5},{"place":146,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.21},{"place":147,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":58.6},{"place":148,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":58},{"place":149,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":57.9},{"place":150,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":56.9},{"place":151,"model":"step-r1-v-mini","company":"stepfun","family":"Step","version":"Step R1","score":56.6},{"place":152,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":56.3},{"place":153,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":55.7},{"place":154,"model":"internvl3.5-30b-a3b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":55.7},{"place":155,"model":"sensenova-v6-reasoner","company":"sensetime","family":"SenseNova","version":"SenseNova V6","score":55.39},{"place":156,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":54.4},{"place":157,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":54.4},{"place":158,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":54.4},{"place":159,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":54.05},{"place":160,"model":"internvl3.5-38b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":54},{"place":161,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.9},{"place":162,"model":"ovis2.5-9b","company":"alibaba","family":"Ovis","version":"Ovis2.5","score":53.9},{"place":163,"model":"kimi-k1.6-preview","company":"moonshotai","family":"Kimi","version":"Kimi k1.6","score":53.29},{"place":164,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.9},{"place":165,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":52.7},{"place":166,"model":"skywork-r1v3-38b","company":"skywork","family":"Skywork","version":"Skywork R1V3","score":52.6},{"place":167,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.4},{"place":168,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.1},{"place":169,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":52.05},{"place":170,"model":"open-vision-reasoner-7b","company":"stepfun","family":"Open-Vision-Reasoner","version":"Open-Vision-Reasoner","score":51.8},{"place":171,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.6},{"place":172,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.4},{"place":173,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":50.99},{"place":174,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":50.32},{"place":175,"model":"qianfan-vl-70b","company":"baidu","family":"Qianfan-VL","version":"Qianfan-VL","score":50.29},{"place":176,"model":"skywork-r1v2-38b","company":"skywork","family":"Skywork","version":"Skywork-R1V2","score":49.7},{"place":177,"model":"doubao-1.5-vision-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":48.62},{"place":178,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":48.35},{"place":179,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":48.1},{"place":180,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":47.3},{"place":181,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":46.6},{"place":182,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":46},{"place":183,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":46},{"place":184,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":45.8},{"place":185,"model":"vl-rethinker-72b","company":"tiger-lab","family":"VL-Rethinker","version":"VL-Rethinker","score":44.93},{"place":186,"model":"llava-critic-r1-7b","company":"lmms-lab","family":"LLaVA","version":"LLaVA-Critic-R1","score":44.1},{"place":187,"model":"vision-r1-7b","company":"ecnu","family":"Vision","version":"Vision-R1","score":43.9},{"place":188,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":43.1},{"place":189,"model":"skywork-r1v2-38b-awq","company":"skywork","family":"Skywork","version":"Skywork-R1V2","score":42.9},{"place":190,"model":"infrl-qwen2.5-vl-72b-preview","company":"unknown","family":"INFRL","version":"INFRL-Qwen2.5-VL","score":42.73},{"place":191,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":41.3},{"place":192,"model":"vl-rethinker-32b","company":"tiger-lab","family":"VL-Rethinker","version":"VL-Rethinker","score":40.5},{"place":193,"model":"vicrit-rl-72b","company":"microsoft","family":"ViCrit","version":"ViCrit-RL","score":40.1},{"place":194,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":40},{"place":195,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":39.8},{"place":196,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":39.4},{"place":197,"model":"kimi-k1.5","company":"moonshotai","family":"Kimi","version":"Kimi k1.5","score":38.6},{"place":198,"model":"virgo-72b","company":"ruc","family":"Virgo","version":"Virgo","score":38.4},{"place":199,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":38.1},{"place":200,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":37.99},{"place":201,"model":"ovis2.5-2b","company":"alibaba","family":"Ovis","version":"Ovis2.5","score":37.4},{"place":202,"model":"avar-thinker-7b","company":"alibaba","family":"AVAR","version":"AVAR-Thinker","score":37.4},{"place":203,"model":"internvl3-14b","company":"opengvlab","family":"Intern","version":"InternVL3","score":37},{"place":204,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":36.8},{"place":205,"model":"qvq-72b","company":"qwen","family":"QvQ","version":"QvQ 72B","score":35.9},{"place":206,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":35.6},{"place":207,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":35.52},{"place":208,"model":"internvl3-38b","company":"opengvlab","family":"Intern","version":"InternVL3","score":34.5},{"place":209,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":33.2},{"place":210,"model":"thinklite-vl-7b","company":"microsoft","family":"ThinkLite","version":"ThinkLite-VL","score":32.9},{"place":211,"model":"qianfan-vl-8b","company":"baidu","family":"Qianfan-VL","version":"Qianfan-VL","score":32.82},{"place":212,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":32.2},{"place":213,"model":"ovis2-34b","company":"alibaba","family":"Ovis","version":"Ovis2","score":31.9},{"place":214,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":31.8},{"place":215,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":31.64},{"place":216,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":31.64},{"place":217,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":31.6},{"place":218,"model":"ursa-8b-ps-grpo","company":"tsinghua","family":"URSA","version":"URSA","score":31.5},{"place":219,"model":"tbac-vlr1-7b","company":"tencent","family":"TBAC","version":"TBAC-VLR1","score":31.4},{"place":220,"model":"llava-critic-r1-11b","company":"lmms-lab","family":"LLaVA","version":"LLaVA-Critic-R1","score":30.9},{"place":221,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":30.6},{"place":222,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":30.4},{"place":223,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":30.4},{"place":224,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":30.39},{"place":225,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":30.26},{"place":226,"model":"mmr1-math-v0-7b","company":"alibaba","family":"MMR1","version":"MMR1-Math-v0","score":30.2},{"place":227,"model":"dualmindvlm-7b","company":"hkbu","family":"DualMindVLM","version":"DualMindVLM","score":30.2},{"place":228,"model":"ovis2-16b","company":"alibaba","family":"Ovis","version":"Ovis2","score":30.1},{"place":229,"model":"r1-onevision-7b","company":"zju","family":"R1-Onevision","version":"R1-Onevision","score":29.9},{"place":230,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":29},{"place":231,"model":"vold-3b","company":"microsoft","family":"VOLD (Qwen2.5","version":"VOLD","score":28},{"place":232,"model":"internvl3-9b","company":"opengvlab","family":"Intern","version":"InternVL3","score":27.6},{"place":233,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":27.13},{"place":234,"model":"qwen2.5-vl-dp-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-VL-DP","score":26.9},{"place":235,"model":"mm-eureka-qwen-7b","company":"opengvlab","family":"MM-Eureka","version":"MM-Eureka-Qwen","score":26.9},{"place":236,"model":"vision-sr1-7b","company":"tencent","family":"Vision","version":"Vision-SR1","score":26.7},{"place":237,"model":"mathglm-vision-32b","company":"zai","family":"GLM","version":"MathGLM-Vision","score":26.5},{"place":238,"model":"vlaa-thinker-qwen2.5vl-7b","company":"ucsc","family":"VLAA-Thinker","version":"VLAA-Thinker-Qwen2.5VL","score":26.4},{"place":239,"model":"mathcoder-vl-8b","company":"mathllm","family":"MathCoder","version":"MathCoder-VL","score":26.1},{"place":240,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":25.9},{"place":241,"model":"openvlthinker-7b","company":"ucla","family":"OpenVLThinker","version":"OpenVLThinker","score":25.9},{"place":242,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":25.9},{"place":243,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":25.3},{"place":244,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":25.1},{"place":245,"model":"tbac-vlr1-3b-preview","company":"tencent","family":"TBAC","version":"TBAC-VLR1","score":25},{"place":246,"model":"r1-vl-7b","company":"ntu","family":"R1","version":"R1-VL","score":24.7},{"place":247,"model":"x-reasoner-3b","company":"microsoft","family":"X","version":"X-Reasoner","score":24.4},{"place":248,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":24},{"place":249,"model":"r1-onevision-3b","company":"zju","family":"R1-Onevision","version":"R1-Onevision","score":23.6},{"place":250,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":23.6},{"place":251,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":23.4},{"place":252,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":23.1},{"place":253,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":22.76},{"place":254,"model":"mathcoder-vl-2b","company":"mathllm","family":"MathCoder","version":"MathCoder-VL","score":21.7},{"place":255,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":21.7},{"place":256,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":21.7},{"place":257,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":21.4},{"place":258,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":21.2},{"place":259,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":20.9},{"place":260,"model":"multimath-7b","company":"pku","family":"Multimath","version":"Multimath","score":20.7},{"place":261,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.33},{"place":262,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":19.7},{"place":263,"model":"mulberry-qwen2vl-7b","company":"tsinghua","family":"Mulberry","version":"Mulberry-Qwen2VL","score":19.5},{"place":264,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":19.24},{"place":265,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":19.2},{"place":266,"model":"internvl3-1b","company":"opengvlab","family":"Intern","version":"InternVL3","score":18.8},{"place":267,"model":"ovis1.6-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":18.8},{"place":268,"model":"ovis1.6-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":18.78},{"place":269,"model":"mavis-7b","company":"cuhk","family":"MAVIS","version":"MAVIS","score":18.6},{"place":270,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":18.4},{"place":271,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":18.4},{"place":272,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":17.9},{"place":273,"model":"qwen2-vl-dp-7b","company":"qwen","family":"Qwen","version":"Qwen2-VL-DP","score":17.7},{"place":274,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":17.66},{"place":275,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":17.5},{"place":276,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":17.4},{"place":277,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":17.17},{"place":278,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":17},{"place":279,"model":"internvl-chat-v1.2-plus","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2-Plus","score":16.97},{"place":280,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":16.9},{"place":281,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":16.5},{"place":282,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":16.3},{"place":283,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":16.3},{"place":284,"model":"math-llava-13b","company":"sutd","family":"Math","version":"Math-LLaVA","score":15.69},{"place":285,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":15.59},{"place":286,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":15.5},{"place":287,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":15},{"place":288,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":14.7},{"place":289,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":14.54},{"place":290,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":14.4},{"place":291,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":13.2},{"place":292,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":12.4},{"place":293,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":12.4},{"place":294,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":12.1},{"place":295,"model":"sharegpt4v-13b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":11.88},{"place":296,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":11.12},{"place":297,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":11.1},{"place":298,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":10.72},{"place":299,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":10.53},{"place":300,"model":"sphinx-v2","company":"alpha-vllm","family":"SPHINX","version":"SPHINX-V2","score":9.7},{"place":301,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":8.52}]},{"id":"mathvision-with-tools","name":"MathVision (With Tools)","topic":"Math reasoning (multimodal)","description":"MathVision visual math benchmark evaluated with a Python code-interpreter tool.","url":"https://mathllm.github.io/mathvision","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":98.6,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":98.6},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":97.8},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":97.8},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":97.1},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":96.8},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":96.1},{"place":7,"model":"gpt-5.4-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":96.1},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":95.7},{"place":9,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":93.2},{"place":10,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":85},{"place":11,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84.6},{"place":12,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84.6}]},{"id":"mathvista","name":"MathVista","topic":"Multimodal math reasoning","description":"Visual math reasoning across diverse tasks.","url":"https://mathvista.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":90.7,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":111,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":90.7},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":90.5},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":90.2},{"place":4,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":90.1},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.8},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.2},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.1},{"place":8,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":88},{"place":9,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":87.7},{"place":10,"model":"o3","company":"openai","family":"o3","version":"o3","score":86.8},{"place":11,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.8},{"place":12,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":86.3},{"place":13,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":86.1},{"place":14,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":86},{"place":15,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.8},{"place":16,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":85.6},{"place":17,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":85.6},{"place":18,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":85.5},{"place":19,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":85.2},{"place":20,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.1},{"place":21,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":85},{"place":22,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":84.8},{"place":23,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":84.6},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.6},{"place":25,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":84.4},{"place":26,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.4},{"place":27,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.4},{"place":28,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.4},{"place":29,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.2},{"place":30,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":83.97},{"place":31,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":83.97},{"place":32,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.88},{"place":33,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":83.6},{"place":34,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":83.51},{"place":35,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.5},{"place":36,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":83.3},{"place":37,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":82.85},{"place":38,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":82.8},{"place":39,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.7},{"place":40,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":82.7},{"place":41,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":82.7},{"place":42,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":82.5},{"place":43,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":82.1},{"place":44,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.9},{"place":45,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.9},{"place":46,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.4},{"place":47,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":81.3},{"place":48,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.2},{"place":49,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":81.2},{"place":50,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":81},{"place":51,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.9},{"place":52,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":80.7},{"place":53,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":80.7},{"place":54,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":80.7},{"place":55,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.6},{"place":56,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":80.6},{"place":57,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":80.4},{"place":58,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.2},{"place":59,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":80.1},{"place":60,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":80.1},{"place":61,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80},{"place":62,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":79.9},{"place":63,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":79.9},{"place":64,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":79.86},{"place":65,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.4},{"place":66,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":79.2},{"place":67,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":79.2},{"place":68,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.5},{"place":69,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.5},{"place":70,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":78.5},{"place":71,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.4},{"place":72,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":77.4},{"place":73,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.2},{"place":74,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":77.1},{"place":75,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.78},{"place":76,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":75.9},{"place":77,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":75.6},{"place":78,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":75.5},{"place":79,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":75.5},{"place":80,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.3},{"place":81,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":74.6},{"place":82,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":74.6},{"place":83,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":74.3},{"place":84,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":74.2},{"place":85,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":73.7},{"place":86,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":73.7},{"place":87,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.7},{"place":88,"model":"command-a-vision-07-2025","company":"cohere","family":"Command","version":"Command","score":73.5},{"place":89,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.1},{"place":90,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":71.6},{"place":91,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":71.3},{"place":92,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":70.7},{"place":93,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":70.7},{"place":94,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.7},{"place":95,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":69.4},{"place":96,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":68.91},{"place":97,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.8},{"place":98,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":68.5},{"place":99,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":68.5},{"place":100,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":68.2},{"place":101,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":67.8},{"place":102,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":67.3},{"place":103,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":67.09},{"place":104,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":64.6},{"place":105,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":64.4},{"place":106,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":64.3},{"place":107,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":62.5},{"place":108,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":62.2},{"place":109,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.2},{"place":110,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62.1},{"place":111,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":61.6},{"place":112,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.3},{"place":113,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":61.2},{"place":114,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":60.8},{"place":115,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":59.9},{"place":116,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":59.4},{"place":117,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":59.1},{"place":118,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":59.1},{"place":119,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":58.9},{"place":120,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":58.6},{"place":121,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.6},{"place":122,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.6},{"place":123,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.5},{"place":124,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":58},{"place":125,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":57.6},{"place":126,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":57.2},{"place":127,"model":"gemini-1.5-flash-8b-0827","company":"google","family":"Gemini","version":"Gemini 1.5","score":56.9},{"place":128,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":56.7},{"place":129,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":56.6},{"place":130,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":56.3},{"place":131,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":55.7},{"place":132,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":54.2},{"place":133,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":54.2},{"place":134,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.9},{"place":135,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":51.6},{"place":136,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":51.5},{"place":137,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":50.4},{"place":138,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":44.8},{"place":139,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":44.5},{"place":140,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":40.9}]},{"id":"mathvista-mini","name":"MathVista-Mini","topic":"Math reasoning (multimodal)","description":"Lightweight subset of MathVista for quick evaluation of visual mathematical reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-397B-A17B","top_percent":90.3,"top_model_id":"qwen3.5-397b-a17b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 397B A17B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":212,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.3},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":90.1},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.9},{"place":4,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.8},{"place":5,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.4},{"place":6,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.4},{"place":7,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.4},{"place":8,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.2},{"place":9,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":86.1},{"place":10,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.9},{"place":11,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.8},{"place":12,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.8},{"place":13,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.7},{"place":14,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":85.6},{"place":15,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.1},{"place":16,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":85},{"place":17,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":84.5},{"place":18,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":83.97},{"place":19,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.8},{"place":20,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.8},{"place":21,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":83.1},{"place":22,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":83.1},{"place":23,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":82.9},{"place":24,"model":"nemotron-3-nano-omni-30b-a3b-reasoning","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.8},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.7},{"place":26,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.3},{"place":27,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.9},{"place":28,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.8},{"place":29,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.8},{"place":30,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.3},{"place":31,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":80.9},{"place":32,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":80.1},{"place":33,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.1},{"place":34,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80},{"place":35,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":79.9},{"place":36,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.8},{"place":37,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.5},{"place":38,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.5},{"place":39,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.4},{"place":40,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.3},{"place":41,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":79.1},{"place":42,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":79.1},{"place":43,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":78.6},{"place":44,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.4},{"place":45,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.2},{"place":46,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.2},{"place":47,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":77.1},{"place":48,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.7},{"place":49,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":76.5},{"place":50,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.4},{"place":51,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":75.9},{"place":52,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":75.5},{"place":53,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":75.5},{"place":54,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":75.2},{"place":55,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":75},{"place":56,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":74.8},{"place":57,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.7},{"place":58,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.6},{"place":59,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":73.5},{"place":60,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":73.3},{"place":61,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":73.3},{"place":62,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":73.1},{"place":63,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":73.1},{"place":64,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.8},{"place":65,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":72.5},{"place":66,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":72.4},{"place":67,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":72.3},{"place":68,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":71.9},{"place":69,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":71.8},{"place":70,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":71.5},{"place":71,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":71.4},{"place":72,"model":"qvq-72b","company":"qwen","family":"QvQ","version":"QvQ 72B","score":71.4},{"place":73,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":71},{"place":74,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":70.9},{"place":75,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":70.5},{"place":76,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":70.5},{"place":77,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.3},{"place":78,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":70.2},{"place":79,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":69.8},{"place":80,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":68.5},{"place":81,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":68.2},{"place":82,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":68.1},{"place":83,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":67.9},{"place":84,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":67.7},{"place":85,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":67.7},{"place":86,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":67.7},{"place":87,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":67.5},{"place":88,"model":"ovis1.6-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":67.2},{"place":89,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":67.1},{"place":90,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":67.1},{"place":91,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":66.6},{"place":92,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":66.3},{"place":93,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":66.1},{"place":94,"model":"aria","company":"rhymes","family":"Aria","version":"Aria","score":66.1},{"place":95,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":65.5},{"place":96,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.3},{"place":97,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":65.3},{"place":98,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":64.4},{"place":99,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":64},{"place":100,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":63.9},{"place":101,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":63.8},{"place":102,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":63.8},{"place":103,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":63.8},{"place":104,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":63.8},{"place":105,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":63.7},{"place":106,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.6},{"place":107,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":63.2},{"place":108,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":62.8},{"place":109,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":62.3},{"place":110,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.2},{"place":111,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":62.1},{"place":112,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":61.6},{"place":113,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":61.3},{"place":114,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.3},{"place":115,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":61.3},{"place":116,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":60.7},{"place":117,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":60.6},{"place":118,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":60.5},{"place":119,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":59.7},{"place":120,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":59.6},{"place":121,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":59.5},{"place":122,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":59.4},{"place":123,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":59},{"place":124,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":58.6},{"place":125,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":58.6},{"place":126,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":58.4},{"place":127,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":58.3},{"place":128,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":58.2},{"place":129,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":58.2},{"place":130,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":58.1},{"place":131,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":58.1},{"place":132,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":58},{"place":133,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":57.8},{"place":134,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":57.7},{"place":135,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":57.6},{"place":136,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":57.4},{"place":137,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":57.3},{"place":138,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":57.2},{"place":139,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":56.8},{"place":140,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":56.5},{"place":141,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":55.8},{"place":142,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":55.6},{"place":143,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":54.7},{"place":144,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":54.3},{"place":145,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":54.1},{"place":146,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":53.6},{"place":147,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":53.5},{"place":148,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":53.2},{"place":149,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":53.2},{"place":150,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":53},{"place":151,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.9},{"place":152,"model":"grok-1.5v","company":"xai","family":"Grok","version":"Grok 1.5","score":52.8},{"place":153,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":52.4},{"place":154,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":52.4},{"place":155,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":52.2},{"place":156,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":52.1},{"place":157,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":51.9},{"place":158,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":51.6},{"place":159,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":51.5},{"place":160,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":51.3},{"place":161,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":51.1},{"place":162,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":51},{"place":163,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":50.9},{"place":164,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":50.5},{"place":165,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":50.5},{"place":166,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":50.3},{"place":167,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":50},{"place":168,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":49.9},{"place":169,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":49.5},{"place":170,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":49},{"place":171,"model":"llava-next-110b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":49},{"place":172,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.7},{"place":173,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":47.9},{"place":174,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":47.8},{"place":175,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":47.8},{"place":176,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":47.8},{"place":177,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":47.7},{"place":178,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":47.6},{"place":179,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":47.6},{"place":180,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":47},{"place":181,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":46.5},{"place":182,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":46.4},{"place":183,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":46.3},{"place":184,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":45.8},{"place":185,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":45.8},{"place":186,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":45.8},{"place":187,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.2},{"place":188,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":45.2},{"place":189,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":45.2},{"place":190,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":44.9},{"place":191,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":44.8},{"place":192,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":44.5},{"place":193,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":44.5},{"place":194,"model":"phi-3-vision-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":44.5},{"place":195,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":44.4},{"place":196,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":43.9},{"place":197,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":43.9},{"place":198,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":43.4},{"place":199,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":43.3},{"place":200,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":43.3},{"place":201,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":43.2},{"place":202,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":43},{"place":203,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":43},{"place":204,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":42.5},{"place":205,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":40.9},{"place":206,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":40.5},{"place":207,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":40.4},{"place":208,"model":"llava-llama-3-8b","company":"llava","family":"LLaVA","version":"LLaVA-LLaMA-3","score":40},{"place":209,"model":"blip-3-4b","company":"salesforce","family":"BLIP","version":"BLIP-3","score":39.6},{"place":210,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":39.4},{"place":211,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":39.1},{"place":212,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":38.7},{"place":213,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":38.6},{"place":214,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37.8},{"place":215,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":37.7},{"place":216,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":37.5},{"place":217,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":37.2},{"place":218,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":36.8},{"place":219,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":36.5},{"place":220,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":36.1},{"place":221,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":35.3},{"place":222,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":34.8},{"place":223,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":34.8},{"place":224,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":34.7},{"place":225,"model":"llava-next-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":34.6},{"place":226,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":34.5},{"place":227,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":34},{"place":228,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":33.8},{"place":229,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":32.4},{"place":230,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":31.5},{"place":231,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":31.1},{"place":232,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":30.7},{"place":233,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":30.6},{"place":234,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":30},{"place":235,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":29.5},{"place":236,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":29.4},{"place":237,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":28.9},{"place":238,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":28.8},{"place":239,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":28.7},{"place":240,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":28},{"place":241,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":27.8},{"place":242,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":27.7},{"place":243,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":26.4},{"place":244,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":26.2},{"place":245,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":26.1},{"place":246,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":25.8},{"place":247,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":25.6},{"place":248,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":25.3},{"place":249,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":25.3},{"place":250,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":24.6},{"place":251,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":23.7},{"place":252,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":23.6},{"place":253,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":23.1},{"place":254,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":18.6},{"place":255,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":10.3}]},{"id":"mattools","name":"MatTools","topic":"Materials science tool use","description":"Benchmark evaluating LLM agents on materials-science tool usage (pymatgen-based QA and code/tool generation tasks).","url":"https://arxiv.org/abs/2505.10852","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":68.8,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":68.8},{"place":2,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":63.8},{"place":3,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":49.3},{"place":4,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":47.1},{"place":5,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":47.1},{"place":6,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":44.93},{"place":7,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":34.1},{"place":8,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21},{"place":9,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":15.9},{"place":10,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":10.9}]},{"id":"maverix","name":"MAVERIX","topic":"Audio-visual video understanding","description":"Benchmark requiring joint video and audio understanding (situational awareness, social sentiment).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Flash","top_percent":67.4,"top_model_id":"gemini-2.5-flash","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.4},{"place":2,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":66.6}]},{"id":"maxife","name":"MAXIFE","topic":"Instruction following (multilingual)","description":"Multilingual instruction-following evaluation across English and multilingual original prompts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.7-Max","top_percent":89.2,"top_model_id":"qwen3.7-max","top_generation":"Qwen3.7","top_model_base":"Qwen3.7 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":29,"total_models":3854,"placements":[{"place":1,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":89.2},{"place":2,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.9},{"place":3,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":88.8},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":88.4},{"place":5,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.2},{"place":6,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":88.2},{"place":7,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88},{"place":8,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.9},{"place":9,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":87.7},{"place":10,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":87.7},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.5},{"place":12,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.6},{"place":13,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":85.6},{"place":14,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":85.3},{"place":15,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84},{"place":16,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":83.7},{"place":17,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.4},{"place":18,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.2},{"place":19,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":81.3},{"place":20,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":80.1},{"place":21,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":79.9},{"place":22,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.2},{"place":23,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78},{"place":24,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.4},{"place":25,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":72.8},{"place":26,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":72.1},{"place":27,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.6},{"place":28,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":50.7},{"place":29,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.2}]},{"id":"mbe-bar-exam","name":"MBE Bar Exam","topic":"Legal exams","description":"Multistate Bar Examination (US bar exam) multiple-choice questions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":88.8,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.8},{"place":2,"model":"thomson-1.0-small","company":"thomsonreuters","family":"Thomson","version":"Thomson-1.0","score":83.4},{"place":3,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":83.1},{"place":4,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.1},{"place":5,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.3}]},{"id":"mbpp","name":"MBPP","topic":"Code generation","description":"Short Python problems with hidden tests.","url":"https://huggingface.co/datasets/Muennighoff/mbpp","leaderboard":"https://llm-stats.com/benchmarks","github":"","paper":"https://arxiv.org/abs/2108.07732","metric":"percent","stars":"36312","top_model":"Kimi-K2 Thinking","top_percent":97.4,"top_model_id":"kimi-k2-thinking","top_generation":"Kimi K2","top_model_base":"Kimi K2 Thinking","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":522,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":97.4},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":96.8},{"place":3,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":96.2},{"place":4,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":95.5},{"place":5,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":95.5},{"place":6,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":95.5},{"place":7,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":95.3},{"place":8,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":95.2},{"place":9,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":94.3},{"place":10,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":94.2},{"place":11,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":94.16},{"place":12,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":93.9},{"place":13,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.4},{"place":14,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":93.4},{"place":15,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":93.39},{"place":16,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":93.1},{"place":17,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":93.1},{"place":18,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":92.9},{"place":19,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":92.7},{"place":20,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":92.3},{"place":21,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":92.3},{"place":22,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":92.3},{"place":23,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.9},{"place":24,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":91.8},{"place":25,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":91.8},{"place":26,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":91.8},{"place":27,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":91.6},{"place":28,"model":"llama-3.3-nemotron-49b-super-v1","company":"nvidia","family":"Llama","version":"Llama 3.3","score":91.3},{"place":29,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":91.05},{"place":30,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":91.05},{"place":31,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":91},{"place":32,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":91},{"place":33,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":90.7},{"place":34,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.5},{"place":35,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":90.5},{"place":36,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.2},{"place":37,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":89.7},{"place":38,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":89.7},{"place":39,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":89.4},{"place":40,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":89.4},{"place":41,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":89.4},{"place":42,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":89.4},{"place":43,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":89.4},{"place":44,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":89.4},{"place":45,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":89.2},{"place":46,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":89.11},{"place":47,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89},{"place":48,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":88.9},{"place":49,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.6},{"place":50,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":88.29},{"place":51,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":88.2},{"place":52,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.2},{"place":53,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":87.83},{"place":54,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.6},{"place":55,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":87.6},{"place":56,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":87.6},{"place":57,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":87.6},{"place":58,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":87.6},{"place":59,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":87.3},{"place":60,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":86.8},{"place":61,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.65},{"place":62,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":86.2},{"place":63,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.2},{"place":64,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86.2},{"place":65,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":86},{"place":66,"model":"grok-beta","company":"xai","family":"Grok","version":"Grok","score":86},{"place":67,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":86},{"place":68,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":86},{"place":69,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.97},{"place":70,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":85.8},{"place":71,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":85.7},{"place":72,"model":"stable-diffcoder-8b-instruct","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":85.7},{"place":73,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":85.7},{"place":74,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":85.7},{"place":75,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.5},{"place":76,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":85.45},{"place":77,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":85.4},{"place":78,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":85.2},{"place":79,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":85.2},{"place":80,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":85.2},{"place":81,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":85.2},{"place":82,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":85.01},{"place":83,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":85},{"place":84,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":84.8},{"place":85,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":84.7},{"place":86,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.7},{"place":87,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":84.7},{"place":88,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.7},{"place":89,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":84.6},{"place":90,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":84.6},{"place":91,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.5},{"place":92,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84.5},{"place":93,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84.2},{"place":94,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":84.08},{"place":95,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":84.05},{"place":96,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":84},{"place":97,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":84},{"place":98,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84},{"place":99,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":83.8},{"place":100,"model":"claude-3-sonnet-mar-2024","company":"anthropic","family":"claude-3-sonnet","version":"claude-3-sonnet (Mar 2024)","score":83.6},{"place":101,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":83.6},{"place":102,"model":"stable-diffcoder-8b-base","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":83.6},{"place":103,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":83.6},{"place":104,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.5},{"place":105,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":83.5},{"place":106,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":83},{"place":107,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":82.8},{"place":108,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.8},{"place":109,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":82.8},{"place":110,"model":"gpt-3.5-turbo-nov-2023","company":"openai","family":"GPT","version":"GPT-3.5","score":82.5},{"place":111,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":82.5},{"place":112,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":82.5},{"place":113,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":82.5},{"place":114,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":82.3},{"place":115,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":82},{"place":116,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":82},{"place":117,"model":"seed-coder-8b-base","company":"bytedance","family":"Seed","version":"Seed Coder","score":82},{"place":118,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82},{"place":119,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":81.8},{"place":120,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":81.71},{"place":121,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":81.6},{"place":122,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":81.5},{"place":123,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":81.5},{"place":124,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":81.4},{"place":125,"model":"seed1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":81.4},{"place":126,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.4},{"place":127,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.32},{"place":128,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":81},{"place":129,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":81},{"place":130,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":81},{"place":131,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":80.8},{"place":132,"model":"artigenz-coder-ds-6.7b","company":"artigenz","family":"Artigenz-Coder-DS-6.7B","version":"Artigenz Coder DS","score":80.7},{"place":133,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.5},{"place":134,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":80.4},{"place":135,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":80.4},{"place":136,"model":"opencodeinterpreter-ds-33b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":80.2},{"place":137,"model":"claude-3-haiku-mar-2024","company":"anthropic","family":"claude-3-haiku","version":"claude-3-haiku (Mar 2024)","score":80.2},{"place":138,"model":"deepseek-coder-33b","company":"deepseek","family":"DeepSeek Coder","version":"DeepSeek Coder","score":80.2},{"place":139,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":80.2},{"place":140,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":80.2},{"place":141,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.2},{"place":142,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80},{"place":143,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80},{"place":144,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":80},{"place":145,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":80},{"place":146,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":80},{"place":147,"model":"opencoder-8b-base","company":"map","family":"OpenCoder","version":"OpenCoder","score":79.9},{"place":148,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":79.6},{"place":149,"model":"dream-coder-7b-instruct","company":"huawei","family":"Dream","version":"Dream-Coder v0","score":79.6},{"place":150,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":79.4},{"place":151,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":79.4},{"place":152,"model":"whiterabbitneo-33b-v1","company":"whiterabbit","family":"WhiteRabbitNeo-33B-v1","version":"WhiteRabbitNeo-33B-v1","score":79.4},{"place":153,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":79.4},{"place":154,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":79.4},{"place":155,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.2},{"place":156,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":79.1},{"place":157,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":79.06},{"place":158,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":79},{"place":159,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":79},{"place":160,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.8},{"place":161,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":78.8},{"place":162,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":78.59},{"place":163,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.38},{"place":164,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":78.3},{"place":165,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":78.2},{"place":166,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.2},{"place":167,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":78.2},{"place":168,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":78},{"place":169,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":78},{"place":170,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":77.9},{"place":171,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":77.8},{"place":172,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":77.75},{"place":173,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":77.75},{"place":174,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":77.7},{"place":175,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":77.6},{"place":176,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":77.5},{"place":177,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":77.3},{"place":178,"model":"xwincoder-34b","company":"xwin","family":"XwinCoder-34B","version":"XwinCoder-34B","score":77},{"place":179,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":77},{"place":180,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":76.9},{"place":181,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":76.9},{"place":182,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":76.8},{"place":183,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":76.7},{"place":184,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":76.7},{"place":185,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.7},{"place":186,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":76.69},{"place":187,"model":"opencodeinterpreter-ds-6.7b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":76.5},{"place":188,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":76.4},{"place":189,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":76.4},{"place":190,"model":"code-millenials-34b","company":"code","family":"code-millenials-34B","version":"code-millenials-34B","score":76.2},{"place":191,"model":"gemini-diffusion","company":"google","family":"Gemini","version":"Gemini Diffusion","score":76},{"place":192,"model":"speechless-coder-ds-6.7b","company":"speechless","family":"speechless-coder-ds-6.7B","version":"speechless-coder-ds-6.7B","score":75.9},{"place":193,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":75.9},{"place":194,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":75.9},{"place":195,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":75.8},{"place":196,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":75.7},{"place":197,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":75.7},{"place":198,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":75.6},{"place":199,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75.49},{"place":200,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":75.4},{"place":201,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.4},{"place":202,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":75.4},{"place":203,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75.4},{"place":204,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":75.4},{"place":205,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":75.4},{"place":206,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":75.2},{"place":207,"model":"wizardcoder-python-34b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":75.1},{"place":208,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":75.1},{"place":209,"model":"diffucoder-7b-instruct","company":"apple","family":"DiffuCoder","version":"DiffuCoder","score":75.1},{"place":210,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":75},{"place":211,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":74.9},{"place":212,"model":"wavecoder-ultra-6.7b","company":"wavecoder","family":"WaveCoder-Ultra-6.7B","version":"WaveCoder-Ultra-6.7B","score":74.9},{"place":213,"model":"starchat2-15b-v0.1","company":"huggingface","family":"starchat2-15b-v0.1","version":"starchat2-15b-v0.1","score":74.9},{"place":214,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.9},{"place":215,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":74.9},{"place":216,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":74.9},{"place":217,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.71},{"place":218,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":74.71},{"place":219,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":74.6},{"place":220,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":74.6},{"place":221,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.6},{"place":222,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.4},{"place":223,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":74.4},{"place":224,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":74.3},{"place":225,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":74.3},{"place":226,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":74.28},{"place":227,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.2},{"place":228,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":74.2},{"place":229,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":74.2},{"place":230,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":74},{"place":231,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":73.9},{"place":232,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":73.9},{"place":233,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.82},{"place":234,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":73.8},{"place":235,"model":"speechless-codellama-34b-v2.0","company":"speechless","family":"speechless-codellama-34B-v2.0","version":"speechless-codellama-34B-v2.0","score":73.8},{"place":236,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":73.8},{"place":237,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.8},{"place":238,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":73.8},{"place":239,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":73.6},{"place":240,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":73.5},{"place":241,"model":"speechless-starcoder2-15b","company":"bigcode","family":"speechless-starcoder2-15b","version":"speechless-starcoder2-15b","score":73.5},{"place":242,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":73.5},{"place":243,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.4},{"place":244,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":73.4},{"place":245,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":73.2},{"place":246,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":73.2},{"place":247,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":73},{"place":248,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":73},{"place":249,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":73},{"place":250,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":73},{"place":251,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":72.8},{"place":252,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":72.8},{"place":253,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.7},{"place":254,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.6},{"place":255,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":72.6},{"place":256,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":72.58},{"place":257,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":72.58},{"place":258,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":72.5},{"place":259,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":72.5},{"place":260,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":72.5},{"place":261,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":72.2},{"place":262,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":72.2},{"place":263,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":72.14},{"place":264,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":72},{"place":265,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":72},{"place":266,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":72},{"place":267,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":72},{"place":268,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":72},{"place":269,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":72},{"place":270,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":71.9},{"place":271,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":71.9},{"place":272,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":71.9},{"place":273,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":71.9},{"place":274,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":71.7},{"place":275,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":71.4},{"place":276,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":71.2},{"place":277,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":71.2},{"place":278,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":71.2},{"place":279,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":71.16},{"place":280,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":71},{"place":281,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":70.9},{"place":282,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":70.9},{"place":283,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":70.9},{"place":284,"model":"codellama-70b","company":"meta","family":"CodeLlama","version":"CodeLlama","score":70.8},{"place":285,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":70.8},{"place":286,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":70.8},{"place":287,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":70.8},{"place":288,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.76},{"place":289,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":70.63},{"place":290,"model":"magicoder-s-cl-7b","company":"magicoder","family":"Magicoder-S-CL-7B","version":"Magicoder-S-CL-7B","score":70.6},{"place":291,"model":"dolphin-2.6-mixtral-8x7b","company":"mistral","family":"dolphin-2.6-mixtral-8x7b","version":"dolphin-2.6-mixtral-8x7b","score":70.6},{"place":292,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":70.6},{"place":293,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":70.5},{"place":294,"model":"codegemma-7b-it","company":"google","family":"Codegemma","version":"Codegemma","score":70.4},{"place":295,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":70.4},{"place":296,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":70.4},{"place":297,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":70.2},{"place":298,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.2},{"place":299,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":70.1},{"place":300,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":70.1},{"place":301,"model":"llada-moe-7b-a1b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":70},{"place":302,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":70},{"place":303,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":70},{"place":304,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":69.8},{"place":305,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":69.7},{"place":306,"model":"mistral-small-3-24b-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":69.64},{"place":307,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.6},{"place":308,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":69.6},{"place":309,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":69.6},{"place":310,"model":"yi-coder-9b","company":"01ai","family":"Yi","version":"Yi-Coder","score":69.4},{"place":311,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":69.3},{"place":312,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":69.2},{"place":313,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":69.2},{"place":314,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.2},{"place":315,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":69.05},{"place":316,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":68.9},{"place":317,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":68.8},{"place":318,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":68.8},{"place":319,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":68.7},{"place":320,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":68.6},{"place":321,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":68.6},{"place":322,"model":"codestral-mamba","company":"mistral","family":"Codestral","version":"Codestral","score":68.5},{"place":323,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":68.5},{"place":324,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":68.4},{"place":325,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":68.39},{"place":326,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":68.3},{"place":327,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":68.3},{"place":328,"model":"baichuan-3","company":"baichuan","family":"Baichuan","version":"Baichuan 3","score":68.2},{"place":329,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":68},{"place":330,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":67.9},{"place":331,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":67.9},{"place":332,"model":"llama-4-scout","company":"meta","family":"Llama","version":"Llama 1","score":67.8},{"place":333,"model":"codegemma-1.1-7b","company":"google","family":"CodeGemma","version":"CodeGemma","score":67.7},{"place":334,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":67.3},{"place":335,"model":"databricks-dbrx-instruct","company":"databricks","family":"databricks/dbrx-instruct","version":"databricks/dbrx-instruct","score":67.2},{"place":336,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":67.2},{"place":337,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.9},{"place":338,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.9},{"place":339,"model":"speechless-starcoder2-7b","company":"bigcode","family":"speechless-starcoder2-7b","version":"speechless-starcoder2-7b","score":66.7},{"place":340,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":66.7},{"place":341,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":66.6},{"place":342,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":66.2},{"place":343,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":66.2},{"place":344,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":66.2},{"place":345,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":66.2},{"place":346,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":66},{"place":347,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":65.96},{"place":348,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":65.9},{"place":349,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":65.9},{"place":350,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":65.9},{"place":351,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":65.8},{"place":352,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":65.6},{"place":353,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":65.51},{"place":354,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":65.5},{"place":355,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":65.5},{"place":356,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":65.5},{"place":357,"model":"rnd1-base-0910","company":"radicalnumerics","family":"RND1","version":"RND1","score":65.4},{"place":358,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":65.4},{"place":359,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":65.3},{"place":360,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":65.2},{"place":361,"model":"codegemma-7b","company":"google","family":"Codegemma","version":"codegemma-7b","score":65.1},{"place":362,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":65},{"place":363,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":64.6},{"place":364,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":64.6},{"place":365,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64.5},{"place":366,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":64.4},{"place":367,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":64.4},{"place":368,"model":"wizardcoder-15b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":64.3},{"place":369,"model":"speechless-coding-7b-16k-tora","company":"speechless","family":"speechless-coding-7B-16k-tora","version":"speechless-coding-7B-16k-tora","score":64.2},{"place":370,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":64.2},{"place":371,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":64.2},{"place":372,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":64.2},{"place":373,"model":"phi-2-2.7b","company":"microsoft","family":"phi-2-2.7B","version":"phi-2-2.7B","score":64},{"place":374,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":64},{"place":375,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":63.9},{"place":376,"model":"openchat-3.5-7b-0106","company":"openchat","family":"OpenChat-3.5-7B-0106","version":"OpenChat-3.5-7B-0106","score":63.8},{"place":377,"model":"gemma-3n-e4b-instructed-litert-preview","company":"google","family":"Gemma","version":"Gemma 3n","score":63.6},{"place":378,"model":"gemma-3n-e4b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":63.6},{"place":379,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":63.6},{"place":380,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":63.5},{"place":381,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":63.4},{"place":382,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":63.2},{"place":383,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":63.2},{"place":384,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.2},{"place":385,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.1},{"place":386,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":63.08},{"place":387,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63},{"place":388,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":63},{"place":389,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":63},{"place":390,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":62.6},{"place":391,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":62.6},{"place":392,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":62.6},{"place":393,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":62.4},{"place":394,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":62.39},{"place":395,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":62.39},{"place":396,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":62.2},{"place":397,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.17},{"place":398,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.9},{"place":399,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":61.8},{"place":400,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":61.8},{"place":401,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":61.8},{"place":402,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":61.59},{"place":403,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":61.4},{"place":404,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":61.4},{"place":405,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":61.4},{"place":406,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":61.4},{"place":407,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":61.4},{"place":408,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":61.4},{"place":409,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":61.4},{"place":410,"model":"wizardcoder-python-34b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":61.2},{"place":411,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":61.1},{"place":412,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":61.1},{"place":413,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":61},{"place":414,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":60.7},{"place":415,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.7},{"place":416,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":60.6},{"place":417,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.6},{"place":418,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":60.4},{"place":419,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.4},{"place":420,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.3},{"place":421,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":60.3},{"place":422,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":60.27},{"place":423,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":60.21},{"place":424,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":60.2},{"place":425,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":60.2},{"place":426,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.2},{"place":427,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":60.2},{"place":428,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":59.9},{"place":429,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":59.8},{"place":430,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":59.5},{"place":431,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":59.5},{"place":432,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":59.5},{"place":433,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":59.2},{"place":434,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":58.8},{"place":435,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":58.8},{"place":436,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":58.7},{"place":437,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":58.66},{"place":438,"model":"wizardcoder-python-7b-v1.0","company":"microsoft","family":"WizardCoder-Python-7B-V1.0","version":"WizardCoder-Python-7B-V1.0","score":58.5},{"place":439,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":58.1},{"place":440,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":58.1},{"place":441,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":58},{"place":442,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":57.8},{"place":443,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":57.6},{"place":444,"model":"mistralhermes-codepro-7b-v1","company":"mistral","family":"MistralHermes","version":"MistralHermes CodePro v1","score":57.4},{"place":445,"model":"speechless-code-mistral-7b-v1.0","company":"speechless","family":"speechless-code-mistral-7B-v1.0","version":"speechless-code-mistral-7B-v1.0","score":57.4},{"place":446,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":57.4},{"place":447,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":57.1},{"place":448,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":57.1},{"place":449,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":57.1},{"place":450,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":57},{"place":451,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":57},{"place":452,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":56.9},{"place":453,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":56.8},{"place":454,"model":"codet5-16b","company":"salesforce","family":"CodeT5+-16B","version":"CodeT5+-16B","score":56.6},{"place":455,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":56.6},{"place":456,"model":"gemma-3n-e2b-instructed-litert-preview","company":"google","family":"Gemma","version":"Gemma 3n","score":56.6},{"place":457,"model":"codet5plus-16b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":56.6},{"place":458,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":56.2},{"place":459,"model":"codellama-python-34b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":56.2},{"place":460,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":55.8},{"place":461,"model":"codegemma-2b","company":"google","family":"Codegemma","version":"codegemma-2b","score":55.6},{"place":462,"model":"wizardcoder-python-13b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":55.6},{"place":463,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":55.6},{"place":464,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":55.6},{"place":465,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.56},{"place":466,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.4},{"place":467,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":55.2},{"place":468,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":55.2},{"place":469,"model":"starcoder-15b","company":"bigcode","family":"StarCoder-15B","version":"StarCoder","score":55.1},{"place":470,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":55.1},{"place":471,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":55.04},{"place":472,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":55},{"place":473,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":55},{"place":474,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":54.9},{"place":475,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":54.8},{"place":476,"model":"stablecode-3b","company":"stability","family":"StableCode","version":"StableCode","score":54.8},{"place":477,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":54.4},{"place":478,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":54.4},{"place":479,"model":"codegen-16b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":54.2},{"place":480,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":54.1},{"place":481,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":54},{"place":482,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":54},{"place":483,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":53.9},{"place":484,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":53.85},{"place":485,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":53.6},{"place":486,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":53.4},{"place":487,"model":"codet5-6b","company":"salesforce","family":"CodeT5+-6B","version":"CodeT5+-6B","score":52.9},{"place":488,"model":"codet5plus-6b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":52.9},{"place":489,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":52.9},{"place":490,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":52.9},{"place":491,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":52.6},{"place":492,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":52.6},{"place":493,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":52.6},{"place":494,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":52.5},{"place":495,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":52.5},{"place":496,"model":"openhermes-2.5-code-290k-13b","company":"openhermes","family":"OpenHermes-2.5-Code-290k-13B","version":"OpenHermes-2.5-Code-290k-13B","score":52.4},{"place":497,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":52.4},{"place":498,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":52.4},{"place":499,"model":"code-qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":52.4},{"place":500,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":52.4},{"place":501,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":52.4},{"place":502,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":52.2},{"place":503,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":52.2},{"place":504,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":52.1},{"place":505,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":51.9},{"place":506,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":51.9},{"place":507,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":51.8},{"place":508,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":51.8},{"place":509,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":51.8},{"place":510,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":51.6},{"place":511,"model":"yi-coder-1.5b","company":"01ai","family":"Yi","version":"Yi-Coder","score":51.6},{"place":512,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":51.5},{"place":513,"model":"code-qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":51.4},{"place":514,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":51.1},{"place":515,"model":"minicpm-moe-8x2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":51.05},{"place":516,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":51},{"place":517,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":50.95},{"place":518,"model":"codegen-6b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":50.8},{"place":519,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":50.6},{"place":520,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":50.6},{"place":521,"model":"xdan-l1-chat-rl-v1-7b","company":"xdan","family":"xDAN-L1-Chat-RL-v1-7B","version":"xDAN-L1-Chat-RL-v1-7B","score":50.3},{"place":522,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":50.3},{"place":523,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":50.3},{"place":524,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":50.2},{"place":525,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":50.12},{"place":526,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":50},{"place":527,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":50},{"place":528,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":49.8},{"place":529,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.6},{"place":530,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":49.4},{"place":531,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":49.4},{"place":532,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":49.4},{"place":533,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":49.1},{"place":534,"model":"codellama-python-13b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":49},{"place":535,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":48.95},{"place":536,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":48.9},{"place":537,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":48.9},{"place":538,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":48.5},{"place":539,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":48.48},{"place":540,"model":"codet5-2b","company":"salesforce","family":"CodeT5+-2B","version":"CodeT5+-2B","score":48.4},{"place":541,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":48.4},{"place":542,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":48.3},{"place":543,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":48.2},{"place":544,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":48.01},{"place":545,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":48},{"place":546,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":48},{"place":547,"model":"codellama-python-7b","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":47.6},{"place":548,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":47.5},{"place":549,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":47.5},{"place":550,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":47.4},{"place":551,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":47.4},{"place":552,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":47.31},{"place":553,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":47.3},{"place":554,"model":"coda-1.7b-instruct","company":"salesforce","family":"CoDA","version":"CoDA","score":47.2},{"place":555,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":47.1},{"place":556,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":47},{"place":557,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":47},{"place":558,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":47},{"place":559,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":46.9},{"place":560,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":46.8},{"place":561,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":46.8},{"place":562,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":46.8},{"place":563,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":46.4},{"place":564,"model":"codegen-2b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":46.3},{"place":565,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":46.2},{"place":566,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":46.2},{"place":567,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":46.1},{"place":568,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":46},{"place":569,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":45.8},{"place":570,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":45.8},{"place":571,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":45.6},{"place":572,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":45.4},{"place":573,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":45.2},{"place":574,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":45},{"place":575,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":44.86},{"place":576,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":44.8},{"place":577,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":44.8},{"place":578,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":44.7},{"place":579,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":44.4},{"place":580,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":44.4},{"place":581,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":44.4},{"place":582,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":44.4},{"place":583,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":44.4},{"place":584,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":44.2},{"place":585,"model":"code-qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":44.2},{"place":586,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":44.2},{"place":587,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":44},{"place":588,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":44},{"place":589,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":43.9},{"place":590,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.6},{"place":591,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":43.2},{"place":592,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":42.8},{"place":593,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":42.8},{"place":594,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":42.15},{"place":595,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":42.1},{"place":596,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":42.1},{"place":597,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":41.8},{"place":598,"model":"code-qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":41.8},{"place":599,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":41.6},{"place":600,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":41.5},{"place":601,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":41.45},{"place":602,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":41.4},{"place":603,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":41.4},{"place":604,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":41.4},{"place":605,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.2},{"place":606,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":41.2},{"place":607,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":41.2},{"place":608,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":41},{"place":609,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":41},{"place":610,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":40.9},{"place":611,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":40.9},{"place":612,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":40.9},{"place":613,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":40.8},{"place":614,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":40.6},{"place":615,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":40.52},{"place":616,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":40.4},{"place":617,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":40.2},{"place":618,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":39.8},{"place":619,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":39.7},{"place":620,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":39.7},{"place":621,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":39.6},{"place":622,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":39.6},{"place":623,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":39.6},{"place":624,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":39.34},{"place":625,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39.3},{"place":626,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":39.2},{"place":627,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":39},{"place":628,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":39},{"place":629,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":38.9},{"place":630,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":38.9},{"place":631,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":38.6},{"place":632,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":38.6},{"place":633,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":38.2},{"place":634,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":37.8},{"place":635,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":37.7},{"place":636,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":37.7},{"place":637,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":37.7},{"place":638,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":37.4},{"place":639,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.4},{"place":640,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":36.8},{"place":641,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":36.8},{"place":642,"model":"qwen1.5-moe-a2.7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":36.6},{"place":643,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":36.53},{"place":644,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":36.5},{"place":645,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":36.5},{"place":646,"model":"codegeex2-6b","company":"zai","family":"CodeGeeX","version":"CodeGeeX2","score":36.2},{"place":647,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":35.8},{"place":648,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":35.7},{"place":649,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":35.6},{"place":650,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":35.4},{"place":651,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":35.36},{"place":652,"model":"coda-1.7b-base","company":"salesforce","family":"CoDA","version":"CoDA","score":35.2},{"place":653,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":35.2},{"place":654,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":35.2},{"place":655,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":35.2},{"place":656,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":35.2},{"place":657,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":35},{"place":658,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":34.9},{"place":659,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":34.6},{"place":660,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":34},{"place":661,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":33.9},{"place":662,"model":"llama-2-34b","company":"meta","family":"Llama","version":"Llama 2","score":33.8},{"place":663,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":33.6},{"place":664,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":33.5},{"place":665,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":33.1},{"place":666,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":33.1},{"place":667,"model":"llama-2-34b","company":"meta","family":"Llama","version":"Llama 2","score":33},{"place":668,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":32.8},{"place":669,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":32.75},{"place":670,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":32.55},{"place":671,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":32.32},{"place":672,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":32.3},{"place":673,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":31.9},{"place":674,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":31.85},{"place":675,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":31.6},{"place":676,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":31.5},{"place":677,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":30.8},{"place":678,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":30.4},{"place":679,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":30.3},{"place":680,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":30.2},{"place":681,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":30.2},{"place":682,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":30.2},{"place":683,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":29.8},{"place":684,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":29.8},{"place":685,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":29.74},{"place":686,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":29.2},{"place":687,"model":"qwen1.5-4b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":29.2},{"place":688,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":29.2},{"place":689,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":29.1},{"place":690,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":29.1},{"place":691,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":29},{"place":692,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":28.8},{"place":693,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":28.6},{"place":694,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":28.4},{"place":695,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":28.34},{"place":696,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":28.3},{"place":697,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":28},{"place":698,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":27.6},{"place":699,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":27.4},{"place":700,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":27.4},{"place":701,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":27.2},{"place":702,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":27.2},{"place":703,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":27.17},{"place":704,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":27},{"place":705,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":27},{"place":706,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":26.8},{"place":707,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":26.3},{"place":708,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":26.1},{"place":709,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":26.1},{"place":710,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.4},{"place":711,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":25.4},{"place":712,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":25.2},{"place":713,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":24.82},{"place":714,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":24.2},{"place":715,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":23.7},{"place":716,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":23.4},{"place":717,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":22.8},{"place":718,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":22.8},{"place":719,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":22.8},{"place":720,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":22.8},{"place":721,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":22},{"place":722,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":22},{"place":723,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":21.8},{"place":724,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":21.4},{"place":725,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":21.2},{"place":726,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":20.8},{"place":727,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":20.6},{"place":728,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":20.1},{"place":729,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":20},{"place":730,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":19.91},{"place":731,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":19.9},{"place":732,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":19.8},{"place":733,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":18},{"place":734,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":17.8},{"place":735,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":17.7},{"place":736,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":16.8},{"place":737,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":16.1},{"place":738,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":15.6},{"place":739,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":15},{"place":740,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":14.8},{"place":741,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":14.8},{"place":742,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":14.8},{"place":743,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":14.5},{"place":744,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":14},{"place":745,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":14},{"place":746,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":12.4},{"place":747,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":12.1},{"place":748,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":11.4},{"place":749,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":11.2},{"place":750,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":10.2},{"place":751,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":10},{"place":752,"model":"zyte-1b","company":"zysecai","family":"Zyte","version":"Zyte","score":9.8},{"place":753,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":9.8},{"place":754,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":9.38},{"place":755,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":9},{"place":756,"model":"qwen1.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":6.8},{"place":757,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":6.6},{"place":758,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":5.6}]},{"id":"mbpp-ko","name":"MBPP-Ko","topic":"Code generation (Korean)","description":"Korean translation of MBPP code generation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-30B-A3B","top_percent":66.84,"top_model_id":"qwen3-30b-a3b","top_generation":"Qwen3","top_model_base":"Qwen3 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.84},{"place":2,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":66.84},{"place":3,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":65.41},{"place":4,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":61.55},{"place":5,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":61.55},{"place":6,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":57.29},{"place":7,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":47.97},{"place":8,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":44.55},{"place":9,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":39.38}]},{"id":"mbpp-plus","name":"MBPP+","topic":"Code generation","description":"Extended MBPP with more tests and stricter evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM 4.6","top_percent":94.2,"top_model_id":"glm-4.6","top_generation":"GLM 4.6","top_model_base":"GLM 4.6","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":379,"total_models":3854,"placements":[{"place":1,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":94.2},{"place":2,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":92.6},{"place":3,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":88.62},{"place":4,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":88.6},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.21},{"place":6,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":86},{"place":7,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":85.7},{"place":8,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":84.2},{"place":9,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.9},{"place":10,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83.9},{"place":11,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83.86},{"place":12,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83.86},{"place":13,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":83.1},{"place":14,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":83.07},{"place":15,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":82.54},{"place":16,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":82.5},{"place":17,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":82.3},{"place":18,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82.3},{"place":19,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":81.8},{"place":20,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.5},{"place":21,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":81.48},{"place":22,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":81.35},{"place":23,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":81},{"place":24,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":80.95},{"place":25,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":80.89},{"place":26,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":80.2},{"place":27,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":80.2},{"place":28,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":80.2},{"place":29,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":79.9},{"place":30,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":79.9},{"place":31,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":79.4},{"place":32,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":79.4},{"place":33,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":79.4},{"place":34,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":79.37},{"place":35,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":79.1},{"place":36,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":78.89},{"place":37,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":78.84},{"place":38,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":78.8},{"place":39,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":78.8},{"place":40,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":78.71},{"place":41,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":78.3},{"place":42,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":78.24},{"place":43,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":78.21},{"place":44,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":78.05},{"place":45,"model":"underdog-saluki-27b-1.0","company":"conwayresearch","family":"Underdog","version":"Underdog 1.0","score":78},{"place":46,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77.8},{"place":47,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.8},{"place":48,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":77.8},{"place":49,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":77.8},{"place":50,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":77.78},{"place":51,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.6},{"place":52,"model":"midm-2.0-base-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":77.5},{"place":53,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":77.25},{"place":54,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":77.25},{"place":55,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77.2},{"place":56,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":77.2},{"place":57,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":77.2},{"place":58,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":77.2},{"place":59,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":77},{"place":60,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77},{"place":61,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":76.72},{"place":62,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":76.2},{"place":63,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":76.2},{"place":64,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":75.7},{"place":65,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":75.7},{"place":66,"model":"gpt-oss-20b-moe","company":"openai","family":"GPT","version":"GPT-OSS","score":75.6},{"place":67,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":75.6},{"place":68,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":75.47},{"place":69,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.4},{"place":70,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":75.4},{"place":71,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":75.13},{"place":72,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.13},{"place":73,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":75.1},{"place":74,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.1},{"place":75,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":74.6},{"place":76,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":74.6},{"place":77,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":74.6},{"place":78,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74.6},{"place":79,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.5},{"place":80,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74.3},{"place":81,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74.3},{"place":82,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":74.1},{"place":83,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":74.1},{"place":84,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":74.1},{"place":85,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":74.07},{"place":86,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.07},{"place":87,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":74.07},{"place":88,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":74.07},{"place":89,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":73.81},{"place":90,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":73.81},{"place":91,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":73.81},{"place":92,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":73.81},{"place":93,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73.8},{"place":94,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.8},{"place":95,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":73.54},{"place":96,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":73.5},{"place":97,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.4},{"place":98,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":73.3},{"place":99,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":73.3},{"place":100,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":73.3},{"place":101,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":73.3},{"place":102,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":73.3},{"place":103,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":73.28},{"place":104,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":73.02},{"place":105,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":73},{"place":106,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":72.8},{"place":107,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":72.8},{"place":108,"model":"stable-diffcoder-8b-instruct","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":72.8},{"place":109,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.8},{"place":110,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":72.69},{"place":111,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":72.5},{"place":112,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":72.5},{"place":113,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":72.4},{"place":114,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":72.22},{"place":115,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":72.2},{"place":116,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":72.2},{"place":117,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.2},{"place":118,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":72.2},{"place":119,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":72.2},{"place":120,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":72.2},{"place":121,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":72.2},{"place":122,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":72},{"place":123,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":72},{"place":124,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.96},{"place":125,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":71.96},{"place":126,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.7},{"place":127,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":71.7},{"place":128,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":71.43},{"place":129,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":71.4},{"place":130,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":71.4},{"place":131,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":71.4},{"place":132,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.2},{"place":133,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":71},{"place":134,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":70.9},{"place":135,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":70.9},{"place":136,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":70.7},{"place":137,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":70.6},{"place":138,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.6},{"place":139,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":70.6},{"place":140,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.6},{"place":141,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":70.6},{"place":142,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":70.4},{"place":143,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":70.1},{"place":144,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":70.1},{"place":145,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":69.8},{"place":146,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":69.8},{"place":147,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.8},{"place":148,"model":"gpt-3.5-turbo-nov-2023","company":"openai","family":"GPT","version":"GPT-3.5","score":69.7},{"place":149,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":69.7},{"place":150,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":69.7},{"place":151,"model":"artigenz-coder-ds-6.7b","company":"artigenz","family":"Artigenz-Coder-DS-6.7B","version":"Artigenz Coder DS","score":69.6},{"place":152,"model":"claude-3-sonnet-mar-2024","company":"anthropic","family":"claude-3-sonnet","version":"claude-3-sonnet (Mar 2024)","score":69.3},{"place":153,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":69.3},{"place":154,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":69.3},{"place":155,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":69.3},{"place":156,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.2},{"place":157,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":69.1},{"place":158,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":69},{"place":159,"model":"magicoder-s-ds-6.7b","company":"magicoder","family":"Magicoder-S-DS-6.7B","version":"Magicoder-S-DS-6.7B","score":69},{"place":160,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69},{"place":161,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":69},{"place":162,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":69},{"place":163,"model":"claude-3-haiku-mar-2024","company":"anthropic","family":"claude-3-haiku","version":"claude-3-haiku (Mar 2024)","score":68.8},{"place":164,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":68.8},{"place":165,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":68.8},{"place":166,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":68.8},{"place":167,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":68.8},{"place":168,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":68.78},{"place":169,"model":"opencodeinterpreter-ds-33b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":68.5},{"place":170,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":68.5},{"place":171,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":68.3},{"place":172,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.25},{"place":173,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":68.2},{"place":174,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":68.2},{"place":175,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":68},{"place":176,"model":"k2-horizon-0.9b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":68},{"place":177,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.9},{"place":178,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.9},{"place":179,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.7},{"place":180,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.7},{"place":181,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":67.5},{"place":182,"model":"codestral-12b-instruct","company":"mistral","family":"Codestral","version":"Codestral","score":67.5},{"place":183,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":67.5},{"place":184,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":67.46},{"place":185,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.2},{"place":186,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.2},{"place":187,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":67.2},{"place":188,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.93},{"place":189,"model":"whiterabbitneo-33b-v1","company":"whiterabbit","family":"WhiteRabbitNeo-33B-v1","version":"WhiteRabbitNeo-33B-v1","score":66.9},{"place":190,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":66.7},{"place":191,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":66.7},{"place":192,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":66.6},{"place":193,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.6},{"place":194,"model":"opencodeinterpreter-ds-6.7b","company":"map","family":"OpenCodeInterpreter","version":"OpenCodeInterpreter DS","score":66.4},{"place":195,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.3},{"place":196,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.2},{"place":197,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.1},{"place":198,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":66.1},{"place":199,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":66},{"place":200,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":66},{"place":201,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.9},{"place":202,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":65.87},{"place":203,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.82},{"place":204,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":65.7},{"place":205,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":65.7},{"place":206,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":65.6},{"place":207,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":65.6},{"place":208,"model":"grok-beta","company":"xai","family":"Grok","version":"Grok","score":65.6},{"place":209,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":65.2},{"place":210,"model":"starcoder2-15b-instruct-v0.1","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":65.1},{"place":211,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":65.1},{"place":212,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":64.84},{"place":213,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":64.8},{"place":214,"model":"xwincoder-34b","company":"xwin","family":"XwinCoder-34B","version":"XwinCoder-34B","score":64.8},{"place":215,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":64.8},{"place":216,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":64.7},{"place":217,"model":"starchat2-15b-v0.1","company":"huggingface","family":"starchat2-15b-v0.1","version":"starchat2-15b-v0.1","score":64.6},{"place":218,"model":"code-millenials-34b","company":"code","family":"code-millenials-34B","version":"code-millenials-34B","score":64.6},{"place":219,"model":"codellama-70b-instruct","company":"codellama","family":"CodeLlama","version":"CodeLlama","score":64.6},{"place":220,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":64.47},{"place":221,"model":"speechless-coder-ds-6.7b","company":"speechless","family":"speechless-coder-ds-6.7B","version":"speechless-coder-ds-6.7B","score":64.4},{"place":222,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.4},{"place":223,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":64.3},{"place":224,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":64.3},{"place":225,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":64.02},{"place":226,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":64},{"place":227,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":63.9},{"place":228,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":63.7},{"place":229,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":63.6},{"place":230,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":63.5},{"place":231,"model":"wavecoder-ultra-6.7b","company":"wavecoder","family":"WaveCoder-Ultra-6.7B","version":"WaveCoder-Ultra-6.7B","score":63.5},{"place":232,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.5},{"place":233,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":63.5},{"place":234,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":63.5},{"place":235,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":63.47},{"place":236,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":63.4},{"place":237,"model":"wizardcoder-python-34b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":63.2},{"place":238,"model":"coda-1.7b-instruct","company":"salesforce","family":"CoDA","version":"CoDA","score":63.2},{"place":239,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":63.2},{"place":240,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":63.2},{"place":241,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.2},{"place":242,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":63.1},{"place":243,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":63},{"place":244,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63},{"place":245,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.9},{"place":246,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":62.9},{"place":247,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.7},{"place":248,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":62.7},{"place":249,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.6},{"place":250,"model":"speechless-starcoder2-15b","company":"bigcode","family":"speechless-starcoder2-15b","version":"speechless-starcoder2-15b","score":62.4},{"place":251,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.4},{"place":252,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":62.4},{"place":253,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":62.4},{"place":254,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":62.2},{"place":255,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":62.2},{"place":256,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":62.2},{"place":257,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":62.17},{"place":258,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":62},{"place":259,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":61.98},{"place":260,"model":"codestral-22b-v0.1","company":"mistral","family":"Codestral","version":"Codestral v0.1","score":61.9},{"place":261,"model":"diffucoder-7b-instruct","company":"apple","family":"DiffuCoder","version":"DiffuCoder","score":61.9},{"place":262,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":61.64},{"place":263,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":61.6},{"place":264,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":61.5},{"place":265,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":61.4},{"place":266,"model":"speechless-codellama-34b-v2.0","company":"speechless","family":"speechless-codellama-34B-v2.0","version":"speechless-codellama-34B-v2.0","score":61.4},{"place":267,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":61.4},{"place":268,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":61.4},{"place":269,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":61.2},{"place":270,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":61.2},{"place":271,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":61},{"place":272,"model":"midm-2.0-mini-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":60.9},{"place":273,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.85},{"place":274,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":60.85},{"place":275,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":60.8},{"place":276,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":60.7},{"place":277,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":60.6},{"place":278,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":60.6},{"place":279,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":60.2},{"place":280,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":60.2},{"place":281,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":60.2},{"place":282,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.13},{"place":283,"model":"magicoder-s-cl-7b","company":"magicoder","family":"Magicoder-S-CL-7B","version":"Magicoder-S-CL-7B","score":60.1},{"place":284,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":60.1},{"place":285,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":60.05},{"place":286,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":60.05},{"place":287,"model":"exaone-3.5-2.4b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":59.8},{"place":288,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.79},{"place":289,"model":"mistral-large","company":"mistral","family":"Mistral","version":"Mistral","score":59.5},{"place":290,"model":"mistral-large-2402","company":"mistral","family":"Mistral","version":"Mistral","score":59.5},{"place":291,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":59.4},{"place":292,"model":"qwen2.5-coder-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.4},{"place":293,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":59.3},{"place":294,"model":"dolphin-2.6-mixtral-8x7b","company":"mistral","family":"dolphin-2.6-mixtral-8x7b","version":"dolphin-2.6-mixtral-8x7b","score":59},{"place":295,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":58.7},{"place":296,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":58.6},{"place":297,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.5},{"place":298,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":58.4},{"place":299,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":58.1},{"place":300,"model":"yi-coder-1.5b-chat","company":"01ai","family":"Yi","version":"Yi-Coder","score":57.7},{"place":301,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":57.4},{"place":302,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":57.4},{"place":303,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":57.1},{"place":304,"model":"codegemma-7b-it","company":"google","family":"Codegemma","version":"Codegemma","score":56.9},{"place":305,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":56.9},{"place":306,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":56.9},{"place":307,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":56.7},{"place":308,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":56.61},{"place":309,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":56.6},{"place":310,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":56.5},{"place":311,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":56.35},{"place":312,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":56.3},{"place":313,"model":"speechless-starcoder2-7b","company":"bigcode","family":"speechless-starcoder2-7b","version":"speechless-starcoder2-7b","score":56.3},{"place":314,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":56.3},{"place":315,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":56.1},{"place":316,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.08},{"place":317,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":55.9},{"place":318,"model":"databricks-dbrx-instruct","company":"databricks","family":"databricks/dbrx-instruct","version":"databricks/dbrx-instruct","score":55.8},{"place":319,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":55.8},{"place":320,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":55.6},{"place":321,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":55.4},{"place":322,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":55.3},{"place":323,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":55.3},{"place":324,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":55.3},{"place":325,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":55.29},{"place":326,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":55.03},{"place":327,"model":"deepseek-coder-1.3b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":54.8},{"place":328,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":54.8},{"place":329,"model":"openchat-3.5-7b-0106","company":"openchat","family":"OpenChat-3.5-7B-0106","version":"OpenChat-3.5-7B-0106","score":54.5},{"place":330,"model":"wizardcoder-15b-v1.0","company":"microsoft","family":"WizardCoder","version":"WizardCoder V1.0","score":54.2},{"place":331,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":54.2},{"place":332,"model":"phi-2-2.7b","company":"microsoft","family":"phi-2-2.7B","version":"phi-2-2.7B","score":54.2},{"place":333,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.2},{"place":334,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":54.2},{"place":335,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":54},{"place":336,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":53.9},{"place":337,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":53.6},{"place":338,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":53.1},{"place":339,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53},{"place":340,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":52.9},{"place":341,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":52.65},{"place":342,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":52.6},{"place":343,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":52.5},{"place":344,"model":"codegemma-7b","company":"google","family":"Codegemma","version":"codegemma-7b","score":52.4},{"place":345,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":51.9},{"place":346,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":51.6},{"place":347,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":51.6},{"place":348,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":51.6},{"place":349,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":51.1},{"place":350,"model":"codellama-13b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":51.1},{"place":351,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":50.79},{"place":352,"model":"speechless-coding-7b-16k-tora","company":"speechless","family":"speechless-coding-7B-16k-tora","version":"speechless-coding-7B-16k-tora","score":50.6},{"place":353,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":50.6},{"place":354,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":50.53},{"place":355,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":50.5},{"place":356,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":50},{"place":357,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50},{"place":358,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.74},{"place":359,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":49.7},{"place":360,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.6},{"place":361,"model":"wizardcoder-python-7b-v1.0","company":"microsoft","family":"WizardCoder-Python-7B-V1.0","version":"WizardCoder-Python-7B-V1.0","score":49.5},{"place":362,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":49.4},{"place":363,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":49.2},{"place":364,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":49.1},{"place":365,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":49.07},{"place":366,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":49},{"place":367,"model":"speechless-code-mistral-7b-v1.0","company":"speechless","family":"speechless-code-mistral-7B-v1.0","version":"speechless-code-mistral-7B-v1.0","score":48.7},{"place":368,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":47.9},{"place":369,"model":"codet5-16b","company":"salesforce","family":"CodeT5+-16B","version":"CodeT5+-16B","score":47.1},{"place":370,"model":"codet5plus-16b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":47.1},{"place":371,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":47.1},{"place":372,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.08},{"place":373,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":46.9},{"place":374,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":46.9},{"place":375,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.83},{"place":376,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":46.8},{"place":377,"model":"codegemma-2b","company":"google","family":"Codegemma","version":"codegemma-2b","score":46.6},{"place":378,"model":"mistralhermes-codepro-7b-v1","company":"mistral","family":"MistralHermes","version":"MistralHermes CodePro v1","score":46.4},{"place":379,"model":"starcoder-15b","company":"bigcode","family":"StarCoder-15B","version":"StarCoder","score":46.1},{"place":380,"model":"coda-1.7b-base","company":"salesforce","family":"CoDA","version":"CoDA","score":46},{"place":381,"model":"openhermes-2.5-code-290k-13b","company":"openhermes","family":"OpenHermes-2.5-Code-290k-13B","version":"OpenHermes-2.5-Code-290k-13B","score":45.8},{"place":382,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":45.8},{"place":383,"model":"stablecode-3b","company":"stability","family":"StableCode","version":"StableCode","score":45.8},{"place":384,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":45.7},{"place":385,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":45.6},{"place":386,"model":"codegen-16b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":45.5},{"place":387,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":45},{"place":388,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":44.9},{"place":389,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":44.7},{"place":390,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":44.4},{"place":391,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":44.4},{"place":392,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":44.4},{"place":393,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":44.2},{"place":394,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.8},{"place":395,"model":"qwen2.5-coder-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":43.7},{"place":396,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":43.6},{"place":397,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":43.4},{"place":398,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":43.4},{"place":399,"model":"codegen-6b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":42.9},{"place":400,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":42.5},{"place":401,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":42.1},{"place":402,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":42.1},{"place":403,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":41.6},{"place":404,"model":"codet5-6b","company":"salesforce","family":"CodeT5+-6B","version":"CodeT5+-6B","score":41.5},{"place":405,"model":"codet5plus-6b","company":"salesforce","family":"Codet5plus","version":"Codet5plus","score":41.5},{"place":406,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":41.48},{"place":407,"model":"xdan-l1-chat-rl-v1-7b","company":"xdan","family":"xDAN-L1-Chat-RL-v1-7B","version":"xDAN-L1-Chat-RL-v1-7B","score":41.3},{"place":408,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":41.3},{"place":409,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":40.9},{"place":410,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":40.7},{"place":411,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":39.7},{"place":412,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39.68},{"place":413,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":38.9},{"place":414,"model":"codet5-2b","company":"salesforce","family":"CodeT5+-2B","version":"CodeT5+-2B","score":38.1},{"place":415,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":38.1},{"place":416,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.8},{"place":417,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":37.6},{"place":418,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37.6},{"place":419,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":37},{"place":420,"model":"gemma-7b-it","company":"google","family":"Gemma","version":"Gemma","score":36.8},{"place":421,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":36.2},{"place":422,"model":"codegen-2b","company":"salesforce","family":"CodeGen","version":"CodeGen","score":36},{"place":423,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":36},{"place":424,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.4},{"place":425,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":34.7},{"place":426,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":34.58},{"place":427,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":34.1},{"place":428,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":33.8},{"place":429,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":33.6},{"place":430,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":33.3},{"place":431,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":33.07},{"place":432,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":32.8},{"place":433,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":32.4},{"place":434,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":32.4},{"place":435,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":32.1},{"place":436,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":31.1},{"place":437,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":31},{"place":438,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.21},{"place":439,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":29.9},{"place":440,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":29.37},{"place":441,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":29.1},{"place":442,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":28.6},{"place":443,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":27.6},{"place":444,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":25.7},{"place":445,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":23.5},{"place":446,"model":"gemma-1.1-2b-it","company":"google","family":"gemma-1.1-2b-it","version":"gemma-1.1","score":23.3},{"place":447,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":22.8},{"place":448,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":22.8},{"place":449,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":21.2},{"place":450,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":20.4},{"place":451,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":18.5},{"place":452,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":17.2},{"place":453,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":16.7},{"place":454,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":13.2},{"place":455,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":11.1},{"place":456,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":10.1},{"place":457,"model":"zyte-1b","company":"zysecai","family":"Zyte","version":"Zyte","score":7.5}]},{"id":"mcp-atlas","name":"MCP-Atlas","topic":"Agent evaluation","description":"Aggregate MCP agent benchmark covering tool-use and planning tasks.","url":"","leaderboard":"https://scale.com/leaderboard/mcp_atlas","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Spark 1.2","top_percent":90.3,"top_model_id":"muse-spark-1.2","top_generation":"Muse Spark","top_model_base":"Muse Spark 1.2","top_model_family":"Muse","top_company":"meta","top_open_source":0,"lower_is_better":false,"bench_models":130,"total_models":3854,"placements":[{"place":1,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":90.3},{"place":2,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":89.2},{"place":3,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":88.1},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85.8},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85.7},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84.7},{"place":7,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.5},{"place":8,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":84.2},{"place":9,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":84.2},{"place":10,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":83.8},{"place":11,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":83.7},{"place":12,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":83.6},{"place":13,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.6},{"place":14,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":83.6},{"place":15,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.3},{"place":16,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":83},{"place":17,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":82.8},{"place":18,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":82.6},{"place":19,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.5},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":82.5},{"place":21,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":82.3},{"place":22,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":82.2},{"place":23,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":82.2},{"place":24,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":82.2},{"place":25,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.9},{"place":26,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":81.9},{"place":27,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":81.8},{"place":28,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":81.8},{"place":29,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.6},{"place":30,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":81.3},{"place":31,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":81},{"place":32,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":80.8},{"place":33,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.3},{"place":34,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":80},{"place":35,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":79.4},{"place":36,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":79.2},{"place":37,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":79.1},{"place":38,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":79.1},{"place":39,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":78.7},{"place":40,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":78.2},{"place":41,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":77.8},{"place":42,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":77.8},{"place":43,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":77.3},{"place":44,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":77},{"place":45,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":76.8},{"place":46,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":76.8},{"place":47,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":76.4},{"place":48,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":76.4},{"place":49,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":76},{"place":50,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":76},{"place":51,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.8},{"place":52,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":75.5},{"place":53,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":75.3},{"place":54,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":75},{"place":55,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":75},{"place":56,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.6},{"place":57,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":74.6},{"place":58,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":74.2},{"place":59,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.2},{"place":60,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.2},{"place":61,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.1},{"place":62,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":74.1},{"place":63,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":74.1},{"place":64,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":73.9},{"place":65,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.8},{"place":66,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.6},{"place":67,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.6},{"place":68,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":73.2},{"place":69,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.2},{"place":70,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.3},{"place":71,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":71.8},{"place":72,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.8},{"place":73,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":70.6},{"place":74,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":70.2},{"place":75,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":69.8},{"place":76,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":69.5},{"place":77,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.4},{"place":78,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":69.4},{"place":79,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":69.2},{"place":80,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":69.2},{"place":81,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69},{"place":82,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":69},{"place":83,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.4},{"place":84,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":68.1},{"place":85,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":68.1},{"place":86,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67.4},{"place":87,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":67.2},{"place":88,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66.7},{"place":89,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":66.6},{"place":90,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":66.1},{"place":91,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":65.5},{"place":92,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":64.4},{"place":93,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64},{"place":94,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":64},{"place":95,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":63.9},{"place":96,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.8},{"place":97,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":63.3},{"place":98,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63.1},{"place":99,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62.8},{"place":100,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62.5},{"place":101,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.4},{"place":102,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":62.4},{"place":103,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.3},{"place":104,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.3},{"place":105,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.2},{"place":106,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":62},{"place":107,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":61.4},{"place":108,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":61.3},{"place":109,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":61.3},{"place":110,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":61.2},{"place":111,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":60.6},{"place":112,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":60.6},{"place":113,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":60.6},{"place":114,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":59.8},{"place":115,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.5},{"place":116,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.5},{"place":117,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":58.9},{"place":118,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":58.2},{"place":119,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":58.2},{"place":120,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":57.8},{"place":121,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":57.7},{"place":122,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":57.4},{"place":123,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.2},{"place":124,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":56.7},{"place":125,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":56.1},{"place":126,"model":"nemotron-3.5-bolt-74b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":55.6},{"place":127,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":55.2},{"place":128,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":55.2},{"place":129,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55},{"place":130,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":54.6},{"place":131,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.2},{"place":132,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":54.2},{"place":133,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":54.1},{"place":134,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":54.1},{"place":135,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":54.1},{"place":136,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":53.6},{"place":137,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":52.6},{"place":138,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":51.2},{"place":139,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50},{"place":140,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":49.4},{"place":141,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":49.4},{"place":142,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":49.4},{"place":143,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":48.8},{"place":144,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":48.8},{"place":145,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":47.9},{"place":146,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":47.6},{"place":147,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.4},{"place":148,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.8},{"place":149,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":46.4},{"place":150,"model":"llada2.2-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":46.21},{"place":151,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":45.6},{"place":152,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":44.7},{"place":153,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":44.5},{"place":154,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":44.5},{"place":155,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.8},{"place":156,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.8},{"place":157,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.8},{"place":158,"model":"o3-pro-2025-06-10-high","company":"openai","family":"o3","version":"o3","score":43.6},{"place":159,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":41.12},{"place":160,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":40.9},{"place":161,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":40.9},{"place":162,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.8},{"place":163,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":40.2},{"place":164,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":35.6},{"place":165,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":34.4},{"place":166,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":34},{"place":167,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":30.7},{"place":168,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.5},{"place":169,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":27.2},{"place":170,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":24.6},{"place":171,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":23.9},{"place":172,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":23.4},{"place":173,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":22.2},{"place":174,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15},{"place":175,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.8},{"place":176,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":12.6},{"place":177,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":12},{"place":178,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":8.8},{"place":179,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":8.8},{"place":180,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":7.2},{"place":181,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.4},{"place":182,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.4},{"place":183,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":0.8}]},{"id":"mcp-universe","name":"MCP Universe","topic":"Agent evaluation","description":"Benchmarks multi-step tool-use agents across diverse task suites with a unified overall success metric.","url":"https://mcp-universe.github.io/","leaderboard":"https://mcp-universe.github.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":50.7,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":39,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":50.7},{"place":2,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":47.9},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":46.5},{"place":4,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":45.9},{"place":5,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":44.59},{"place":6,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":44.16},{"place":7,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":43.72},{"place":8,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":40.69},{"place":9,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":35.6},{"place":10,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":35.06},{"place":11,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":33.33},{"place":12,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":32.9},{"place":13,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":32.47},{"place":14,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":31.6},{"place":15,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":31.6},{"place":16,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":31.17},{"place":17,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":30.3},{"place":18,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":29.44},{"place":19,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":29.44},{"place":20,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":29.4},{"place":21,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":28.14},{"place":22,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":27.27},{"place":23,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":26.41},{"place":24,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":26.41},{"place":25,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":26.41},{"place":26,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":26.41},{"place":27,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":25.97},{"place":28,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":25.97},{"place":29,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":24.68},{"place":30,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":24.24},{"place":31,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":24.24},{"place":32,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":22.94},{"place":33,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":22.08},{"place":34,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":22.08},{"place":35,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.65},{"place":36,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":21.65},{"place":37,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":19.91},{"place":38,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":19.91},{"place":39,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":19.91},{"place":40,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":19.48},{"place":41,"model":"kimi-k2-instruct-0711","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":19.05},{"place":42,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":18.18},{"place":43,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":18.18},{"place":44,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":18.18},{"place":45,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":15.58},{"place":46,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":14.29}]},{"id":"mcpmark","name":"MCPMark","topic":"Agent tool-use (MCP)","description":"Benchmark for Model Context Protocol (MCP) agent tool-use.","url":"https://mcpmark.ai/","leaderboard":"https://mcpmark.ai/","github":"https://github.com/eval-sys/mcpmark","paper":"","metric":"percent","stars":"127","top_model":"GPT-5.6 Terra","top_percent":74,"top_model_id":"gpt-5.6-terra","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":93,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":74},{"place":2,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":72.4},{"place":3,"model":"jais-3-mova-36b-a4b","company":"g42","family":"Jais","version":"Jais 3","score":69.3},{"place":4,"model":"jais-3-375b-a23b","company":"g42","family":"Jais","version":"Jais 3","score":68.5},{"place":5,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":67.7},{"place":6,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":66.9},{"place":7,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.9},{"place":8,"model":"jais-3-32b","company":"g42","family":"Jais","version":"Jais 3","score":66.1},{"place":9,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":65.3},{"place":10,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":62.5},{"place":11,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":60.8},{"place":12,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":58.7},{"place":13,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":57.5},{"place":14,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":57.5},{"place":15,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":57.5},{"place":16,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.1},{"place":17,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":56.7},{"place":18,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":55.9},{"place":19,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":55.9},{"place":20,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":53.9},{"place":21,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.8},{"place":22,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":52.6},{"place":23,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":51.6},{"place":24,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":51.2},{"place":25,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":50.9},{"place":26,"model":"gemini-3-pro-low","company":"google","family":"Gemini","version":"Gemini 3","score":50.8},{"place":27,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":49.6},{"place":28,"model":"jais-3-7b","company":"g42","family":"Jais","version":"Jais 3","score":49.6},{"place":29,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":48.8},{"place":30,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.8},{"place":31,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":48.2},{"place":32,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":46.9},{"place":33,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":46.9},{"place":34,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.1},{"place":35,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":45.7},{"place":36,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":44.9},{"place":37,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":43.1},{"place":38,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.3},{"place":39,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":38},{"place":40,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37},{"place":41,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":36.8},{"place":42,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.3},{"place":43,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":33.5},{"place":44,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33.3},{"place":45,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32.1},{"place":46,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":31.7},{"place":47,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.5},{"place":48,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":31.1},{"place":49,"model":"jais-3-3.7b","company":"g42","family":"Jais","version":"Jais 3","score":30.7},{"place":50,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":30.3},{"place":51,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":29.9},{"place":52,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":29.7},{"place":53,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":29.5},{"place":54,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":29.5},{"place":55,"model":"claude-sonnet-4-high","company":"anthropic","family":"Claude","version":"Claude 4","score":28.3},{"place":56,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":28.2},{"place":57,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":28.1},{"place":58,"model":"claude-sonnet-4-low","company":"anthropic","family":"Claude","version":"Claude 4","score":27.4},{"place":59,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":27.4},{"place":60,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27},{"place":61,"model":"o3","company":"openai","family":"o3","version":"o3","score":25.4},{"place":62,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.2},{"place":63,"model":"qwen3-coder-plus","company":"qwen","family":"Qwen","version":"Qwen3","score":24.8},{"place":64,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":24.4},{"place":65,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":24},{"place":66,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":21.9},{"place":67,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":21.9},{"place":68,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":21.3},{"place":69,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":20.5},{"place":70,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":20.4},{"place":71,"model":"kimi-k2-0711-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":19.1},{"place":72,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":18.1},{"place":73,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":17.7},{"place":74,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":17.3},{"place":75,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":17.3},{"place":76,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":16.7},{"place":77,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":16.5},{"place":78,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":15.8},{"place":79,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":15.6},{"place":80,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":14.2},{"place":81,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":14.2},{"place":82,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.4},{"place":83,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12.5},{"place":84,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":12.1},{"place":85,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":9.1},{"place":86,"model":"gpt-5-mini-low","company":"openai","family":"GPT","version":"GPT-5","score":8.3},{"place":87,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":8.1},{"place":88,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":6.3},{"place":89,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":5.1},{"place":90,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":4.7},{"place":91,"model":"gpt-5-nano-low","company":"openai","family":"GPT","version":"GPT-5","score":4.3},{"place":92,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":3.9},{"place":93,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.2},{"place":94,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":2.3},{"place":95,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1.6},{"place":96,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":0.8},{"place":97,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":98,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":99,"model":"allam-7b-instruct-preview","company":"humain","family":"ALLaM","version":"ALLaM","score":0},{"place":100,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":0},{"place":101,"model":"granite-4.0-h-3b-ar","company":"IBM","family":"Granite","version":"Granite 4.0","score":0},{"place":102,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":0}]},{"id":"mcpmark-verified","name":"MCPMark-Verified","topic":"Agent tool-use (MCP)","description":"Human-verified edition of MCPMark covering Notion, GitHub, Filesystem, Postgres and Playwright MCP servers.","url":"https://mcpmark.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":96.06,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":96.06},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":94.5},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":92.91},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":92.91},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":92.9},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":92.9},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87.4},{"place":8,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.61},{"place":9,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":81.89},{"place":10,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":81.1},{"place":11,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":76.4},{"place":12,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":76.38},{"place":13,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":72.83},{"place":14,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":72.8},{"place":15,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":71.65}]},{"id":"mdolly","name":"mDolly","topic":"Instruction following (multilingual)","description":"Multilingual variant of the Dolly instruction-following benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Tiny Aya Global","top_percent":86.9,"top_model_id":"tiny-aya-global","top_generation":"Aya","top_model_base":"Tiny Aya Global","top_model_family":"Aya","top_company":"cohere","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":86.9},{"place":2,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":77.5},{"place":3,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.3},{"place":4,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":61.6}]},{"id":"mdpbench","name":"MDPBench","topic":"Document parsing","description":"Document parsing benchmark (reported in OvisOCR3 release).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OvisOCR3","top_percent":88.8,"top_model_id":"ovisocr3","top_generation":"OvisOCR3","top_model_base":"OvisOCR3","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":88.8},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.4},{"place":3,"model":"monkeyocrv2-b-parsing","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCRv2","score":83.3},{"place":4,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":78.9},{"place":5,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":76.8},{"place":6,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":73},{"place":7,"model":"ovisocr2","company":"alibaba","family":"Ovis","version":"OvisOCR2","score":69},{"place":8,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":67.3},{"place":9,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.6}]},{"id":"measurebench","name":"MeasureBench","topic":"Visual measurement reading","description":"Benchmark of reading measurement instruments (gauges, rulers, meters) from images.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":62.9,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":62.9},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":58.9},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":49.9},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":44.4},{"place":5,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":29.7}]},{"id":"medbullets-op4","name":"Medbullets (4 options)","topic":"Medical QA","description":"USMLE Step 2/3-style clinical questions, 4-option version.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedMO-8B","top_percent":66.5,"top_model_id":"medmo-8b","top_generation":"MedMO","top_model_base":"MedMO","top_model_family":"MedMO","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":66.5},{"place":2,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":65.2},{"place":3,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":62},{"place":4,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":57.5},{"place":5,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":57.4},{"place":6,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":55.1},{"place":7,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":40.5}]},{"id":"medbullets-op5","name":"Medbullets (5 options)","topic":"Medical QA","description":"USMLE Step 2/3-style clinical questions, 5-option version.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedMO-8B","top_percent":60.2,"top_model_id":"medmo-8b","top_generation":"MedMO","top_model_base":"MedMO","top_model_family":"MedMO","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":60.2},{"place":2,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":57.8},{"place":3,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":53.8},{"place":4,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":47.7},{"place":5,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":47.6},{"place":6,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":47},{"place":7,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":37.3}]},{"id":"medchembench-internal","name":"MedChemBench (internal)","topic":"Medicinal chemistry","description":"OpenAI internal eval reported in the GPT-6 Astra announcement: medicinal chemistry tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":49.3,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":49.3},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":48.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":47.4},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":35.5},{"place":5,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":35},{"place":6,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":30.4}]},{"id":"medmcqa","name":"MedMCQA","topic":"Medical exams","description":"Indian medical entrance exam (AIIMS/NEET PG) multiple-choice QA.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-4","top_percent":72.51,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":27,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":72.51},{"place":2,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":70.2},{"place":3,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":65},{"place":4,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":62},{"place":5,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":60.1},{"place":6,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":59.8},{"place":7,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":58.1},{"place":8,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":58},{"place":9,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":56.3},{"place":10,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":56.25},{"place":11,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":55.7},{"place":12,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":51.8},{"place":13,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":45.4},{"place":14,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":42.86},{"place":15,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":42.12},{"place":16,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":41.73},{"place":17,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":41.34},{"place":18,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":40.66},{"place":19,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":39.6},{"place":20,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":39.52},{"place":21,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":37.93},{"place":22,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":35.87},{"place":23,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":33.88},{"place":24,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":31.96},{"place":25,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":31.39},{"place":26,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":30.22},{"place":27,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":27.45}]},{"id":"medqa","name":"MedQA","topic":"Medical exams","description":"US medical licensing exam-style multiple choice questions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OpenEvidence Darwin","top_percent":100,"top_model_id":"openevidence-darwin","top_generation":"OpenEvidence 2026","top_model_base":"OpenEvidence Darwin","top_model_family":"OpenEvidence","top_company":"openevidence","top_open_source":0,"lower_is_better":false,"bench_models":40,"total_models":3854,"placements":[{"place":1,"model":"openevidence-darwin","company":"openevidence","family":"OpenEvidence","version":"OpenEvidence 2026","score":100},{"place":2,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":92.1},{"place":3,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":85.8},{"place":4,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":85.3},{"place":5,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":84.3},{"place":6,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":83.8},{"place":7,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":80.28},{"place":8,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":78.5},{"place":9,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":78.3},{"place":10,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":69.1},{"place":11,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":64.4},{"place":12,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":63.5},{"place":13,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":62.1},{"place":14,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.6},{"place":15,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":55.4},{"place":16,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":53.81},{"place":17,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":53.7},{"place":18,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":53.7},{"place":19,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":53},{"place":20,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":50.7},{"place":21,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":48.7},{"place":22,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":47.6},{"place":23,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":47.3},{"place":24,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":43.8},{"place":25,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":43},{"place":26,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":41.8},{"place":27,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":40.38},{"place":28,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":35.04},{"place":29,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":34.8},{"place":30,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":32.99},{"place":31,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":32.68},{"place":32,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":29.07},{"place":33,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":28.83},{"place":34,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":27.49},{"place":35,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":27.49},{"place":36,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":27.42},{"place":37,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":26.24},{"place":38,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":24.12},{"place":39,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":21.29},{"place":40,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":16.97}]},{"id":"medqa-mcmle","name":"MedQA (MCMLE)","topic":"Medical QA (Chinese)","description":"MedQA Mainland China Medical Licensing Exam subset (5 options).","url":"https://github.com/jind11/MedQA","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2009.13081","metric":"percent","stars":"","top_model":"GPT-4","top_percent":74.58,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":74.58},{"place":2,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":61.62},{"place":3,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":58.76},{"place":4,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54.93},{"place":5,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":52.92},{"place":6,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":45.53},{"place":7,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":43.67},{"place":8,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":39.46},{"place":9,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":32.66},{"place":10,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":29.74},{"place":11,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":27.67},{"place":12,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":24.78},{"place":13,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":23.38},{"place":14,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":21.72},{"place":15,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":19.79},{"place":16,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":18.07}]},{"id":"medxpertqa-mm","name":"MedXpertQA-MM","topic":"Medical VQA","description":"Multimodal medical expert question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":81.5,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":58,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":81.5},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":81.3},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.7},{"place":4,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":80.4},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.2},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80},{"place":7,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":79.6},{"place":8,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":78.4},{"place":9,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":10,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":77.3},{"place":11,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":77.1},{"place":12,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":76.9},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76},{"place":14,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":73.3},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":71.7},{"place":16,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":71},{"place":17,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70},{"place":18,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":68.7},{"place":19,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":68.1},{"place":20,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.3},{"place":21,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":65.8},{"place":22,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":65.3},{"place":23,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":64.8},{"place":24,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":64.4},{"place":25,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64},{"place":26,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.6},{"place":27,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.4},{"place":28,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.4},{"place":29,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.3},{"place":30,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.1},{"place":31,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":54.7},{"place":32,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54},{"place":33,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.9},{"place":34,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":49},{"place":35,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.7},{"place":36,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.6},{"place":37,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.6},{"place":38,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":44.8},{"place":39,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.9},{"place":40,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":42.9},{"place":41,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":42.1},{"place":42,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.6},{"place":43,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":35.5},{"place":44,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":35.3},{"place":45,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":34.4},{"place":46,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":34.4},{"place":47,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":28.7},{"place":48,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":27},{"place":49,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.9},{"place":50,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":26.9},{"place":51,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":26.8},{"place":52,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":26.7},{"place":53,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.3},{"place":54,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":26.2},{"place":55,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":24.9},{"place":56,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":24.8},{"place":57,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":23.5},{"place":58,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":21.6},{"place":59,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":20.9},{"place":60,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":18.8},{"place":61,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":17.1},{"place":62,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":16.4},{"place":63,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":13}]},{"id":"medxpertqa-text","name":"MedXpertQA (Text)","topic":"Medical QA","description":"Text-only subset of MedXpertQA expert-level medical multiple-choice questions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OpenEvidence Darwin","top_percent":72.8,"top_model_id":"openevidence-darwin","top_generation":"OpenEvidence 2026","top_model_base":"OpenEvidence Darwin","top_model_family":"OpenEvidence","top_company":"openevidence","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"openevidence-darwin","company":"openevidence","family":"OpenEvidence","version":"OpenEvidence 2026","score":72.8},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.5},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":59.6},{"place":4,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":52.6},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":52.1},{"place":6,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":50.2},{"place":7,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":23.7},{"place":8,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":20.9},{"place":9,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":19.9},{"place":10,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":16.5},{"place":11,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":16.4},{"place":12,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":16.4},{"place":13,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":16.4},{"place":14,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":14.4},{"place":15,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":14.2},{"place":16,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":12.1},{"place":17,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":11.6}]},{"id":"membench","name":"MemBench","topic":"Long-term memory","description":"Benchmark of factual and reflective memory of LLM-based agents across participation and observation scenarios.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2506.21605","metric":"percent","stars":"","top_model":"MemT-1.0-Flash","top_percent":73.5,"top_model_id":"memt-1.0-flash","top_generation":"MemT-1.0","top_model_base":"MemT-1.0-Flash","top_model_family":"MemT","top_company":"memtensor","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"memt-1.0-flash","company":"memtensor","family":"MemT","version":"MemT-1.0","score":73.5},{"place":2,"model":"memt-1.0-nano","company":"memtensor","family":"MemT","version":"MemT-1.0","score":71.8}]},{"id":"memoryagentbench","name":"MemoryAgentBench","topic":"Long-term memory","description":"Evaluates memory agents on accurate retrieval, test-time learning, long-range understanding and conflict resolution.","url":"https://github.com/HUST-AI-HYZ/MemoryAgentBench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2507.05257","metric":"percent","stars":"","top_model":"MemT-1.0-Flash","top_percent":17.4,"top_model_id":"memt-1.0-flash","top_generation":"MemT-1.0","top_model_base":"MemT-1.0-Flash","top_model_family":"MemT","top_company":"memtensor","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"memt-1.0-flash","company":"memtensor","family":"MemT","version":"MemT-1.0","score":17.4},{"place":2,"model":"memt-1.0-nano","company":"memtensor","family":"MemT","version":"MemT-1.0","score":15.5}]},{"id":"memorybench","name":"MemoryBench","topic":"Long-term memory","description":"Meta-reported benchmark of remembering and retrieving user context across conversations.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Wonder","top_percent":85.6,"top_model_id":"muse-wonder","top_generation":"Muse Wonder","top_model_base":"Muse Wonder","top_model_family":"Muse","top_company":"meta","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":85.6},{"place":2,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":85.5},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":81.5},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":81.4},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":79}]},{"id":"mentalhealthbench","name":"MentalHealthBench","topic":"Medical","description":"OpenAI MentalHealthBench (overall): quality of responses in mental-health conversations (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":58.7,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":58.7},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":57.9},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":55.5},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":54.2},{"place":5,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":53.93},{"place":6,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":51.73},{"place":7,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":51.7},{"place":8,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":49.38},{"place":9,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":48.81},{"place":10,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":47.53},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.7},{"place":12,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":46.2},{"place":13,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":45.11},{"place":14,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":44.4}]},{"id":"mentalhealthbench-emergent","name":"MentalHealthBench (emergent)","topic":"Medical","description":"OpenAI MentalHealthBench (emergent): quality of responses in mental-health conversations (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":58.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":58.5},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":58},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":54.9},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":54.3},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":52.9},{"place":6,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":52.66},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":51.2},{"place":8,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":51.1},{"place":9,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":49.4},{"place":10,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":48.98},{"place":11,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":47.92},{"place":12,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":44.3},{"place":13,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":44.12},{"place":14,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":44.03}]},{"id":"mentalhealthbench-high-acuity","name":"MentalHealthBench (high acuity)","topic":"Medical","description":"OpenAI MentalHealthBench (high acuity): quality of responses in mental-health conversations (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":59.8,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":59.8},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":59.1},{"place":3,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":58.76},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":56.5},{"place":5,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":56.15},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":55.3},{"place":7,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":54.7},{"place":8,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":53.88},{"place":9,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":53.7},{"place":10,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":52.58},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":51.8},{"place":12,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":51.3},{"place":13,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":50.23},{"place":14,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":48.4}]},{"id":"mentalhealthbench-non-acute","name":"MentalHealthBench (non-acute)","topic":"Medical","description":"OpenAI MentalHealthBench (non-acute): quality of responses in mental-health conversations (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":58.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":58.5},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":57.3},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":56.5},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":53.5},{"place":5,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":52.96},{"place":6,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":51.91},{"place":7,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":51.68},{"place":8,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":49.3},{"place":9,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":47.62},{"place":10,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":47.07},{"place":11,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":43.1},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":42.5},{"place":13,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":41.8},{"place":14,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":40.4}]},{"id":"metr","name":"METR","topic":"Long task benchmark","description":"METR evaluates AI agents on long-horizon coding and agentic tasks, measuring autonomous task completion time.","url":"https://metr.org","leaderboard":"","github":"","paper":"","metric":"hours","stars":"","top_model":"Claude Opus 4.5","top_percent":4.82,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":33,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.82},{"place":2,"model":"gpt-5.1-codex-max","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":2.88},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":2.3},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.03},{"place":5,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1.9},{"place":6,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":1.82},{"place":7,"model":"o3","company":"openai","family":"o3","version":"o3","score":1.57},{"place":8,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1.43},{"place":9,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":1.32},{"place":10,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1.25},{"place":11,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":0.97},{"place":12,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":0.93},{"place":13,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":0.75},{"place":14,"model":"o1","company":"openai","family":"o1","version":"o1","score":0.68},{"place":15,"model":"gemini-2.5-pro-preview","company":"google","family":"Gemini","version":"Gemini 2.5","score":0.67},{"place":16,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0.53},{"place":17,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0.5},{"place":18,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":0.45},{"place":19,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":0.38},{"place":20,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":0.37},{"place":21,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0.32},{"place":22,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":0.3},{"place":23,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":0.15},{"place":24,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0.15},{"place":25,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":0.12},{"place":26,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":0.1},{"place":27,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":0.08},{"place":28,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.08},{"place":29,"model":"gpt-4-0125-preview","company":"openai","family":"GPT","version":"GPT-4","score":0.08},{"place":30,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":0.03},{"place":31,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":0.02},{"place":32,"model":"gpt-2","company":"openai","family":"GPT","version":"GPT-2","score":0},{"place":33,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":0}]},{"id":"mewc","name":"MEWC","topic":"Web comprehension","description":"Multi-page End-to-end Web Comprehension benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":89.8,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.8},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82.1},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78.7},{"place":4,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":74.4},{"place":5,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":55.6},{"place":6,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":41.3}]},{"id":"mgsm","name":"MGSM","topic":"Math (multilingual)","description":"Multilingual grade school math word problems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.1 (2025-08-05) Thinking","top_percent":94.4,"top_model_id":"claude-opus-4-1-20250805-thinking","top_generation":"Claude 4.1","top_model_base":"Claude Opus 4.1","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":154,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4-1-20250805-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":94.4},{"place":2,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":94.2},{"place":3,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":93.8},{"place":4,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":93.4},{"place":5,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":93},{"place":6,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":93},{"place":7,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":92.8},{"place":8,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":92.6},{"place":9,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":92.6},{"place":10,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":92.5},{"place":11,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":92.4},{"place":12,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":92.4},{"place":13,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":92.4},{"place":14,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":92.3},{"place":15,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":92.3},{"place":16,"model":"llama-4-maverick-17b-128e-base","company":"meta","family":"Llama","version":"Llama 4","score":92.3},{"place":17,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":92.3},{"place":18,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.2},{"place":19,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":92.1},{"place":20,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":92},{"place":21,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":92},{"place":22,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":92},{"place":23,"model":"o3","company":"openai","family":"o3","version":"o3","score":91.7},{"place":24,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":91.7},{"place":25,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":91.69},{"place":26,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":91.64},{"place":27,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":91.6},{"place":28,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":91.3},{"place":29,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":91.3},{"place":30,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":91.1},{"place":31,"model":"llama-3.3-instruct-turbo-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":91.1},{"place":32,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":91},{"place":33,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":90.9},{"place":34,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":90.9},{"place":35,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":90.9},{"place":36,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":90.9},{"place":37,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":90.9},{"place":38,"model":"o1","company":"openai","family":"o1","version":"o1","score":90.8},{"place":39,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":90.8},{"place":40,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":90.7},{"place":41,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":90.7},{"place":42,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":90.6},{"place":43,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":90.6},{"place":44,"model":"llama-4-scout-17b-16e-base","company":"meta","family":"Llama","version":"Llama 4","score":90.6},{"place":45,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":90.53},{"place":46,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":90.5},{"place":47,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":90.5},{"place":48,"model":"grok-3-mini-fast-high-reasoning","company":"xai","family":"Grok","version":"Grok 3","score":90.4},{"place":49,"model":"grok-3-mini-fast-low-reasoning","company":"xai","family":"Grok","version":"Grok 3","score":90.4},{"place":50,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":90.4},{"place":51,"model":"gemini-2.5-flash-preview-05-20-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":90},{"place":52,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.8},{"place":53,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":89.6},{"place":54,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":89.58},{"place":55,"model":"o1","company":"openai","family":"o1","version":"o1","score":89.3},{"place":56,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":89.3},{"place":57,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":89.2},{"place":58,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":89.01},{"place":59,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":89},{"place":60,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":89},{"place":61,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":88.9},{"place":62,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":88.5},{"place":63,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":88.44},{"place":64,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.16},{"place":65,"model":"llama-4-scout","company":"meta","family":"Llama","version":"Llama 1","score":88},{"place":66,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":87.8},{"place":67,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87.73},{"place":68,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":87.7},{"place":69,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":87.53},{"place":70,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":87.5},{"place":71,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87.47},{"place":72,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":87.4},{"place":73,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":87.4},{"place":74,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":87.36},{"place":75,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":87.28},{"place":76,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":87.2},{"place":77,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.15},{"place":78,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":87},{"place":79,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":87},{"place":80,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":86.9},{"place":81,"model":"llama-3.2-90b-vision","company":"meta","family":"Llama","version":"Llama 3.2","score":86.9},{"place":82,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":86.6},{"place":83,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":86.6},{"place":84,"model":"llama-3.3-nemotron-super-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron Super","score":86.4},{"place":85,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":86.2},{"place":86,"model":"grok-2","company":"xai","family":"Grok","version":"Grok 2","score":86.1},{"place":87,"model":"command-a","company":"cohere","family":"Command","version":"Command","score":85.7},{"place":88,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.7},{"place":89,"model":"claude-3.5-haiku","company":"anthropic","family":"Claude","version":"Claude 3.5","score":85.6},{"place":90,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":85.6},{"place":91,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85.2},{"place":92,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":84.6},{"place":93,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84.4},{"place":94,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.4},{"place":95,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":84.2},{"place":96,"model":"mistral-small-1.0","company":"mistral","family":"Mistral Small","version":"Mistral Small","score":84},{"place":97,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":84},{"place":98,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83},{"place":99,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":82.93},{"place":100,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":82.73},{"place":101,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":82.72},{"place":102,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":82.33},{"place":103,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":82.32},{"place":104,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.27},{"place":105,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.76},{"place":106,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":81.3},{"place":107,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":81.27},{"place":108,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":80.8},{"place":109,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":80.4},{"place":110,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":80.33},{"place":111,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":80.2},{"place":112,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":79.8},{"place":113,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":79.18},{"place":114,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":78.37},{"place":115,"model":"jamba-1.5-large","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":77.4},{"place":116,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":76.5},{"place":117,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.2},{"place":118,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":76.07},{"place":119,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":75.7},{"place":120,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":74.32},{"place":121,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":74},{"place":122,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":73.68},{"place":123,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":73.31},{"place":124,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":72.73},{"place":125,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":72.4},{"place":126,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":71.7},{"place":127,"model":"jamba-1.6-large","company":"ai21","family":"Jamba","version":"Jamba 1.6","score":71.2},{"place":128,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":71.12},{"place":129,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":70},{"place":130,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":69.9},{"place":131,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":69.3},{"place":132,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":68.9},{"place":133,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":68.72},{"place":134,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":68.7},{"place":135,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":67.8},{"place":136,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.6},{"place":137,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.56},{"place":138,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.11},{"place":139,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.05},{"place":140,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":65.3},{"place":141,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":65},{"place":142,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.6},{"place":143,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":63.6},{"place":144,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":63.5},{"place":145,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":61.68},{"place":146,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":57},{"place":147,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":56.5},{"place":148,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":56.13},{"place":149,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":55.3},{"place":150,"model":"lfm2-1.2b","company":"liquidai","family":"LFM","version":"LFM2","score":55.04},{"place":151,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":54.75},{"place":152,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":54},{"place":153,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":47},{"place":154,"model":"lfm2-700m","company":"liquidai","family":"LFM","version":"LFM2","score":45.36},{"place":155,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":43.6},{"place":156,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":42.1},{"place":157,"model":"jamba-mini-1.6","company":"ai21","family":"Jamba","version":"Jamba Mini","score":41.7},{"place":158,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":41.28},{"place":159,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":38.72},{"place":160,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":37},{"place":161,"model":"jamba-1.5-mini","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":29.6},{"place":162,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":29.52},{"place":163,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":29.12},{"place":164,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":28.76},{"place":165,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":28.64},{"place":166,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":28.56},{"place":167,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":8.9},{"place":168,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":1.8}]},{"id":"mhpp","name":"MHPP","topic":"Code generation","description":"Mostly Hard Python Problems: 210 hand-written function-level Python problems probing harder code-generation skills; pass@1.","url":"https://github.com/SparksofAGI/MHPP","leaderboard":"","github":"https://github.com/SparksofAGI/MHPP","paper":"https://arxiv.org/abs/2405.11430","metric":"percent","stars":"","top_model":"Stable-DiffCoder-8B-Instruct","top_percent":42.4,"top_model_id":"stable-diffcoder-8b-instruct","top_generation":"Stable-DiffCoder","top_model_base":"Stable-DiffCoder 8B","top_model_family":"Seed","top_company":"bytedance","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"stable-diffcoder-8b-instruct","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":42.4},{"place":2,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":36.2},{"place":3,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":32.8},{"place":4,"model":"opencoder-8b-instruct","company":"map","family":"OpenCoder","version":"OpenCoder","score":30.5},{"place":5,"model":"yi-coder-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":26.7},{"place":6,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.7},{"place":7,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":20},{"place":8,"model":"codeqwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":17.6},{"place":9,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":17.1},{"place":10,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":6.7}]},{"id":"miabench","name":"MIABench","topic":"Multimodal instruction following","description":"Multimodal instruction-following benchmark evaluating accuracy on complex image-text tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":96,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":96},{"place":2,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":95.1},{"place":3,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":94.8},{"place":4,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":94.1},{"place":5,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":93.36},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.7},{"place":7,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":92.4},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.3},{"place":9,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":92.3},{"place":10,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":92.3},{"place":11,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":92.27},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.25},{"place":13,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.8},{"place":14,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.6},{"place":15,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":91.2},{"place":16,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.2},{"place":17,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.1},{"place":18,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":90.7},{"place":19,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.5},{"place":20,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.7},{"place":21,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":89.6},{"place":22,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":89.4},{"place":23,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":88.76},{"place":24,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":85.25},{"place":25,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":84.02},{"place":26,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.6}]},{"id":"microvqa","name":"MicroVQA","topic":"Biological microscopy","description":"Visual question answering benchmark for biological microscopy images.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":71.02,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.02},{"place":2,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":69.67},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":69},{"place":4,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":68.81},{"place":5,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.71},{"place":6,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":66.22},{"place":7,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":63.92},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":63.63},{"place":9,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.63},{"place":10,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":63.34},{"place":11,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":63.34},{"place":12,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":63.3},{"place":13,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":61.8},{"place":14,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":61.04},{"place":15,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":60.4},{"place":16,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":55.4},{"place":17,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.8},{"place":18,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.17},{"place":19,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":51.73}]},{"id":"milu","name":"MILU","topic":"Indic languages","description":"Multi-task Indic Language Understanding benchmark (11 Indian languages + English), accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":85.29,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.29},{"place":2,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.65},{"place":3,"model":"gnani-evon-v3.3-30b-a3b","company":"gnani","family":"gnani-evon","version":"gnani-evon-v3.3","score":78.74},{"place":4,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":75.71},{"place":5,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":67.15}]},{"id":"mimic-cxr","name":"MIMIC-CXR (classification)","topic":"Medical imaging","description":"Chest X-ray condition classification on MIMIC-CXR, macro F1 over top conditions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedGemma 27B","top_percent":90,"top_model_id":"medgemma-27b-it","top_generation":"MedGemma 1","top_model_base":"MedGemma","top_model_family":"MedGemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":90},{"place":2,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":89.5},{"place":3,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":88.9},{"place":4,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":81.2}]},{"id":"mimo-niah-multi-128k","name":"NIAH-Multi 128K","topic":"Long-context QA","description":"Needle-in-a-haystack multi-query benchmark at 128K context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2 Base","top_percent":99.5,"top_model_id":"kimi-k2-base","top_generation":"Kimi K2","top_model_base":"Kimi K2 Base","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":99.5},{"place":2,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":98.6},{"place":3,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":97.2},{"place":4,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":94.3}]},{"id":"mimo-niah-multi-32k","name":"NIAH-Multi 32K","topic":"Long-context QA","description":"Needle-in-a-haystack multi-query benchmark at 32K context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2 Base","top_percent":99.8,"top_model_id":"kimi-k2-base","top_generation":"Kimi K2","top_model_base":"Kimi K2 Base","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":99.8},{"place":2,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":99.7},{"place":3,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":99.3},{"place":4,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.6}]},{"id":"mimo-niah-multi-64k","name":"NIAH-Multi 64K","topic":"Long-context QA","description":"Needle-in-a-haystack multi-query benchmark at 64K context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2 Base","top_percent":100,"top_model_id":"kimi-k2-base","top_generation":"Kimi K2","top_model_base":"Kimi K2 Base","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":100},{"place":2,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":99.9},{"place":3,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":98.6},{"place":4,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.9}]},{"id":"mindcube","name":"MindCube","topic":"Spatial navigation","description":"Spatial navigation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ACE-Brain-0.5-8B","top_percent":94.2,"top_model_id":"ace-brain-0.5-8b","top_generation":"ACE-Brain-0.5","top_model_base":"ACE-Brain-0.5 8B","top_model_family":"ACE-Brain","top_company":"unknown","top_open_source":1,"lower_is_better":false,"bench_models":51,"total_models":3854,"placements":[{"place":1,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":94.2},{"place":2,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":86.2},{"place":3,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":82.1},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":78.8},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":78.3},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77.3},{"place":7,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":77.1},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.8},{"place":9,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":70},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":66.7},{"place":11,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":66.3},{"place":12,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":65.4},{"place":13,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":64.7},{"place":14,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":63.4},{"place":15,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":62},{"place":16,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":61.7},{"place":17,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.2},{"place":18,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":61.1},{"place":19,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":60.9},{"place":20,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.6},{"place":21,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.2},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.3},{"place":23,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":58},{"place":24,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":57},{"place":25,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":56.6},{"place":26,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":55.6},{"place":27,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":55},{"place":28,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":54.7},{"place":29,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":54.2},{"place":30,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":53},{"place":31,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":52.7},{"place":32,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.4},{"place":33,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":50.1},{"place":34,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.2},{"place":35,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":47.7},{"place":36,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":45.6},{"place":37,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":43.9},{"place":38,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":43.1},{"place":39,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":42.6},{"place":40,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":40.3},{"place":41,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":39.7},{"place":42,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":39.2},{"place":43,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":39},{"place":44,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":38.9},{"place":45,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":38},{"place":46,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":37.6},{"place":47,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":36.2},{"place":48,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36},{"place":49,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":33.9},{"place":50,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":33.7},{"place":51,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":33.4},{"place":52,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":32.5},{"place":53,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":31.3},{"place":54,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":31},{"place":55,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":30.9},{"place":56,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":30.4},{"place":57,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":29.2},{"place":58,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.4},{"place":59,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":27.4},{"place":60,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":26.9}]},{"id":"mindcube-tiny","name":"MindCube-Tiny","topic":"Spatial reasoning","description":"Tiny evaluation subset of MindCube spatial mental-model benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ZDTaichu5.0-9B","top_percent":78.27,"top_model_id":"zdtaichu5.0-9b","top_generation":"ZDTaichu5.0","top_model_base":"ZDTaichu5.0 9B","top_model_family":"ZDTaichu","top_company":"taichu","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":78.27},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.87},{"place":3,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":63.56},{"place":4,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":62.81},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":60.38},{"place":6,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.6},{"place":7,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.85}]},{"id":"minerva-math","name":"Minerva Math","topic":"University-level math","description":"Advanced quantitative reasoning set inspired by the Minerva benchmark for STEM problem solving.","url":"https://github.com/allenai/minerva-math","leaderboard":"","github":"https://github.com/allenai/minerva-math","paper":"https://arxiv.org/abs/2206.14858","metric":"percent","stars":"","top_model":"Qwen3 235B A22B Thinking","top_percent":98,"top_model_id":"qwen-3-235b-a22b-thinking","top_generation":"Qwen3","top_model_base":"Qwen3 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":67,"total_models":3854,"placements":[{"place":1,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":98},{"place":2,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":97.3},{"place":3,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":96.9},{"place":4,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":94.9},{"place":5,"model":"k2-high-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":94.5},{"place":6,"model":"k2-medium-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":90.6},{"place":7,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":87.66},{"place":8,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":85.3},{"place":9,"model":"k2-low-70b","company":"mbzuai","family":"K2","version":"K2 V2","score":85},{"place":10,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.84},{"place":11,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":82.78},{"place":12,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.64},{"place":13,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.1},{"place":14,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":81.32},{"place":15,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":80.1},{"place":16,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":80.1},{"place":17,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.8},{"place":18,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":77.8},{"place":19,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":74},{"place":20,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":67.94},{"place":21,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.6},{"place":22,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65},{"place":23,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":64.06},{"place":24,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":63.32},{"place":25,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":62.4},{"place":26,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":62.06},{"place":27,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.66},{"place":28,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.6},{"place":29,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":54.37},{"place":30,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.99},{"place":31,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":50.09},{"place":32,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":49.9},{"place":33,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.3},{"place":34,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":46.5},{"place":35,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":45.6},{"place":36,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":44.1},{"place":37,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":43.74},{"place":38,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":43},{"place":39,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":43},{"place":40,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":40.2},{"place":41,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":40.1},{"place":42,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":40.1},{"place":43,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":39.6},{"place":44,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":37.1},{"place":45,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":36.8},{"place":46,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.18},{"place":47,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":34.6},{"place":48,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":34.2},{"place":49,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.5},{"place":50,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":31.6},{"place":51,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":29.4},{"place":52,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":29.4},{"place":53,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":29.4},{"place":54,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.21},{"place":55,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":26.1},{"place":56,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":25},{"place":57,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":24.44},{"place":58,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":22.43},{"place":59,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":21.7},{"place":60,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":20.6},{"place":61,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":20.6},{"place":62,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":20.2},{"place":63,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":19.5},{"place":64,"model":"numinamath-7b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":19.1},{"place":65,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":17.3},{"place":66,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":16.9},{"place":67,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":16.2},{"place":68,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":15.6},{"place":69,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":15.2},{"place":70,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":9.4},{"place":71,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":8.7},{"place":72,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":5.5}]},{"id":"minerva-video","name":"Minerva (Video)","topic":"Video reasoning","description":"Minerva video question-answering benchmark with complex multi-step reasoning over videos (not the Minerva math set).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":70.7,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":70.7},{"place":2,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":68.6},{"place":3,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":68.5},{"place":4,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":66.5},{"place":5,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":65.9},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":64.4},{"place":8,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.8},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":63.5},{"place":10,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":54.7}]},{"id":"minif2f-pass1","name":"MiniF2F pass@1","topic":"Math competition","description":"MiniF2F competition benchmark pass@1 accuracy.","url":"https://github.com/deepmind/mathematics_dataset","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","top_percent":50,"top_model_id":"nvidia-nemotron-3-nano-30b-a3b-bf16","top_generation":"Nemotron 3","top_model_base":"Nemotron-3 Nano 30B A3B BF16","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":50},{"place":2,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":12.1},{"place":3,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":5.7}]},{"id":"minif2f-pass32","name":"MiniF2F pass@32","topic":"Math competition","description":"MiniF2F competition benchmark pass@32 accuracy.","url":"https://github.com/deepmind/mathematics_dataset","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LongCat-Flash-Prover","top_percent":93.9,"top_model_id":"longcat-flash-prover","top_generation":"LongCat-Flash","top_model_base":"LongCat-Flash-Prover","top_model_family":"LongCat","top_company":"meituan","top_open_source":1,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":93.9},{"place":2,"model":"goedel-prover-v2-32b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":88.1},{"place":3,"model":"goedel-prover-v2-8b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":84.6},{"place":4,"model":"kimina-prover-72b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":84},{"place":5,"model":"deepseek-prover-v2-671b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":82.4},{"place":6,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.9},{"place":7,"model":"kimina-prover-8b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":78.3},{"place":8,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":77.9},{"place":9,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":76.6},{"place":10,"model":"leanabell-prover-v2-ds","company":"kuaishou","family":"Leanabell-Prover","version":"Leanabell-Prover-V2","score":76.6},{"place":11,"model":"deepseek-prover-v2-7b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":75.6},{"place":12,"model":"leanabell-prover-v2-km","company":"kuaishou","family":"Leanabell-Prover","version":"Leanabell-Prover-V2","score":68.4},{"place":13,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.6},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.2},{"place":15,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":43},{"place":16,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":16.8}]},{"id":"minif2f-test","name":"MiniF2F (Test)","topic":"Math competition","description":"MiniF2F competition benchmark (test split).","url":"https://github.com/deepmind/mathematics_dataset","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Leanstral 1.5","top_percent":100,"top_model_id":"leanstral-1.5","top_generation":"Leanstral 1.5","top_model_base":"Leanstral 1.5","top_model_family":"Leanstral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"leanstral-1.5","company":"mistral","family":"Leanstral","version":"Leanstral 1.5","score":100},{"place":2,"model":"seed-prover","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover","score":99.6},{"place":3,"model":"delta-prover","company":"delta-prover","family":"Delta-Prover","version":"Delta-Prover","score":95.9},{"place":4,"model":"longcat-flash-thinking","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":81.6},{"place":5,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":79.5},{"place":6,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":51.2},{"place":7,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":43.4},{"place":8,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":42.6},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":41.8},{"place":10,"model":"internlm2-math-plus-1.8b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":38.9},{"place":11,"model":"o3","company":"openai","family":"o3","version":"o3","score":37.7},{"place":12,"model":"internlm2-math-plus-mixtral8x22b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":37.3},{"place":13,"model":"internlm2-math-base-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":30.3},{"place":14,"model":"internlm2-math-base-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":29.5},{"place":15,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":28.7},{"place":16,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":28.3},{"place":17,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":27},{"place":18,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":26.6},{"place":19,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":26.2},{"place":20,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":25.8},{"place":21,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":25.4},{"place":22,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":24.6},{"place":23,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":23.4},{"place":24,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":22.1},{"place":25,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":22.1},{"place":26,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":22.1},{"place":27,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":22.1},{"place":28,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":21.3},{"place":29,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":20.5},{"place":30,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":18},{"place":31,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":18},{"place":32,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":17.6}]},{"id":"mirb","name":"MIRB","topic":"Multi-image reasoning","description":"Multi-Image Relational Benchmark (average over perception, visual world knowledge, reasoning, multi-hop).","url":"https://github.com/ys-zong/MIRB","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2406.12742","metric":"percent","stars":"","top_model":"InternVL2.5-38B","top_percent":61.2,"top_model_id":"internvl2.5-38b","top_generation":"InternVL2.5","top_model_base":"InternVL2.5-38B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":61.2},{"place":2,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":61.1},{"place":3,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":58.2},{"place":4,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":56.9},{"place":5,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":55.7},{"place":6,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":55.2},{"place":7,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":53.8},{"place":8,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":53.7},{"place":9,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":53.1},{"place":10,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":53.1},{"place":11,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":52.5},{"place":12,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":51.7},{"place":13,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":50.3},{"place":14,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":50},{"place":15,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":42.5},{"place":16,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":39.9},{"place":17,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":36.4},{"place":18,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":35.6},{"place":19,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.1},{"place":20,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":31.5}]},{"id":"mixcount","name":"MixCount","topic":"Visual counting","description":"MixCount test object counting, exact-match accuracy.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":40.4,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":40.4},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":32.2},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":15.2},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":11.4},{"place":5,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":7}]},{"id":"mixeval","name":"MixEval","topic":"Multi-task reasoning","description":"Mixed-subject benchmark covering knowledge and reasoning tasks across domains.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen2 72B Instruct","top_percent":86.7,"top_model_id":"qwen2-72b-instruct","top_generation":"Qwen2","top_model_base":"Qwen2 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":33,"total_models":3854,"placements":[{"place":1,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":86.7},{"place":2,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":85.7},{"place":3,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":84.1},{"place":4,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":84},{"place":5,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":82.9},{"place":6,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":82.8},{"place":7,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":82.3},{"place":8,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":82.3},{"place":9,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":81.7},{"place":10,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":81},{"place":11,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":80.6},{"place":12,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":77.3},{"place":13,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.05},{"place":14,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":76.5},{"place":15,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76},{"place":16,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":75},{"place":17,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.2},{"place":18,"model":"afm-4.5b","company":"arcee","family":"AFM","version":"AFM","score":73.75},{"place":19,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":72.8},{"place":20,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.9},{"place":21,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":71.4},{"place":22,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":71.2},{"place":23,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.1},{"place":24,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":70.8},{"place":25,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":70},{"place":26,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":67},{"place":27,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":66.9},{"place":28,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.9},{"place":29,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":64.3},{"place":30,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":63.4},{"place":31,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":62.9},{"place":32,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":62.2},{"place":33,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":62.1},{"place":34,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.4},{"place":35,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":37.2}]},{"id":"mixeval-hard","name":"MixEval Hard","topic":"Multi-task reasoning (hard)","description":"Hard subset of MixEval covering diverse reasoning tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-9B","top_percent":50.3,"top_model_id":"qwen3.5-9b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 9B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.3},{"place":2,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":46.4},{"place":3,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":41.6},{"place":4,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.4},{"place":5,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":31.6},{"place":6,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27.6},{"place":7,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":26.9},{"place":8,"model":"llama-3.1-3b","company":"meta","family":"Llama","version":"Llama 3.1","score":24.9},{"place":9,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":24.3}]},{"id":"mle-bench","name":"MLE-Bench","topic":"ML engineering","description":"OpenAI MLE-Bench: Kaggle-style machine-learning engineering competitions solved by agents.","url":"https://github.com/openai/mle-bench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 5","top_percent":66.9,"top_model_id":"claude-sonnet-5","top_generation":"Claude 5","top_model_base":"Claude Sonnet 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":66.9},{"place":2,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":63.9},{"place":3,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":49.7},{"place":4,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":47.6},{"place":5,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":43.2},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":42.6},{"place":7,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":39.2},{"place":8,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":22}]},{"id":"mle-bench-30","name":"MLE-bench-30","topic":"ML engineering","description":"30-competition subset of MLE-bench (Kaggle ML engineering tasks); average position score as used in the Gemini 3.6 Flash model card.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Naive-N0.5-Flash","top_percent":73.7,"top_model_id":"naive-n0.5-flash","top_generation":"Naive-N0.5","top_model_base":"Naive-N0.5 Flash","top_model_family":"Naive","top_company":"naiveai","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":73.7},{"place":2,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":66.9},{"place":3,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":63.9},{"place":4,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":49.7},{"place":5,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":47.6},{"place":6,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":43.2}]},{"id":"mle-bench-lite","name":"MLE-Bench Lite","topic":"ML engineering","description":"MLE-Bench Lite: 22-competition low-complexity subset of OpenAI MLE-Bench; metric is medal rate.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":88.9,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":40,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":88.9},{"place":2,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":88.2},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88},{"place":4,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.8},{"place":5,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":86.2},{"place":6,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":85.8},{"place":7,"model":"arex-2","company":"baai","family":"AREX","version":"AREX-2","score":81.8},{"place":8,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.3},{"place":9,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":80.8},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.3},{"place":11,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.7},{"place":12,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":73.7},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":72.73},{"place":14,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":72.7},{"place":15,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":72.7},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":72.7},{"place":17,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":72.7},{"place":18,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":72.7},{"place":19,"model":"frontis-ma1-35b","company":"frontis","family":"Frontis","version":"Frontis-MA1","score":71.21},{"place":20,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":71.2},{"place":21,"model":"frontis-ma1-35b","company":"frontis","family":"Frontis","version":"Frontis-MA1","score":71.2},{"place":22,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":68.2},{"place":23,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":66.7},{"place":24,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":66.67},{"place":25,"model":"frontis-ma1-30b","company":"frontis","family":"Frontis","version":"Frontis-MA1","score":66.67},{"place":26,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":66.6},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":66.6},{"place":28,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":65.2},{"place":29,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":63.64},{"place":30,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":63.6},{"place":31,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":62.12},{"place":32,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":62.12},{"place":33,"model":"frontis-ma1-35b","company":"frontis","family":"Frontis","version":"Frontis-MA1","score":60.61},{"place":34,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":59.1},{"place":35,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.1},{"place":36,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":59.1},{"place":37,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":59.09},{"place":38,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":54.55},{"place":39,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.5},{"place":40,"model":"frontis-ma1-30b","company":"frontis","family":"Frontis","version":"Frontis-MA1","score":53.03},{"place":41,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":51.5},{"place":42,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.5},{"place":43,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":43.94},{"place":44,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":43.9},{"place":45,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40.9},{"place":46,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":40.9},{"place":47,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.4},{"place":48,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":39.4},{"place":49,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.39},{"place":50,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34.9},{"place":51,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":34.9},{"place":52,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34.85},{"place":53,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":34.85},{"place":54,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":34.85},{"place":55,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":31.8},{"place":56,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":27.3},{"place":57,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":27.3},{"place":58,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.24},{"place":59,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.2},{"place":60,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":22.7},{"place":61,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":18.2},{"place":62,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":7.6}]},{"id":"mls-bench-lite","name":"MLS-Bench-Lite","topic":"Agentic ML engineering","description":"Lite version of MLS-Bench, a long-horizon agentic machine-learning research/engineering benchmark with an official leaderboard.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":49.9,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":49.9},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":48.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.2},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":42.8},{"place":5,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":41},{"place":6,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":40.4},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":35.5},{"place":8,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":35.1},{"place":9,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":31.7},{"place":10,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":26.7}]},{"id":"mlvu","name":"MLVU","topic":"Large video understanding","description":"MLVU: Large-scale multi-task benchmark for video understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":90.8,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":105,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.8},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":87.6},{"place":3,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":87.4},{"place":4,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.3},{"place":5,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":86.8},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.7},{"place":7,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.7},{"place":8,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.6},{"place":9,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86.2},{"place":10,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.2},{"place":11,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":86.1},{"place":12,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.9},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.6},{"place":14,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":85.6},{"place":15,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.6},{"place":16,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":85},{"place":17,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.7},{"place":18,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.4},{"place":19,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.8},{"place":20,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.8},{"place":21,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":83.3},{"place":22,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":83},{"place":23,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.8},{"place":24,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":82.8},{"place":25,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.3},{"place":26,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":82.1},{"place":27,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.1},{"place":28,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":81.9},{"place":29,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":81.7},{"place":30,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":81.7},{"place":31,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.5},{"place":32,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.3},{"place":33,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.2},{"place":34,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80.68},{"place":35,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.9},{"place":36,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.9},{"place":37,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.5},{"place":38,"model":"internvl3.5-241b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.2},{"place":39,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.1},{"place":40,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.8},{"place":41,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":77.72},{"place":42,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":77.7},{"place":43,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":77.5},{"place":44,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":76.9},{"place":45,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":76.5},{"place":46,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.2},{"place":47,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.7},{"place":48,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":75.7},{"place":49,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":75.7},{"place":50,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.3},{"place":51,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":75.3},{"place":52,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":75.2},{"place":53,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.1},{"place":54,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":75.1},{"place":55,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":75.07},{"place":56,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":74.6},{"place":57,"model":"reka-edge-2603","company":"reka","family":"Reka Edge","version":"Reka Edge","score":74.3},{"place":58,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":73.5},{"place":59,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.8},{"place":60,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":72.3},{"place":61,"model":"oryx-1.5-32b","company":"tsinghua","family":"Oryx","version":"Oryx-1.5","score":72.3},{"place":62,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":71.7},{"place":63,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":71.4},{"place":64,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":71},{"place":65,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":70.2},{"place":66,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":69.9},{"place":67,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.3},{"place":68,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":69.2},{"place":69,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.2},{"place":70,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":69.1},{"place":71,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":68.9},{"place":72,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":68.7},{"place":73,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.3},{"place":74,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":68.3},{"place":75,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":68},{"place":76,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":66.4},{"place":77,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.6},{"place":78,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":65.2},{"place":79,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":64.6},{"place":80,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":64.2},{"place":81,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64},{"place":82,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":64},{"place":83,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":63},{"place":84,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":62.4},{"place":85,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":61.6},{"place":86,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.5},{"place":87,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":61.4},{"place":88,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":60.6},{"place":89,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":60.4},{"place":90,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":60.2},{"place":91,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":59.9},{"place":92,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":58.8},{"place":93,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.4},{"place":94,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.6},{"place":95,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":57.3},{"place":96,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":56.7},{"place":97,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":56.6},{"place":98,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":56},{"place":99,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":55.2},{"place":100,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":55.2},{"place":101,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":54.9},{"place":102,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.9},{"place":103,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":54.3},{"place":104,"model":"videotemp-o3-7b","company":"kuaishou","family":"Keye-VL","version":"VideoTemp-o3","score":54.2},{"place":105,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":53.8},{"place":106,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":53.4},{"place":107,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":53.2},{"place":108,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":52.8},{"place":109,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":52.6},{"place":110,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":52.6},{"place":111,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.39},{"place":112,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":52},{"place":113,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":51.8},{"place":114,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":51.6},{"place":115,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":49.2},{"place":116,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":48.4},{"place":117,"model":"videochat2-hd-mistral","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":47.9},{"place":118,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":47.3},{"place":119,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":45.2},{"place":120,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":44.18},{"place":121,"model":"smolvlm2-0.256b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":40.6},{"place":122,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.4},{"place":123,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":37.85},{"place":124,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":32.5}]},{"id":"mm-browsecomp","name":"MM-BrowseComp","topic":"Multimodal browsing","description":"Multimodal browsing comprehension benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":59.3,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.3},{"place":2,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":52},{"place":3,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":47.4},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":46.3},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":41.9},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.2},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":25},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":7.2}]},{"id":"mm-clawbench","name":"MM-ClawBench","topic":"Personal agent tasks","description":"MiniMax MM-ClawBench (MM Claw): end-to-end OpenClaw-style personal-agent benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":75.4,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.4},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":73.6},{"place":3,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":64.2},{"place":4,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":62.7},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":61.8},{"place":6,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":57.6}]},{"id":"mm-ifeval","name":"MM-IFEval","topic":"Multimodal instruction following","description":"Instruction-following benchmark assessing multimodal obedience to complex prompts.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2502.04688","metric":"percent","stars":"","top_model":"GPT-5","top_percent":83.1,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":42,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":83.1},{"place":2,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.8},{"place":3,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.7},{"place":4,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.5},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.94},{"place":6,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":69.9},{"place":7,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.59},{"place":8,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.2},{"place":9,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":68.2},{"place":10,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":68.03},{"place":11,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":66.7},{"place":12,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":66.3},{"place":13,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":65.77},{"place":14,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":65.7},{"place":15,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.6},{"place":16,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":65.41},{"place":17,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":64.6},{"place":18,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.5},{"place":19,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.8},{"place":20,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.1},{"place":21,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":63},{"place":22,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62.85},{"place":23,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":61.53},{"place":24,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":60.6},{"place":25,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.4},{"place":26,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":56.3},{"place":27,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.4},{"place":28,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":54.6},{"place":29,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":54.5},{"place":30,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.32},{"place":31,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":52.29},{"place":32,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.1},{"place":33,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":51.83},{"place":34,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":51.68},{"place":35,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":51.4},{"place":36,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":50.74},{"place":37,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":50.45},{"place":38,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":48.4},{"place":39,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":47.31},{"place":40,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":47.1},{"place":41,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":46.35},{"place":42,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":45.91},{"place":43,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":45},{"place":44,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":44.57},{"place":45,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":38.62},{"place":46,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":38.49},{"place":47,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":36.17},{"place":48,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.78},{"place":49,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":33.09},{"place":50,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":24.99},{"place":51,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":19.42},{"place":52,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":11.27}]},{"id":"mm-mt-bench","name":"MM-MT-Bench","topic":"Multimodal instruction following","description":"Multi-turn multimodal instruction following benchmark evaluating dialogue quality and helpfulness.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Qwen3-VL-235B-A22B Thinking","top_percent":8.5,"top_model_id":"qwen3-vl-235b-a22b-thinking","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":8.5},{"place":2,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":8.49},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":8.4},{"place":4,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":8.4},{"place":5,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":8.1},{"place":6,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":8.08},{"place":7,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":8.01},{"place":8,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":8},{"place":9,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":7.83},{"place":10,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":7.8},{"place":11,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":7.72},{"place":12,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":7.7},{"place":13,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":7.6},{"place":14,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":7.6},{"place":15,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":7.5},{"place":16,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":7.5},{"place":17,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":7.5},{"place":18,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":7.4},{"place":19,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":7.4},{"place":20,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":7.1},{"place":21,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":6.7},{"place":22,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":6.36},{"place":23,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":6.2},{"place":24,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":6.05},{"place":25,"model":"gemini-1.5-flash-8b-0827","company":"google","family":"Gemini","version":"Gemini 1.5","score":5.93},{"place":26,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":5.9},{"place":27,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":5.46},{"place":28,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":5.23},{"place":29,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":4.95}]},{"id":"mmar","name":"MMAR","topic":"Audio reasoning","description":"MMAR: deep reasoning over speech, sound, music and their mix (%).","url":"https://github.com/ddlBoJack/MMAR","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2505.13032","metric":"percent","stars":"","top_model":"StepAudio 3 Realtime","top_percent":86.5,"top_model_id":"stepaudio-3-realtime","top_generation":"StepAudio 3","top_model_base":"StepAudio 3 Realtime","top_model_family":"Step","top_company":"stepfun","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":86.5},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.7},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":81.7},{"place":4,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":80},{"place":5,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":79.8},{"place":6,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":79.8},{"place":7,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":78.5},{"place":8,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.7},{"place":9,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":75.9},{"place":10,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":75.4},{"place":11,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":74},{"place":12,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":67.3}]},{"id":"mmau-pro","name":"MMAU-Pro","topic":"Audio reasoning","description":"MMAU-Pro: challenging audio understanding and reasoning benchmark (speech, sound, music).","url":"https://arxiv.org/abs/2508.13992","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-Omni-Plus","top_percent":70,"top_model_id":"qwen3.5-omni-plus","top_generation":"Qwen3.5 Omni","top_model_base":"Qwen3.5 Omni Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":70},{"place":2,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":69.9},{"place":3,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":69.8},{"place":4,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":69.4},{"place":5,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":67.4},{"place":6,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":67},{"place":7,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":65.6},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65}]},{"id":"mmbench","name":"MMBench (EN)","topic":"Multimodal understanding (English)","description":"MMBench v1.0 English test split.","url":"https://mmbench.opencompass.org.cn/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2307.06281","metric":"percent","stars":"","top_model":"InternVL2.5-78B","top_percent":88.3,"top_model_id":"internvl2.5-78b","top_generation":"InternVL2.5","top_model_base":"InternVL2.5-78B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":100,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":88.3},{"place":2,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":86.8},{"place":3,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":86.5},{"place":4,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":86.5},{"place":5,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":86.5},{"place":6,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":86.5},{"place":7,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":86.4},{"place":8,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":85.8},{"place":9,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":85.4},{"place":10,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":84.6},{"place":11,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":84.6},{"place":12,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":83.4},{"place":13,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":83.4},{"place":14,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":83.4},{"place":15,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":83.1},{"place":16,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":83},{"place":17,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":83},{"place":18,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":82.6},{"place":19,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":82.3},{"place":20,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":82.3},{"place":21,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":82.2},{"place":22,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":82.2},{"place":23,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":82.2},{"place":24,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":81.7},{"place":25,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":81.5},{"place":26,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":81.3},{"place":27,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":81.1},{"place":28,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":81.1},{"place":29,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":81.1},{"place":30,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":81},{"place":31,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":81},{"place":32,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":80.8},{"place":33,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":80.7},{"place":34,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":80.7},{"place":35,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":80.6},{"place":36,"model":"llava-next-110b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":80.5},{"place":37,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":80.5},{"place":38,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":80.4},{"place":39,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":80.4},{"place":40,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":80.2},{"place":41,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":79.7},{"place":42,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":79.7},{"place":43,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":79.6},{"place":44,"model":"cogvlm2-llama3-chinese-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":78.9},{"place":45,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":78.6},{"place":46,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":78.1},{"place":47,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":77.6},{"place":48,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":77.6},{"place":49,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":77.6},{"place":50,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":77.2},{"place":51,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":77},{"place":52,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":77},{"place":53,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":77},{"place":54,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":76.7},{"place":55,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":76.2},{"place":56,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":76},{"place":57,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":75.7},{"place":58,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":75.2},{"place":59,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":75.1},{"place":60,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":75.1},{"place":61,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":75},{"place":62,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":74.9},{"place":63,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":74.9},{"place":64,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":74.7},{"place":65,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":74.7},{"place":66,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":74.6},{"place":67,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":74.4},{"place":68,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":73.9},{"place":69,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":73.9},{"place":70,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":73.9},{"place":71,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":73.8},{"place":72,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":73.6},{"place":73,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":73.6},{"place":74,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":73.6},{"place":75,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":73.3},{"place":76,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":73.2},{"place":77,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":73.2},{"place":78,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":72.4},{"place":79,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":72.4},{"place":80,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":72.1},{"place":81,"model":"llava-llama-3-8b","company":"llava","family":"LLaVA","version":"LLaVA-LLaMA-3","score":71.7},{"place":82,"model":"unified-io-2-xxl","company":"allenai","family":"Unified-IO","version":"Unified-IO 2","score":71.5},{"place":83,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":70.7},{"place":84,"model":"vila-13b","company":"nvidia","family":"VILA","version":"VILA","score":70.3},{"place":85,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":70},{"place":86,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":69.6},{"place":87,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":69.2},{"place":88,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":69.1},{"place":89,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":68.8},{"place":90,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":68.4},{"place":91,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":68.2},{"place":92,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":68.2},{"place":93,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":67.8},{"place":94,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":67.7},{"place":95,"model":"llava-next-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":67.4},{"place":96,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":67},{"place":97,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":66.4},{"place":98,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":66.2},{"place":99,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":65.9},{"place":100,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":65.8},{"place":101,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":65.4},{"place":102,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":64.6},{"place":103,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":64.5},{"place":104,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":64.3},{"place":105,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":64.1},{"place":106,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":63.7},{"place":107,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":63.6},{"place":108,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":63.3},{"place":109,"model":"mobilevlm-v2-3b","company":"meituan","family":"MobileVLM","version":"MobileVLM V2","score":63.2},{"place":110,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":61.8},{"place":111,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":61.6},{"place":112,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":60.7},{"place":113,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":60.6},{"place":114,"model":"mobilevlm-3b","company":"meituan","family":"MobileVLM","version":"MobileVLM","score":59.6},{"place":115,"model":"mobilevlm-v2-1.7b","company":"meituan","family":"MobileVLM","version":"MobileVLM V2","score":59.6},{"place":116,"model":"llava-phi","company":"midea","family":"LLaVA","version":"LLaVA-Phi","score":59.5},{"place":117,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":54.5},{"place":118,"model":"mobilevlm-1.7b","company":"meituan","family":"MobileVLM","version":"MobileVLM","score":53.2},{"place":119,"model":"dreamllm-7b","company":"megvii","family":"DreamLLM","version":"DreamLLM","score":49.9},{"place":120,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":36},{"place":121,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":34.1},{"place":122,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":33.9},{"place":123,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":23},{"place":124,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":5.7}]},{"id":"mmbench-cn","name":"MMBench (CN)","topic":"Multimodal understanding (Chinese)","description":"MMBench v1.0 Chinese test split.","url":"https://mmbench.opencompass.org.cn/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2307.06281","metric":"percent","stars":"","top_model":"InternVL2.5-78B","top_percent":88.5,"top_model_id":"internvl2.5-78b","top_generation":"InternVL2.5","top_model_base":"InternVL2.5-78B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":78,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":88.5},{"place":2,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":86.6},{"place":3,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":86.6},{"place":4,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":86.5},{"place":5,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":86.3},{"place":6,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":86.3},{"place":7,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":85.5},{"place":8,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":85.3},{"place":9,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":83.5},{"place":10,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":82.6},{"place":11,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":82.1},{"place":12,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":82.1},{"place":13,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":82},{"place":14,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":82},{"place":15,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":81.9},{"place":16,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":81.2},{"place":17,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":81.2},{"place":18,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":80.8},{"place":19,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":80.7},{"place":20,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":80.7},{"place":21,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":80.7},{"place":22,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":80.5},{"place":23,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":80.5},{"place":24,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":80.3},{"place":25,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":80.2},{"place":26,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":80.2},{"place":27,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":79.9},{"place":28,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":79.6},{"place":29,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":79.4},{"place":30,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":79.4},{"place":31,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":79.3},{"place":32,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":79.3},{"place":33,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":79.2},{"place":34,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":79.2},{"place":35,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":79},{"place":36,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":77.7},{"place":37,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":77.6},{"place":38,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":75.7},{"place":39,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":75.1},{"place":40,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":74.9},{"place":41,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":74.4},{"place":42,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":74.4},{"place":43,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":74.3},{"place":44,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":74.3},{"place":45,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":74.3},{"place":46,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":74.2},{"place":47,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":73.9},{"place":48,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":73.9},{"place":49,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":73.9},{"place":50,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":73.8},{"place":51,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":73.8},{"place":52,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":73.7},{"place":53,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":73.5},{"place":54,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":73.5},{"place":55,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":73.3},{"place":56,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":72.4},{"place":57,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":71.9},{"place":58,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":71.4},{"place":59,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":71.4},{"place":60,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":70.9},{"place":61,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":70.7},{"place":62,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":70.7},{"place":63,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":69.8},{"place":64,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":69.2},{"place":65,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":68.6},{"place":66,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":68.5},{"place":67,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":68.1},{"place":68,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":68},{"place":69,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":67.9},{"place":70,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":67.5},{"place":71,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":66.6},{"place":72,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":66.5},{"place":73,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":66.3},{"place":74,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":66.1},{"place":75,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":64.2},{"place":76,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":63.6},{"place":77,"model":"llava-llama-3-8b","company":"llava","family":"LLaVA","version":"LLaVA-LLaMA-3","score":63.2},{"place":78,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":62.9},{"place":79,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":62.6},{"place":80,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":62.2},{"place":81,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":60.7},{"place":82,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":59.2},{"place":83,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":57.2},{"place":84,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":56.7},{"place":85,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":56.3},{"place":86,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":55.9},{"place":87,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":55.5},{"place":88,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":38.1},{"place":89,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":23.7},{"place":90,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":14.1}]},{"id":"mmbench-gui-l2","name":"MMBench-GUI L2","topic":"GUI grounding","description":"MMBench-GUI level-2 element grounding across Windows, macOS, Linux, iOS, Android and Web.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2507.19478","metric":"percent","stars":"","top_model":"MAI-UI-8B","top_percent":88.8,"top_model_id":"mai-ui-8b","top_generation":"MAI-UI","top_model_base":"MAI-UI 8B","top_model_family":"MAI-UI","top_company":"tongyi","top_open_source":1,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"mai-ui-8b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":88.8},{"place":2,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.3},{"place":3,"model":"gta1-32b","company":"salesforce","family":"GTA1","version":"GTA1","score":83.4},{"place":4,"model":"gui-owl-32b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl","score":83},{"place":5,"model":"mai-ui-2b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":82.6},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.3},{"place":7,"model":"infigui-g1-7b","company":"infix-ai","family":"InfiGUI","version":"InfiGUI","score":80.8},{"place":8,"model":"gui-owl-7b","company":"alibaba","family":"GUI","version":"GUI","score":80.5},{"place":9,"model":"gui-g2-7b","company":"zju","family":"GUI","version":"GUI","score":78.8},{"place":10,"model":"gta1-7b","company":"salesforce","family":"GTA1","version":"GTA1","score":78.5},{"place":11,"model":"se-gui-7b","company":"se-gui","family":"SE-GUI","version":"SE-GUI","score":76.6},{"place":12,"model":"gui-actor-7b-qwen2.5-vl","company":"microsoft","family":"GUI-Actor","version":"GUI-Actor","score":76.5},{"place":13,"model":"ui-tars-72b-dpo","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":74.3},{"place":14,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":72.2},{"place":15,"model":"uground-v1-7b","company":"osunlp","family":"UGround","version":"UGround-V1","score":65.7},{"place":16,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":64.3},{"place":17,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.5},{"place":18,"model":"aguvis-7b","company":"hku","family":"Aguvis","version":"Aguvis","score":45.7},{"place":19,"model":"os-atlas-7b","company":"os-copilot","family":"OS-Atlas","version":"OS-Atlas","score":41.4},{"place":20,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":4.7},{"place":21,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":2.9}]},{"id":"mmbench-v1.1-cn","name":"MMBench v1.1 (CN)","topic":"Multimodal understanding (Chinese)","description":"MMBench v1.1 Chinese subset for evaluating multimodal LLMs.","url":"https://mmbench.opencompass.org.cn/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2307.06281","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":91.3,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":345,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.3},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.98},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":90.6},{"place":4,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":89.8},{"place":5,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.78},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.7},{"place":7,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.1},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89},{"place":9,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89},{"place":10,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":88.3},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.3},{"place":12,"model":"congrong-v2.0","company":"cloudwalk","family":"CongRong","version":"CongRong-v2.0","score":88.3},{"place":13,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":88.24},{"place":14,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.2},{"place":15,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":88.2},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.1},{"place":17,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":87.9},{"place":18,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":87.8},{"place":19,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":87.7},{"place":20,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":87.7},{"place":21,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":87.6},{"place":22,"model":"sensenova-v6-pro","company":"sensetime","family":"SenseNova","version":"SenseNova-V6-Pro","score":87.6},{"place":23,"model":"internvl2.5-78b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":87.5},{"place":24,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":87.4},{"place":25,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87.4},{"place":26,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.3},{"place":27,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":87.2},{"place":28,"model":"rbdashmm3-dpo-38b","company":"rbdash","family":"RBDashMM3","version":"RBDashMM3-DPO","score":87.2},{"place":29,"model":"step-1o","company":"stepfun","family":"Step","version":"Step-1o","score":87},{"place":30,"model":"sensenova-v6-5-pro","company":"sensetime","family":"SenseNova","version":"SenseNova-V6-5-Pro","score":87},{"place":31,"model":"internvl3-38b","company":"opengvlab","family":"Intern","version":"InternVL3","score":86.6},{"place":32,"model":"jt-vl-chat-v3.0","company":"chinamobile","family":"JT","version":"JT-VL-Chat-V3.0","score":86.6},{"place":33,"model":"bailingmm-pro-0120","company":"antgroup","family":"BailingMM","version":"BailingMM-Pro-0120","score":86.5},{"place":34,"model":"ovis2-34b","company":"alibaba","family":"Ovis","version":"Ovis2","score":86.5},{"place":35,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":86.43},{"place":36,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":86.4},{"place":37,"model":"bluelm-2.5-3b-0909","company":"vivo","family":"BlueLM","version":"BlueLM-2.5","score":86.4},{"place":38,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":86.2},{"place":39,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":86.2},{"place":40,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":86.2},{"place":41,"model":"gpt-5-mini-2025-08","company":"openai","family":"GPT","version":"GPT-5","score":86.1},{"place":42,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":86},{"place":43,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86},{"place":44,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":85.8},{"place":45,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":85.7},{"place":46,"model":"qwen-vl-max-0809","company":"qwen","family":"Qwen","version":"Qwen-VL","score":85.7},{"place":47,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":85.6},{"place":48,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":85.6},{"place":49,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.5},{"place":50,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":85.5},{"place":51,"model":"ovis2-16b","company":"alibaba","family":"Ovis","version":"Ovis2","score":85.5},{"place":52,"model":"internvl2.5-38b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":85.4},{"place":53,"model":"sensenova","company":"sensetime","family":"SenseNova","version":"SenseNova","score":85.2},{"place":54,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":85.2},{"place":55,"model":"taiyi","company":"megvii","family":"Taiyi","version":"Taiyi","score":85},{"place":56,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.9},{"place":57,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":84.9},{"place":58,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":84.8},{"place":59,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":84.7},{"place":60,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.7},{"place":61,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":84.7},{"place":62,"model":"sail-vl2-8b","company":"bytedance","family":"SAIL","version":"SAIL-VL2","score":84.7},{"place":63,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":84.5},{"place":64,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":84.5},{"place":65,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":84.1},{"place":66,"model":"internvl2.5-26b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":84.1},{"place":67,"model":"glm-4v-plus-0111","company":"zai","family":"GLM","version":"GLM-4V-Plus (2025-01-11)","score":84.1},{"place":68,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":84.1},{"place":69,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":83.9},{"place":70,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":83.9},{"place":71,"model":"doubao-1.5-vision-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":83.9},{"place":72,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":83.7},{"place":73,"model":"sail-vl-1.6-8b","company":"bytedance","family":"SAIL","version":"SAIL-VL-1.6","score":83.7},{"place":74,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":83.6},{"place":75,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.5},{"place":76,"model":"step-1.5v","company":"stepfun","family":"Step","version":"Step-1.5V","score":83.5},{"place":77,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":83.5},{"place":78,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":83.4},{"place":79,"model":"ovis2-8b","company":"alibaba","family":"Ovis","version":"Ovis2","score":83.4},{"place":80,"model":"hunyuan-standard-vision-2024-12-31","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":83.3},{"place":81,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":83.3},{"place":82,"model":"internvl3-14b","company":"opengvlab","family":"Intern","version":"InternVL3","score":83.3},{"place":83,"model":"ola-7b","company":"tsinghua","family":"Ola","version":"Ola","score":83.2},{"place":84,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":83.2},{"place":85,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":83},{"place":86,"model":"varco-vision-2.0-14b","company":"ncsoft","family":"VARCO","version":"VARCO-VISION-2.0","score":83},{"place":87,"model":"jt-vl-chat-mini","company":"chinamobile","family":"JT","version":"JT-VL-Chat-Mini","score":83},{"place":88,"model":"bailingmm-lite-1203","company":"antgroup","family":"BailingMM","version":"BailingMM-Lite-1203","score":82.9},{"place":89,"model":"valley3","company":"bytedance","family":"Valley","version":"Valley3","score":82.6},{"place":90,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":82.5},{"place":91,"model":"grok-2-vision-1212","company":"xai","family":"Grok","version":"Grok 2","score":82.5},{"place":92,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":82.4},{"place":93,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":82.4},{"place":94,"model":"internvl3-9b","company":"opengvlab","family":"Intern","version":"InternVL3","score":82.4},{"place":95,"model":"bluelm-v-3b","company":"vivo","family":"BlueLM","version":"BlueLM-V","score":82.3},{"place":96,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":82.2},{"place":97,"model":"bailingmm-mini","company":"antgroup","family":"bailingMM","version":"bailingMM-mini","score":82.2},{"place":98,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":82.1},{"place":99,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":82},{"place":100,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":81.9},{"place":101,"model":"llava-onevision-72b-si","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":81.9},{"place":102,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":81.9},{"place":103,"model":"awaker2.5-vl","company":"metabrain","family":"Awaker2.5","version":"Awaker2.5-VL","score":81.8},{"place":104,"model":"r-4b","company":"tencent","family":"R","version":"R","score":81.8},{"place":105,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":81.7},{"place":106,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":81.7},{"place":107,"model":"sail-vl-1.5-8b","company":"bytedance","family":"SAIL","version":"SAIL-VL-1.5","score":81.7},{"place":108,"model":"mug-u-7b","company":"shopee","family":"MUG","version":"MUG-U","score":81.6},{"place":109,"model":"valley2-dpo","company":"bytedance","family":"Valley","version":"Valley2-DPO","score":81.6},{"place":110,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":81.5},{"place":111,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":81.5},{"place":112,"model":"ovis1.6-gemma2-27b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":81.5},{"place":113,"model":"internvl2.5-8b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":81.5},{"place":114,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":81.2},{"place":115,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":81.1},{"place":116,"model":"wethink-qwen2.5vl-7b","company":"tencent","family":"WeThink","version":"WeThink-Qwen2.5VL","score":81.1},{"place":117,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":81},{"place":118,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":81},{"place":119,"model":"ovis2-4b","company":"alibaba","family":"Ovis","version":"Ovis2","score":81},{"place":120,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":80.9},{"place":121,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":80.9},{"place":122,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":80.7},{"place":123,"model":"valley2","company":"bytedance","family":"Valley","version":"Valley2","score":80.7},{"place":124,"model":"abab7-preview","company":"minimax","family":"abab7","version":"abab7-preview","score":80.6},{"place":125,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":80.6},{"place":126,"model":"congrong","company":"cloudwalk","family":"CongRong","version":"CongRong","score":80.4},{"place":127,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":80.3},{"place":128,"model":"rbdash-v1.5","company":"dlut","family":"RBDash","version":"RBDash-v1.5","score":80.3},{"place":129,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":80.2},{"place":130,"model":"points1.5-qwen2.5-7b","company":"tencent","family":"POINTS1.5","version":"POINTS1.5-Qwen2.5","score":80.2},{"place":131,"model":"varco-vision-14b","company":"ncsoft","family":"VARCO","version":"VARCO-VISION","score":80.1},{"place":132,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":80.1},{"place":133,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":80},{"place":134,"model":"valley-eagle","company":"bytedance","family":"Valley","version":"Valley-Eagle","score":79.9},{"place":135,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":79.9},{"place":136,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":79.8},{"place":137,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":79.8},{"place":138,"model":"mmalaya2","company":"datacanvas","family":"MMAlaya2","version":"MMAlaya2","score":79.7},{"place":139,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":79.6},{"place":140,"model":"step-1.5v-mini","company":"stepfun","family":"Step","version":"Step-1.5V-mini","score":79.6},{"place":141,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":79.6},{"place":142,"model":"minicpm-v-4","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V-4","score":79.6},{"place":143,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":79.5},{"place":144,"model":"omchat-v2.0-13b","company":"omai","family":"OmChat","version":"OmChat-v2.0","score":79.5},{"place":145,"model":"ovis1.6-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":79.5},{"place":146,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":79.5},{"place":147,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":79.4},{"place":148,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":79.3},{"place":149,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":79.3},{"place":150,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":79.2},{"place":151,"model":"sail-vl2-2b","company":"bytedance","family":"SAIL","version":"SAIL-VL2","score":79.2},{"place":152,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":79.1},{"place":153,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":79.1},{"place":154,"model":"ristretto-3b","company":"liauto","family":"Ristretto","version":"Ristretto","score":79.1},{"place":155,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":78.8},{"place":156,"model":"jt-vl-chat-2b","company":"chinamobile","family":"JT","version":"JT-VL-Chat","score":78.8},{"place":157,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":78.6},{"place":158,"model":"telemm","company":"teleai","family":"TeleMM","version":"TeleMM","score":78.3},{"place":159,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":78.2},{"place":160,"model":"glm-4v","company":"zai","family":"GLM","version":"GLM-4V","score":78},{"place":161,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":78},{"place":162,"model":"bumblebee-7b-v2.2","company":"monolith","family":"Bumblebee","version":"Bumblebee","score":78},{"place":163,"model":"points-yi-1.5-9b","company":"tencent","family":"POINTS","version":"POINTS-Yi-1.5","score":77.8},{"place":164,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":77.6},{"place":165,"model":"ovis-u1-3b","company":"alibaba","family":"Ovis","version":"Ovis-U1","score":77.6},{"place":166,"model":"sail-vl-1.5-2b","company":"bytedance","family":"SAIL","version":"SAIL-VL-1.5","score":77.5},{"place":167,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":77.3},{"place":168,"model":"mirage-12b-v2.0","company":"monolith","family":"Mirage","version":"Mirage","score":77.2},{"place":169,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":77.1},{"place":170,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":77.1},{"place":171,"model":"llava-next-qwen-32b","company":"llava","family":"LLaVA","version":"LLaVA-Next-Qwen","score":77.1},{"place":172,"model":"qtunevl1.5-3b","company":"reconova","family":"QTuneVL1.5","version":"QTuneVL1.5","score":77.1},{"place":173,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":77},{"place":174,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":76.9},{"place":175,"model":"points-qwen2.5-7b","company":"tencent","family":"POINTS","version":"POINTS-Qwen2.5","score":76.9},{"place":176,"model":"internvl2.5-4b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":76.9},{"place":177,"model":"qtunevl1.5-2b","company":"reconova","family":"QTuneVL1.5","version":"QTuneVL1.5","score":76.9},{"place":178,"model":"ovis2-2b","company":"alibaba","family":"Ovis","version":"Ovis2","score":76.8},{"place":179,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":76.7},{"place":180,"model":"aria","company":"rhymes","family":"Aria","version":"Aria","score":76.6},{"place":181,"model":"bumblebee-7b-v2.0","company":"monolith","family":"Bumblebee","version":"Bumblebee","score":76.5},{"place":182,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":76.5},{"place":183,"model":"internvl2-8b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2","score":76.4},{"place":184,"model":"ovis1.5-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.5-Gemma2","score":76.2},{"place":185,"model":"moonshot-v1-8k","company":"moonshotai","family":"Moonshot","version":"Moonshot v1","score":76.2},{"place":186,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":76.1},{"place":187,"model":"yi-vision","company":"01ai","family":"Yi","version":"Yi Vision","score":76.1},{"place":188,"model":"vita-1.5","company":"nju","family":"VITA","version":"VITA-1.5","score":76.1},{"place":189,"model":"long-vita-16k","company":"tencent","family":"VITA","version":"Long-VITA-16K","score":75.9},{"place":190,"model":"llava-onevision-7b-si","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":75.8},{"place":191,"model":"internvl2-8b-mpo-cot","company":"opengvlab","family":"Intern","version":"InternVL2","score":75.8},{"place":192,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":75.77},{"place":193,"model":"bluelm-2.5-3b","company":"vivo","family":"BlueLM","version":"BlueLM-2.5","score":75.5},{"place":194,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":75.2},{"place":195,"model":"ovis1.5-llama3-8b","company":"alibaba","family":"Ovis","version":"Ovis1.5-Llama3","score":75.1},{"place":196,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":75},{"place":197,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":74.9},{"place":198,"model":"xinyuan-vl","company":"cylingo","family":"XinYuan","version":"XinYuan-VL","score":74.6},{"place":199,"model":"flash-vl-2b-dynamic-iss","company":"meituan","family":"Flash-VL","version":"Flash-VL","score":74.4},{"place":200,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":74.3},{"place":201,"model":"xinyuan-vl-2b-instruct","company":"cylingo","family":"XinYuan","version":"XinYuan-VL","score":74.2},{"place":202,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":74.1},{"place":203,"model":"360vl-70b","company":"360","family":"360VL","version":"360VL","score":73.9},{"place":204,"model":"ross-qwen2-7b","company":"casia","family":"Ross","version":"Ross-Qwen2","score":73.8},{"place":205,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":73.7},{"place":206,"model":"eagle-x5-34b-chat","company":"nvidia","family":"Eagle","version":"Eagle-X5","score":73.7},{"place":207,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":73.6},{"place":208,"model":"wemm","company":"tencent","family":"WeMM","version":"WeMM","score":73.6},{"place":209,"model":"bumblebee-7b-v1.6","company":"monolith","family":"Bumblebee","version":"Bumblebee","score":73.6},{"place":210,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":73.2},{"place":211,"model":"idefics3-8b-llama3","company":"huggingface","family":"IDEFICS","version":"Idefics3","score":71.9},{"place":212,"model":"ovis1.6-llama3.2-3b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Llama3.2","score":71.9},{"place":213,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":71.8},{"place":214,"model":"sail-vl-2b","company":"bytedance","family":"SAIL","version":"SAIL-VL","score":71.8},{"place":215,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":71.7},{"place":216,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":71.6},{"place":217,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":71.6},{"place":218,"model":"reka-flash","company":"reka","family":"Reka","version":"Reka","score":71.4},{"place":219,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":71.4},{"place":220,"model":"llava-cot","company":"llava","family":"LLaVA","version":"LLaVA-CoT","score":71.4},{"place":221,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":71.2},{"place":222,"model":"llava-next-interleave-7b-dpo","company":"llava","family":"LLaVA","version":"LLaVA-Next-Interleave","score":70.9},{"place":223,"model":"varco-vision-2.0-1.7b","company":"ncsoft","family":"VARCO","version":"VARCO-VISION-2.0","score":70.8},{"place":224,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":70.5},{"place":225,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":70.1},{"place":226,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":70.1},{"place":227,"model":"llama-3-mixsense-v1.1","company":"zerovision","family":"Llama","version":"Llama-3-MixSense-v1.1","score":70.1},{"place":228,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":70.1},{"place":229,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":70.1},{"place":230,"model":"llava-internlm2-7b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-7B (QLoRA)","score":70},{"place":231,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":232,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":69.9},{"place":233,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":69.7},{"place":234,"model":"qtunevl1-2b","company":"reconova","family":"QTuneVL1","version":"QTuneVL1","score":69.6},{"place":235,"model":"internvl2.5-2b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":69.5},{"place":236,"model":"llava-next-interleave-7b","company":"llava","family":"LLaVA","version":"LLaVA-Next-Interleave","score":69.4},{"place":237,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":69.4},{"place":238,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":69.2},{"place":239,"model":"parrot-7b","company":"alibaba","family":"Parrot","version":"Parrot","score":69.2},{"place":240,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":68.9},{"place":241,"model":"qwen-vl-plus-0809","company":"qwen","family":"Qwen","version":"Qwen-VL","score":68.7},{"place":242,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":68.7},{"place":243,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":68.6},{"place":244,"model":"minimonkey","company":"hust","family":"Monkey","version":"MiniMonkey","score":68.3},{"place":245,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":68.2},{"place":246,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68},{"place":247,"model":"transcore-m","company":"pci","family":"TransCore","version":"TransCore-M","score":67.9},{"place":248,"model":"llama-3-mixsense","company":"zerovision","family":"Llama","version":"Llama-3-MixSense","score":67.8},{"place":249,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":67.5},{"place":250,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":67.1},{"place":251,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":66.8},{"place":252,"model":"internlm-xcomposer2-1.8b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2","score":66.8},{"place":253,"model":"mini-internvl-chat-4b-v1.5","company":"opengvlab","family":"Intern","version":"Mini-InternVL-Chat","score":66.8},{"place":254,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.8},{"place":255,"model":"ovis2-1b","company":"alibaba","family":"Ovis","version":"Ovis2","score":66.6},{"place":256,"model":"internvl3-1b","company":"opengvlab","family":"Intern","version":"InternVL3","score":66.4},{"place":257,"model":"vintern-3b-beta","company":"fifth-civil-defender","family":"Vintern","version":"Vintern","score":66.2},{"place":258,"model":"mantis-8b-idefics2","company":"tiger-lab","family":"Mantis","version":"Mantis","score":65.8},{"place":259,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":65.7},{"place":260,"model":"granite-vision-3.2-2b","company":"IBM","family":"Granite","version":"Granite-Vision-3.2","score":65.7},{"place":261,"model":"falcon2-vlm-11b","company":"tii","family":"Falcon2","version":"Falcon2-VLM","score":65.6},{"place":262,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":65.5},{"place":263,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":65.5},{"place":264,"model":"xgen-mm-instruct-dpo-v1.5","company":"salesforce","family":"XGen","version":"XGen-MM-Instruct-DPO-v1.5","score":65.5},{"place":265,"model":"vila1.5-13b","company":"nvidia","family":"VILA","version":"VILA1.5","score":65.2},{"place":266,"model":"eagle-x5-13b","company":"nvidia","family":"Eagle","version":"Eagle-X5","score":65.2},{"place":267,"model":"monkey-chat","company":"hust","family":"Monkey","version":"Monkey-Chat","score":65.1},{"place":268,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":65.1},{"place":269,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":65},{"place":270,"model":"granite-vision-3.3-2b","company":"IBM","family":"Granite","version":"Granite-Vision-3.3","score":65},{"place":271,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.9},{"place":272,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":64.9},{"place":273,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":64.8},{"place":274,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":64.5},{"place":275,"model":"granite-vision-3.1-2b-preview","company":"IBM","family":"Granite","version":"Granite-Vision-3.1","score":64.4},{"place":276,"model":"internvl2.5-1b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":64.3},{"place":277,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":64.2},{"place":278,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":64.2},{"place":279,"model":"llava-internlm-7b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM-7B (QLoRA)","score":64.1},{"place":280,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":64.1},{"place":281,"model":"hawkvl-2b","company":"reconova","family":"HawkVL","version":"HawkVL","score":63.8},{"place":282,"model":"slime-8b","company":"casia","family":"Slime","version":"Slime","score":63.7},{"place":283,"model":"cambrian-13b","company":"nyu","family":"Cambrian","version":"Cambrian","score":63.6},{"place":284,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":63.5},{"place":285,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":63.1},{"place":286,"model":"mantis-8b-siglip-llama3","company":"tiger-lab","family":"Mantis","version":"Mantis","score":63.1},{"place":287,"model":"sharegpt4v-13b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":63},{"place":288,"model":"mini-internvl-chat-2b-v1.5","company":"opengvlab","family":"Intern","version":"Mini-InternVL-Chat","score":63},{"place":289,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":62.8},{"place":290,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":62.8},{"place":291,"model":"llava-v1.5-13b-qlora","company":"internlm","family":"LLaVA","version":"LLaVA-v1.5-13B (QLoRA)","score":62.5},{"place":292,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":61.9},{"place":293,"model":"mantis-8b-clip-llama3","company":"tiger-lab","family":"Mantis","version":"Mantis","score":61.5},{"place":294,"model":"h2ovl-2b","company":"h2oai","family":"H2OVL","version":"H2OVL","score":61},{"place":295,"model":"xverse-v-13b","company":"xverse","family":"XVERSE","version":"XVERSE-V","score":60.5},{"place":296,"model":"eagle-x5-7b","company":"nvidia","family":"Eagle","version":"Eagle-X5","score":60.5},{"place":297,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":60.4},{"place":298,"model":"llava-llama-3-8b","company":"llava","family":"LLaVA","version":"LLaVA-LLaMA-3","score":60.2},{"place":299,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":59.8},{"place":300,"model":"llava-1.6-mistral-7b","company":"llava","family":"LLaVA","version":"LLaVA-1.6-Mistral","score":59.8},{"place":301,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":59.6},{"place":302,"model":"llava-v1.5-7b-qlora","company":"internlm","family":"LLaVA","version":"LLaVA-v1.5-7B (QLoRA)","score":59.5},{"place":303,"model":"omnilmm-12b","company":"openbmb","family":"OmniLMM","version":"OmniLMM","score":59.4},{"place":304,"model":"llava-1.6-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":59.4},{"place":305,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":58.6},{"place":306,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":58.3},{"place":307,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":58.1},{"place":308,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":58},{"place":309,"model":"llama-3-vila1.5-8b","company":"nvidia","family":"LLaVA","version":"Llama-3-VILA1.5","score":57.9},{"place":310,"model":"sharecaptioner","company":"internlm","family":"InternLM","version":"ShareCaptioner","score":57.8},{"place":311,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":57.7},{"place":312,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":57.5},{"place":313,"model":"abab6.5s","company":"minimax","family":"abab6.5s","version":"abab6.5s","score":57.5},{"place":314,"model":"slime-13b","company":"casia","family":"Slime","version":"Slime","score":56.8},{"place":315,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":56.8},{"place":316,"model":"mmalaya","company":"datacanvas","family":"MMAlaya","version":"MMAlaya","score":56.6},{"place":317,"model":"reka-edge","company":"reka","family":"Reka","version":"Reka","score":56.6},{"place":318,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":56.2},{"place":319,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":55.5},{"place":320,"model":"vila1.5-3b","company":"nvidia","family":"VILA","version":"VILA 1.5","score":54.5},{"place":321,"model":"slime-7b","company":"casia","family":"Slime","version":"Slime","score":54.3},{"place":322,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":54},{"place":323,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":53.9},{"place":324,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.6},{"place":325,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":53.2},{"place":326,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":52.5},{"place":327,"model":"vintern-1b-v2","company":"fifth-civil-defender","family":"Vintern","version":"Vintern","score":52.2},{"place":328,"model":"janus-1.3b","company":"deepseek","family":"Janus","version":"Janus","score":50.4},{"place":329,"model":"smolvlm-instruct","company":"huggingface","family":"SmolVLM","version":"SmolVLM-Instruct","score":50.3},{"place":330,"model":"smolvlm-instruct-dpo","company":"huggingface","family":"SmolVLM","version":"SmolVLM-Instruct-DPO","score":48.1},{"place":331,"model":"llava-onevision-0.5b-si","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":47.6},{"place":332,"model":"emu3-chat","company":"baai","family":"Emu","version":"Emu3-Chat","score":46.1},{"place":333,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":45.5},{"place":334,"model":"aki-4b","company":"sony","family":"AKI","version":"AKI","score":45.3},{"place":335,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":44.4},{"place":336,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":44.3},{"place":337,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":44.2},{"place":338,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":43.9},{"place":339,"model":"h2ovl-800m","company":"h2oai","family":"H2OVL","version":"H2OVL","score":41.5},{"place":340,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":35.8},{"place":341,"model":"smolvlm-synthetic","company":"huggingface","family":"SmolVLM","version":"SmolVLM-Synthetic","score":35.3},{"place":342,"model":"visualglm","company":"zai","family":"GLM","version":"VisualGLM","score":34.6},{"place":343,"model":"smolvlm-500m","company":"huggingface","family":"SmolVLM","version":"SmolVLM","score":33.7},{"place":344,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":33.4},{"place":345,"model":"mantis-8b-fuyu","company":"tiger-lab","family":"Mantis","version":"Mantis","score":31.8},{"place":346,"model":"pandagpt-13b","company":"tencent","family":"PandaGPT","version":"PandaGPT","score":29.2},{"place":347,"model":"moondream2","company":"moondream","family":"Moondream","version":"Moondream2","score":28.5},{"place":348,"model":"chameleon-30b","company":"meta","family":"Chameleon","version":"Chameleon","score":27.8},{"place":349,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":24.2},{"place":350,"model":"chameleon-7b","company":"meta","family":"Chameleon","version":"Chameleon","score":19.6},{"place":351,"model":"idefics-9b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":19.5},{"place":352,"model":"moondream1","company":"moondream","family":"Moondream","version":"Moondream1","score":18.6},{"place":353,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":18.4},{"place":354,"model":"smolvlm-256m","company":"huggingface","family":"SmolVLM","version":"SmolVLM","score":14.5},{"place":355,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":13.3},{"place":356,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":10.7},{"place":357,"model":"smolvlm2-0.256b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":1.9},{"place":358,"model":"minigpt-4-v2","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v2","score":1.4},{"place":359,"model":"kosmos2","company":"microsoft","family":"Kosmos2","version":"Kosmos-2","score":0.9}]},{"id":"mmbench-v1.1-en","name":"MMBench v1.1 (EN)","topic":"Multimodal understanding (English)","description":"MMBench v1.1 English subset for evaluating multimodal LLMs.","url":"https://mmbench.opencompass.org.cn/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2307.06281","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":93.3,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":367,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.3},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":93.19},{"place":3,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":92.75},{"place":4,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.7},{"place":5,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":92.38},{"place":6,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":92.11},{"place":7,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":92.05},{"place":8,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":92.05},{"place":9,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":91.04},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.81},{"place":11,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.55},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.1},{"place":13,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":90.1},{"place":14,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":89.91},{"place":15,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.9},{"place":16,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":89.7},{"place":17,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.55},{"place":18,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.47},{"place":19,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":89.32},{"place":20,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":89.2},{"place":21,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":89},{"place":22,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89},{"place":23,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.9},{"place":24,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":88.8},{"place":25,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":88.8},{"place":26,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.5},{"place":27,"model":"jt-vl-chat-v3.0","company":"chinamobile","family":"JT","version":"JT-VL-Chat-V3.0","score":88.5},{"place":28,"model":"sensenova-v6-pro","company":"sensetime","family":"SenseNova","version":"SenseNova-V6-Pro","score":88.4},{"place":29,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.3},{"place":30,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.3},{"place":31,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":88.2},{"place":32,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":88.2},{"place":33,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":88.2},{"place":34,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.2},{"place":35,"model":"internvl2.5-78b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":87.9},{"place":36,"model":"congrong-v2.0","company":"cloudwalk","family":"CongRong","version":"CongRong-v2.0","score":87.9},{"place":37,"model":"glm-4v-plus-0111","company":"zai","family":"GLM","version":"GLM-4V-Plus (2025-01-11)","score":87.8},{"place":38,"model":"bailingmm-pro-0120","company":"antgroup","family":"BailingMM","version":"BailingMM-Pro-0120","score":87.7},{"place":39,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":87.6},{"place":40,"model":"step-1o","company":"stepfun","family":"Step","version":"Step-1o","score":87.6},{"place":41,"model":"sensenova-v6-5-pro","company":"sensetime","family":"SenseNova","version":"SenseNova-V6-5-Pro","score":87.6},{"place":42,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":87.5},{"place":43,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":87.5},{"place":44,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":87.5},{"place":45,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":87.4},{"place":46,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":87.3},{"place":47,"model":"jt-vl-chat-mini","company":"chinamobile","family":"JT","version":"JT-VL-Chat-Mini","score":87.3},{"place":48,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.1},{"place":49,"model":"rbdashmm3-dpo-38b","company":"rbdash","family":"RBDashMM3","version":"RBDashMM3-DPO","score":87.1},{"place":50,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.07},{"place":51,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":87},{"place":52,"model":"internvl3-38b","company":"opengvlab","family":"Intern","version":"InternVL3","score":87},{"place":53,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":86.9},{"place":54,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":86.9},{"place":55,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86.8},{"place":56,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":86.8},{"place":57,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.6},{"place":58,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":86.6},{"place":59,"model":"ovis2-34b","company":"alibaba","family":"Ovis","version":"Ovis2","score":86.6},{"place":60,"model":"bluelm-2.5-3b-0909","company":"vivo","family":"BlueLM","version":"BlueLM-2.5","score":86.4},{"place":61,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":86.2},{"place":62,"model":"gpt-5-mini-2025-08","company":"openai","family":"GPT","version":"GPT-5","score":86.2},{"place":63,"model":"jt-vl-chat-2b","company":"chinamobile","family":"JT","version":"JT-VL-Chat","score":86.2},{"place":64,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":86.1},{"place":65,"model":"sensenova","company":"sensetime","family":"SenseNova","version":"SenseNova","score":86.1},{"place":66,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":86},{"place":67,"model":"qwen-vl-max-0809","company":"qwen","family":"Qwen","version":"Qwen-VL","score":86},{"place":68,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":85.9},{"place":69,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":85.9},{"place":70,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":85.8},{"place":71,"model":"ovis2-16b","company":"alibaba","family":"Ovis","version":"Ovis2","score":85.8},{"place":72,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":85.53},{"place":73,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":85.5},{"place":74,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":85.5},{"place":75,"model":"ola-7b","company":"tsinghua","family":"Ola","version":"Ola","score":85.5},{"place":76,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":85.5},{"place":77,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.4},{"place":78,"model":"internvl2.5-38b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":85.4},{"place":79,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.3},{"place":80,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":85.3},{"place":81,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":85.1},{"place":82,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":85},{"place":83,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":85},{"place":84,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":84.9},{"place":85,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":84.8},{"place":86,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":84.8},{"place":87,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":84.73},{"place":88,"model":"taiyi","company":"megvii","family":"Taiyi","version":"Taiyi","score":84.7},{"place":89,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":84.7},{"place":90,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":84.6},{"place":91,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":84.5},{"place":92,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.5},{"place":93,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":84.5},{"place":94,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":84.5},{"place":95,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":84.4},{"place":96,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":84.4},{"place":97,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":84.4},{"place":98,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":84.4},{"place":99,"model":"varco-vision-2.0-14b","company":"ncsoft","family":"VARCO","version":"VARCO-VISION-2.0","score":84.4},{"place":100,"model":"internvl2.5-26b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":84.3},{"place":101,"model":"sail-vl-1.6-8b","company":"bytedance","family":"SAIL","version":"SAIL-VL-1.6","score":84.3},{"place":102,"model":"sail-vl2-8b","company":"bytedance","family":"SAIL","version":"SAIL-VL2","score":84.3},{"place":103,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":84.2},{"place":104,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":84.1},{"place":105,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.9},{"place":106,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":83.9},{"place":107,"model":"bailingmm-lite-1203","company":"antgroup","family":"BailingMM","version":"BailingMM-Lite-1203","score":83.9},{"place":108,"model":"hunyuan-standard-vision-2024-12-31","company":"tencent","family":"Hunyuan","version":"Hunyuan Vision","score":83.9},{"place":109,"model":"internvl3-14b","company":"opengvlab","family":"Intern","version":"InternVL3","score":83.9},{"place":110,"model":"ovis2-8b","company":"alibaba","family":"Ovis","version":"Ovis2","score":83.8},{"place":111,"model":"r-4b","company":"tencent","family":"R","version":"R","score":83.7},{"place":112,"model":"valley3","company":"bytedance","family":"Valley","version":"Valley3","score":83.6},{"place":113,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":83.5},{"place":114,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":83.5},{"place":115,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":83.4},{"place":116,"model":"abab7-preview","company":"minimax","family":"abab7","version":"abab7-preview","score":83.4},{"place":117,"model":"llava-onevision-72b-si","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":83.3},{"place":118,"model":"grok-2-vision-1212","company":"xai","family":"Grok","version":"Grok 2","score":83.3},{"place":119,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":83.2},{"place":120,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":83.2},{"place":121,"model":"bluelm-v-3b","company":"vivo","family":"BlueLM","version":"BlueLM-V","score":83.1},{"place":122,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":83.1},{"place":123,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":83},{"place":124,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":83},{"place":125,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":82.9},{"place":126,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":82.82},{"place":127,"model":"ovis1.6-gemma2-27b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":82.8},{"place":128,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":82.66},{"place":129,"model":"awaker2.5-vl","company":"metabrain","family":"Awaker2.5","version":"Awaker2.5-VL","score":82.6},{"place":130,"model":"sail-vl-1.5-8b","company":"bytedance","family":"SAIL","version":"SAIL-VL-1.5","score":82.5},{"place":131,"model":"wethink-qwen2.5vl-7b","company":"tencent","family":"WeThink","version":"WeThink-Qwen2.5VL","score":82.5},{"place":132,"model":"internvl2.5-8b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":82.4},{"place":133,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":82.4},{"place":134,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":82.4},{"place":135,"model":"rbdash-v1.5","company":"dlut","family":"RBDash","version":"RBDash-v1.5","score":82.3},{"place":136,"model":"varco-vision-14b","company":"ncsoft","family":"VARCO","version":"VARCO-VISION","score":82.3},{"place":137,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":82.3},{"place":138,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":82.3},{"place":139,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":82.2},{"place":140,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":82.2},{"place":141,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":82.2},{"place":142,"model":"bailingmm-mini","company":"antgroup","family":"bailingMM","version":"bailingMM-mini","score":82.1},{"place":143,"model":"valley2-dpo","company":"bytedance","family":"Valley","version":"Valley2-DPO","score":82.1},{"place":144,"model":"mug-u-7b","company":"shopee","family":"MUG","version":"MUG-U","score":81.9},{"place":145,"model":"internvl3-9b","company":"opengvlab","family":"Intern","version":"InternVL3","score":81.9},{"place":146,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":81.8},{"place":147,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":81.8},{"place":148,"model":"ovis2-4b","company":"alibaba","family":"Ovis","version":"Ovis2","score":81.8},{"place":149,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":81.6},{"place":150,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":81.6},{"place":151,"model":"telemm","company":"teleai","family":"TeleMM","version":"TeleMM","score":81.6},{"place":152,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":81.5},{"place":153,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":81.5},{"place":154,"model":"ovis1.6-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":81.5},{"place":155,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":81.5},{"place":156,"model":"valley-eagle","company":"bytedance","family":"Valley","version":"Valley-Eagle","score":81.4},{"place":157,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":81.3},{"place":158,"model":"points1.5-qwen2.5-7b","company":"tencent","family":"POINTS1.5","version":"POINTS1.5-Qwen2.5","score":81.2},{"place":159,"model":"ristretto-3b","company":"liauto","family":"Ristretto","version":"Ristretto","score":81.2},{"place":160,"model":"valley2","company":"bytedance","family":"Valley","version":"Valley2","score":81.2},{"place":161,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":81.1},{"place":162,"model":"qwen-vl-plus-0809","company":"qwen","family":"Qwen","version":"Qwen-VL","score":81.1},{"place":163,"model":"congrong","company":"cloudwalk","family":"CongRong","version":"CongRong","score":80.9},{"place":164,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":80.9},{"place":165,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":80.9},{"place":166,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":80.9},{"place":167,"model":"sail-vl2-2b","company":"bytedance","family":"SAIL","version":"SAIL-VL2","score":80.9},{"place":168,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":80.9},{"place":169,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":80.7},{"place":170,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":80.7},{"place":171,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":80.7},{"place":172,"model":"mmalaya2","company":"datacanvas","family":"MMAlaya2","version":"MMAlaya2","score":80.6},{"place":173,"model":"step-1.5v","company":"stepfun","family":"Step","version":"Step-1.5V","score":80.4},{"place":174,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":80.4},{"place":175,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":80.3},{"place":176,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":80.3},{"place":177,"model":"doubao-1.5-vision-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":80.3},{"place":178,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":80.1},{"place":179,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":80.1},{"place":180,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":80.03},{"place":181,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":80},{"place":182,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":80},{"place":183,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":80},{"place":184,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":79.9},{"place":185,"model":"step-1.5v-mini","company":"stepfun","family":"Step","version":"Step-1.5V-mini","score":79.8},{"place":186,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":79.8},{"place":187,"model":"minicpm-v-4","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V-4","score":79.8},{"place":188,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":79.8},{"place":189,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":79.8},{"place":190,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":79.7},{"place":191,"model":"omchat-v2.0-13b","company":"omai","family":"OmChat","version":"OmChat-v2.0","score":79.6},{"place":192,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":79.6},{"place":193,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":79.57},{"place":194,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":79.5},{"place":195,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":79.5},{"place":196,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":79.5},{"place":197,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":79.5},{"place":198,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":79.4},{"place":199,"model":"sail-vl-1.5-2b","company":"bytedance","family":"SAIL","version":"SAIL-VL-1.5","score":79.4},{"place":200,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":79.4},{"place":201,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":79.4},{"place":202,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":79.3},{"place":203,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":79.3},{"place":204,"model":"glm-4v","company":"zai","family":"GLM","version":"GLM-4V","score":79.2},{"place":205,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":79.2},{"place":206,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":79},{"place":207,"model":"points-yi-1.5-9b","company":"tencent","family":"POINTS","version":"POINTS-Yi-1.5","score":79},{"place":208,"model":"points-qwen2.5-7b","company":"tencent","family":"POINTS","version":"POINTS-Qwen2.5","score":79},{"place":209,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":79},{"place":210,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":79},{"place":211,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":78.9},{"place":212,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":78.8},{"place":213,"model":"bumblebee-7b-v2.2","company":"monolith","family":"Bumblebee","version":"Bumblebee","score":78.7},{"place":214,"model":"internvl2.5-4b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":78.6},{"place":215,"model":"qtunevl1.5-2b","company":"reconova","family":"QTuneVL1.5","version":"QTuneVL1.5","score":78.6},{"place":216,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":78.5},{"place":217,"model":"mirage-12b-v2.0","company":"monolith","family":"Mirage","version":"Mirage","score":78.5},{"place":218,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":78.5},{"place":219,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":78.5},{"place":220,"model":"ovis1.5-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.5-Gemma2","score":78.4},{"place":221,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":78.3},{"place":222,"model":"ovis-u1-3b","company":"alibaba","family":"Ovis","version":"Ovis-U1","score":78.3},{"place":223,"model":"aria","company":"rhymes","family":"Aria","version":"Aria","score":78.2},{"place":224,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":78.1},{"place":225,"model":"ovis1.5-llama3-8b","company":"alibaba","family":"Ovis","version":"Ovis1.5-Llama3","score":78.1},{"place":226,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":78},{"place":227,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":78},{"place":228,"model":"wemm","company":"tencent","family":"WeMM","version":"WeMM","score":77.8},{"place":229,"model":"eagle-x5-34b-chat","company":"nvidia","family":"Eagle","version":"Eagle-X5","score":77.8},{"place":230,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":77.8},{"place":231,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":77.8},{"place":232,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":77.7},{"place":233,"model":"llava-onevision-7b-si","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":77.7},{"place":234,"model":"vita-1.5","company":"nju","family":"VITA","version":"VITA-1.5","score":77.5},{"place":235,"model":"qtunevl1.5-3b","company":"reconova","family":"QTuneVL1.5","version":"QTuneVL1.5","score":77.5},{"place":236,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":77.1},{"place":237,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":77.1},{"place":238,"model":"ross-qwen2-7b","company":"casia","family":"Ross","version":"Ross-Qwen2","score":77.1},{"place":239,"model":"ovis2-2b","company":"alibaba","family":"Ovis","version":"Ovis2","score":77.1},{"place":240,"model":"flash-vl-2b-dynamic-iss","company":"meituan","family":"Flash-VL","version":"Flash-VL","score":77.1},{"place":241,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":77},{"place":242,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":77},{"place":243,"model":"xinyuan-vl","company":"cylingo","family":"XinYuan","version":"XinYuan-VL","score":76.9},{"place":244,"model":"moonshot-v1-8k","company":"moonshotai","family":"Moonshot","version":"Moonshot v1","score":76.8},{"place":245,"model":"long-vita-16k","company":"tencent","family":"VITA","version":"Long-VITA-16K","score":76.8},{"place":246,"model":"yi-vision","company":"01ai","family":"Yi","version":"Yi Vision","score":76.6},{"place":247,"model":"llava-next-qwen-32b","company":"llava","family":"LLaVA","version":"LLaVA-Next-Qwen","score":76.5},{"place":248,"model":"internvl2-8b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2","score":76.5},{"place":249,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":76.3},{"place":250,"model":"xinyuan-vl-2b-instruct","company":"cylingo","family":"XinYuan","version":"XinYuan-VL","score":76.2},{"place":251,"model":"ovis1.6-llama3.2-3b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Llama3.2","score":76.2},{"place":252,"model":"360vl-70b","company":"360","family":"360VL","version":"360VL","score":76},{"place":253,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":76},{"place":254,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":75.8},{"place":255,"model":"granite-vision-3.2-2b","company":"IBM","family":"Granite","version":"Granite-Vision-3.2","score":75.8},{"place":256,"model":"bumblebee-7b-v2.0","company":"monolith","family":"Bumblebee","version":"Bumblebee","score":75.7},{"place":257,"model":"internvl2-8b-mpo-cot","company":"opengvlab","family":"Intern","version":"InternVL2","score":75.6},{"place":258,"model":"sail-vl-2b","company":"bytedance","family":"SAIL","version":"SAIL-VL","score":75.5},{"place":259,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":75.4},{"place":260,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":75.3},{"place":261,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":75.3},{"place":262,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":75.3},{"place":263,"model":"xgen-mm-instruct-dpo-v1.5","company":"salesforce","family":"XGen","version":"XGen-MM-Instruct-DPO-v1.5","score":75.2},{"place":264,"model":"idefics3-8b-llama3","company":"huggingface","family":"IDEFICS","version":"Idefics3","score":75},{"place":265,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":74.9},{"place":266,"model":"varco-vision-2.0-1.7b","company":"ncsoft","family":"VARCO","version":"VARCO-VISION-2.0","score":74.9},{"place":267,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":74.6},{"place":268,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":74.6},{"place":269,"model":"reka-flash","company":"reka","family":"Reka","version":"Reka","score":74.5},{"place":270,"model":"llava-cot","company":"llava","family":"LLaVA","version":"LLaVA-CoT","score":74.4},{"place":271,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":74.1},{"place":272,"model":"granite-vision-3.1-2b-preview","company":"IBM","family":"Granite","version":"Granite-Vision-3.1","score":74.1},{"place":273,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":74},{"place":274,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":73.9},{"place":275,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":73.9},{"place":276,"model":"llama-3-mixsense-v1.1","company":"zerovision","family":"Llama","version":"Llama-3-MixSense-v1.1","score":73.7},{"place":277,"model":"bluelm-2.5-3b","company":"vivo","family":"BlueLM","version":"BlueLM-2.5","score":73.7},{"place":278,"model":"bumblebee-7b-v1.6","company":"monolith","family":"Bumblebee","version":"Bumblebee","score":73.6},{"place":279,"model":"mantis-8b-idefics2","company":"tiger-lab","family":"Mantis","version":"Mantis","score":73.6},{"place":280,"model":"llama-3-mixsense","company":"zerovision","family":"Llama","version":"Llama-3-MixSense","score":73.5},{"place":281,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":73.2},{"place":282,"model":"llava-next-interleave-7b","company":"llava","family":"LLaVA","version":"LLaVA-Next-Interleave","score":72.8},{"place":283,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":72.7},{"place":284,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":72.7},{"place":285,"model":"mini-internvl-chat-4b-v1.5","company":"opengvlab","family":"Intern","version":"Mini-InternVL-Chat","score":72.6},{"place":286,"model":"qtunevl1-2b","company":"reconova","family":"QTuneVL1","version":"QTuneVL1","score":72.6},{"place":287,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":72.5},{"place":288,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":72.4},{"place":289,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":72.3},{"place":290,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":72.2},{"place":291,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":72.2},{"place":292,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":72.2},{"place":293,"model":"xverse-v-13b","company":"xverse","family":"XVERSE","version":"XVERSE-V","score":72.1},{"place":294,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":72.1},{"place":295,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":72.1},{"place":296,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":72},{"place":297,"model":"llava-internlm2-7b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-7B (QLoRA)","score":71.9},{"place":298,"model":"internvl2.5-2b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":71.9},{"place":299,"model":"vila1.5-13b","company":"nvidia","family":"VILA","version":"VILA1.5","score":71.8},{"place":300,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":71.7},{"place":301,"model":"llava-next-interleave-7b-dpo","company":"llava","family":"LLaVA","version":"LLaVA-Next-Interleave","score":71.7},{"place":302,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":71.7},{"place":303,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":71.6},{"place":304,"model":"cambrian-13b","company":"nyu","family":"Cambrian","version":"Cambrian","score":71.4},{"place":305,"model":"granite-vision-3.3-2b","company":"IBM","family":"Granite","version":"Granite-Vision-3.3","score":71.3},{"place":306,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":71.1},{"place":307,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":70.8},{"place":308,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":70.5},{"place":309,"model":"internlm-xcomposer2-1.8b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2","score":70.4},{"place":310,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":70.4},{"place":311,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":70.3},{"place":312,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":70.2},{"place":313,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":70.2},{"place":314,"model":"ovis2-1b","company":"alibaba","family":"Ovis","version":"Ovis2","score":70.1},{"place":315,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":70},{"place":316,"model":"eagle-x5-13b","company":"nvidia","family":"Eagle","version":"Eagle-X5","score":70},{"place":317,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":318,"model":"internvl3-1b","company":"opengvlab","family":"Intern","version":"InternVL3","score":69.9},{"place":319,"model":"monkey-chat","company":"hust","family":"Monkey","version":"Monkey-Chat","score":69.6},{"place":320,"model":"minimonkey","company":"hust","family":"Monkey","version":"MiniMonkey","score":69.6},{"place":321,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":69.6},{"place":322,"model":"omnilmm-12b","company":"openbmb","family":"OmniLMM","version":"OmniLMM","score":69.2},{"place":323,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":69.1},{"place":324,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":69.1},{"place":325,"model":"slime-8b","company":"casia","family":"Slime","version":"Slime","score":69},{"place":326,"model":"parrot-7b","company":"alibaba","family":"Parrot","version":"Parrot","score":68.8},{"place":327,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":68.7},{"place":328,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":68.7},{"place":329,"model":"falcon2-vlm-11b","company":"tii","family":"Falcon2","version":"Falcon2-VLM","score":68.7},{"place":330,"model":"h2ovl-2b","company":"h2oai","family":"H2OVL","version":"H2OVL","score":68.7},{"place":331,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.5},{"place":332,"model":"llava-llama-3-8b","company":"llava","family":"LLaVA","version":"LLaVA-LLaMA-3","score":68.5},{"place":333,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":68.4},{"place":334,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":68.4},{"place":335,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":68.3},{"place":336,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":68.2},{"place":337,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68},{"place":338,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":67.9},{"place":339,"model":"transcore-m","company":"pci","family":"TransCore","version":"TransCore-M","score":67.7},{"place":340,"model":"moondream2","company":"moondream","family":"Moondream","version":"Moondream2","score":67.7},{"place":341,"model":"sharegpt4v-13b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":67.5},{"place":342,"model":"mini-internvl-chat-2b-v1.5","company":"opengvlab","family":"Intern","version":"Mini-InternVL-Chat","score":67.5},{"place":343,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":67.5},{"place":344,"model":"eagle-x5-7b","company":"nvidia","family":"Eagle","version":"Eagle-X5","score":67.4},{"place":345,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":67.3},{"place":346,"model":"internvl2.5-1b-mpo","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":67.2},{"place":347,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":67},{"place":348,"model":"llava-v1.5-13b-qlora","company":"internlm","family":"LLaVA","version":"LLaVA-v1.5-13B (QLoRA)","score":67},{"place":349,"model":"vintern-3b-beta","company":"fifth-civil-defender","family":"Vintern","version":"Vintern","score":67},{"place":350,"model":"llava-1.6-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":66.5},{"place":351,"model":"llava-1.6-mistral-7b","company":"llava","family":"LLaVA","version":"LLaVA-1.6-Mistral","score":66.5},{"place":352,"model":"mantis-8b-siglip-llama3","company":"tiger-lab","family":"Mantis","version":"Mantis","score":66.1},{"place":353,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.1},{"place":354,"model":"llava-internlm-7b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM-7B (QLoRA)","score":66},{"place":355,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":65.9},{"place":356,"model":"aki-4b","company":"sony","family":"AKI","version":"AKI","score":65.9},{"place":357,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":65.8},{"place":358,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":65.6},{"place":359,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":65.4},{"place":360,"model":"hawkvl-2b","company":"reconova","family":"HawkVL","version":"HawkVL","score":65.3},{"place":361,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":65.2},{"place":362,"model":"llava-v1.5-7b-qlora","company":"internlm","family":"LLaVA","version":"LLaVA-v1.5-7B (QLoRA)","score":64.7},{"place":363,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":64.6},{"place":364,"model":"smolvlm-instruct","company":"huggingface","family":"SmolVLM","version":"SmolVLM-Instruct","score":64.4},{"place":365,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":64.4},{"place":366,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":64.3},{"place":367,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":64.2},{"place":368,"model":"sharecaptioner","company":"internlm","family":"InternLM","version":"ShareCaptioner","score":63.9},{"place":369,"model":"mantis-8b-clip-llama3","company":"tiger-lab","family":"Mantis","version":"Mantis","score":63.8},{"place":370,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":63.6},{"place":371,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":63.6},{"place":372,"model":"reka-edge","company":"reka","family":"Reka","version":"Reka","score":63.6},{"place":373,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":63.5},{"place":374,"model":"vila1.5-3b","company":"nvidia","family":"VILA","version":"VILA 1.5","score":63.1},{"place":375,"model":"slime-7b","company":"casia","family":"Slime","version":"Slime","score":63.1},{"place":376,"model":"slime-13b","company":"casia","family":"Slime","version":"Slime","score":62.9},{"place":377,"model":"smolvlm-instruct-dpo","company":"huggingface","family":"SmolVLM","version":"SmolVLM-Instruct-DPO","score":62.6},{"place":378,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":62.3},{"place":379,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":61.6},{"place":380,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":61.4},{"place":381,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":61.3},{"place":382,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":60.8},{"place":383,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":60.5},{"place":384,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":60.1},{"place":385,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":60},{"place":386,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":59.6},{"place":387,"model":"moondream1","company":"moondream","family":"Moondream","version":"Moondream1","score":59.6},{"place":388,"model":"emu3-chat","company":"baai","family":"Emu","version":"Emu3-Chat","score":59.3},{"place":389,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":58},{"place":390,"model":"llama-3-vila1.5-8b","company":"nvidia","family":"LLaVA","version":"Llama-3-VILA1.5","score":57.9},{"place":391,"model":"abab6.5s","company":"minimax","family":"abab6.5s","version":"abab6.5s","score":57.9},{"place":392,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":57.4},{"place":393,"model":"mmalaya","company":"datacanvas","family":"MMAlaya","version":"MMAlaya","score":55.7},{"place":394,"model":"vintern-1b-v2","company":"fifth-civil-defender","family":"Vintern","version":"Vintern","score":54.6},{"place":395,"model":"h2ovl-800m","company":"h2oai","family":"H2OVL","version":"H2OVL","score":53.9},{"place":396,"model":"llava-onevision-0.5b-si","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":53},{"place":397,"model":"smolvlm-synthetic","company":"huggingface","family":"SmolVLM","version":"SmolVLM-Synthetic","score":51},{"place":398,"model":"janus-1.3b","company":"deepseek","family":"Janus","version":"Janus","score":50.2},{"place":399,"model":"smolvlm-500m","company":"huggingface","family":"SmolVLM","version":"SmolVLM","score":50},{"place":400,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":49.8},{"place":401,"model":"mantis-8b-fuyu","company":"tiger-lab","family":"Mantis","version":"Mantis","score":44.1},{"place":402,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":41.6},{"place":403,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":41.6},{"place":404,"model":"pandagpt-13b","company":"tencent","family":"PandaGPT","version":"PandaGPT","score":39.7},{"place":405,"model":"smolvlm-256m","company":"huggingface","family":"SmolVLM","version":"SmolVLM","score":39.4},{"place":406,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":38.4},{"place":407,"model":"chameleon-30b","company":"meta","family":"Chameleon","version":"Chameleon","score":37.6},{"place":408,"model":"visualglm","company":"zai","family":"GLM","version":"VisualGLM","score":36.7},{"place":409,"model":"idefics-9b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":35.2},{"place":410,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":30.9},{"place":411,"model":"chameleon-7b","company":"meta","family":"Chameleon","version":"Chameleon","score":19.9},{"place":412,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":11.3},{"place":413,"model":"smolvlm2-0.256b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":11},{"place":414,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":7.51},{"place":415,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":6.4},{"place":416,"model":"minigpt-4-v2","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v2","score":5},{"place":417,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":2.4},{"place":418,"model":"kosmos2","company":"microsoft","family":"Kosmos2","version":"Kosmos-2","score":1.2}]},{"id":"mmbench-v1.1-en-dev","name":"MMBench v1.1 (EN dev)","topic":"General VQA","description":"English dev split of MMBench v1.1 measuring multimodal question answering.","url":"https://mmbench.opencompass.org.cn/home","leaderboard":"https://mmbench.opencompass.org.cn/leaderboard","github":"https://github.com/open-compass/MMBench","paper":"https://arxiv.org/abs/2307.06281","metric":"percent","stars":"","top_model":"Kimi-K2.5","top_percent":94.2,"top_model_id":"kimi-k2.5","top_generation":"Kimi K2.5","top_model_base":"Kimi K2.5","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":80,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":94.2},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.7},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.7},{"place":4,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.8},{"place":5,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.8},{"place":6,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":92.8},{"place":7,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.6},{"place":8,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.3},{"place":9,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.5},{"place":10,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":90.9},{"place":11,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.6},{"place":12,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.29},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.1},{"place":14,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.1},{"place":15,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":89.9},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.78},{"place":17,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.7},{"place":18,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.4},{"place":19,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.2},{"place":20,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":89},{"place":21,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.9},{"place":22,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.9},{"place":23,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":88.8},{"place":24,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.6},{"place":25,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88.3},{"place":26,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":88.2},{"place":27,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":87.54},{"place":28,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87},{"place":29,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":86.8},{"place":30,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.7},{"place":31,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":86.5},{"place":32,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.3},{"place":33,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":85.9},{"place":34,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.1},{"place":35,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":85},{"place":36,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85},{"place":37,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":84.9},{"place":38,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":84.2},{"place":39,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":83.4},{"place":40,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.3},{"place":41,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":83.16},{"place":42,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":82.8},{"place":43,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.7},{"place":44,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":82.47},{"place":45,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":82.4},{"place":46,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.4},{"place":47,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.9},{"place":48,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":81.8},{"place":49,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":81.1},{"place":50,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":81.1},{"place":51,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":81},{"place":52,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":80.6},{"place":53,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":80.41},{"place":54,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":80.3},{"place":55,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":80},{"place":56,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":79.81},{"place":57,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":79.5},{"place":58,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":79.2},{"place":59,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":78.7},{"place":60,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":78.6},{"place":61,"model":"blip-3o-4b","company":"salesforce","family":"BLIP","version":"BLIP-3O","score":78.6},{"place":62,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":78.5},{"place":63,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.4},{"place":64,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.18},{"place":65,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":78.1},{"place":66,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":77.92},{"place":67,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.8},{"place":68,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":77.2},{"place":69,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":76.4},{"place":70,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.2},{"place":71,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76},{"place":72,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":75.5},{"place":73,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":74.8},{"place":74,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.4},{"place":75,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.1},{"place":76,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":73.1},{"place":77,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":72.4},{"place":78,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.6},{"place":79,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":80,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":69.6},{"place":81,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":69.6},{"place":82,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.3},{"place":83,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":69.24},{"place":84,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":69.2},{"place":85,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":68.7},{"place":86,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":68.56},{"place":87,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":67.4},{"place":88,"model":"harmon-1.5b","company":"harmonai","family":"Harmon","version":"Harmon-1.5B","score":65.5},{"place":89,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.2},{"place":90,"model":"vila1.5-3b","company":"nvidia","family":"VILA","version":"VILA 1.5","score":61.7},{"place":91,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":60.91},{"place":92,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":58.5},{"place":93,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":56.27},{"place":94,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":52.32},{"place":95,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":51.6}]},{"id":"mmbench-video","name":"MMBench-Video","topic":"Video QA","description":"Long-form multi-shot video understanding with GPT-4-judged free-form answers; overall mean score on a 0-3 scale.","url":"https://github.com/open-compass/MMBench-Video","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2406.14515","metric":"score","stars":"","top_model":"InternVL2.5-78B","top_percent":1.97,"top_model_id":"internvl2.5-78b","top_generation":"InternVL2.5","top_model_base":"InternVL2.5-78B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":1.97},{"place":2,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":1.87},{"place":3,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":1.86},{"place":4,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":1.82},{"place":5,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":1.78},{"place":6,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":1.73},{"place":7,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":1.71},{"place":8,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":1.7},{"place":9,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1.7},{"place":10,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":1.68},{"place":11,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":1.67},{"place":12,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":1.63},{"place":13,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":1.61},{"place":14,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":1.57},{"place":15,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":1.53},{"place":16,"model":"oryx-1.5-32b","company":"tsinghua","family":"Oryx","version":"Oryx-1.5","score":1.52},{"place":17,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":1.45},{"place":18,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":1.44},{"place":19,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1.44},{"place":20,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":1.36},{"place":21,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":1.3},{"place":22,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":1.3},{"place":23,"model":"videochat2-hd-mistral","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":1.22},{"place":24,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":1.14}]},{"id":"mmc-benchmark","name":"MMC-Benchmark","topic":"Chart understanding","description":"MMC multimodal chart understanding benchmark.","url":"https://github.com/FuxiaoLiu/MMC","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2311.10774","metric":"percent","stars":"","top_model":"Qwen-VL-Max","top_percent":76.4,"top_model_id":"qwen-vl-max","top_generation":"Qwen-VL","top_model_base":"Qwen-VL-Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":76.4},{"place":2,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":74.7},{"place":3,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":74},{"place":4,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":72.8},{"place":5,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":69.6},{"place":6,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":68.9},{"place":7,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":64.4},{"place":8,"model":"vila-13b","company":"nvidia","family":"VILA","version":"VILA","score":64.3},{"place":9,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":61.9},{"place":10,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":61.3},{"place":11,"model":"llava-next-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":60},{"place":12,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":56.7},{"place":13,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":53.8},{"place":14,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":45.9}]},{"id":"mmdu","name":"MMDU","topic":"Multi-turn multi-image dialog","description":"Multi-turn, multi-image dialog understanding benchmark with GPT-4o-judged scores.","url":"","leaderboard":"","github":"https://github.com/Liuziyu77/MMDU","paper":"https://arxiv.org/abs/2406.11833","metric":"percent","stars":"","top_model":"GPT-4V(ision)","top_percent":66.3,"top_model_id":"gpt-4v","top_generation":"GPT-4V","top_model_base":"GPT-4V","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":66.3},{"place":2,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":56.6}]},{"id":"mme-cc","name":"MME-CC","topic":"Multimodal evaluation","description":"MME-CC multimodal evaluation suite.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":56.9,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.9},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":43.4},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":42.7},{"place":4,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":33.7},{"place":5,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":27.5}]},{"id":"mme-elo","name":"MME Elo","topic":"Multimodal perception","description":"Elo-style scoring for the MME multimodal evaluation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"points","stars":"","top_model":"InternVL2.5-78B","top_percent":2494.5,"top_model_id":"internvl2.5-78b","top_generation":"InternVL2.5","top_model_base":"InternVL2.5-78B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":86,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":2494.5},{"place":2,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":2482.7},{"place":3,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":2482.7},{"place":4,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":2455.8},{"place":5,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":2433.6},{"place":6,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2414.7},{"place":7,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":2373.3},{"place":8,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":2348.4},{"place":9,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":2344.1},{"place":10,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":2337.5},{"place":11,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":2329},{"place":12,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":2328.7},{"place":13,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":2328.7},{"place":14,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":2327},{"place":15,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":2326.8},{"place":16,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":2326.8},{"place":17,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":2310.3},{"place":18,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":2307.5},{"place":19,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":2281.7},{"place":20,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":2275},{"place":21,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":2261},{"place":22,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2260.7},{"place":23,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2259},{"place":24,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":2253},{"place":25,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":2242.7},{"place":26,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":2229},{"place":27,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":2220.4},{"place":28,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2215.1},{"place":29,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2210.3},{"place":30,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2210},{"place":31,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":2206.4},{"place":32,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":2204.9},{"place":33,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":2194.2},{"place":34,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":2189.6},{"place":35,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":2189.1},{"place":36,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":2187.8},{"place":37,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":2186.9},{"place":38,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":2186.4},{"place":39,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":2183.4},{"place":40,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":2183.3},{"place":41,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":2175.4},{"place":42,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":2163.8},{"place":43,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":2163.29},{"place":44,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":2148.9},{"place":45,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":2148.9},{"place":46,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":2141},{"place":47,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":2138.2},{"place":48,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":2128.83},{"place":49,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":2123},{"place":50,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":2110.6},{"place":51,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":2110},{"place":52,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":2070.2},{"place":53,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":2070.2},{"place":54,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":2069},{"place":55,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2060},{"place":56,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2059.8},{"place":57,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":2050.9},{"place":58,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":2050.2},{"place":59,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":2050.2},{"place":60,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":2050},{"place":61,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":2049.9},{"place":62,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":2028},{"place":63,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":2024.6},{"place":64,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":2018.8},{"place":65,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":2006.5},{"place":66,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":2006},{"place":67,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":2003.4},{"place":68,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":2003.4},{"place":69,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":1998},{"place":70,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":1971.5},{"place":71,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":1950.5},{"place":72,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":1933.4},{"place":73,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":1933.3},{"place":74,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":1927},{"place":75,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":1926.6},{"place":76,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":1926.5},{"place":77,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":1920.3},{"place":78,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1920},{"place":79,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1920},{"place":80,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":1915.1},{"place":81,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":1915},{"place":82,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":1877},{"place":83,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":1876.8},{"place":84,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1872},{"place":85,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1872},{"place":86,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":1870},{"place":87,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":1869.5},{"place":88,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":1861},{"place":89,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":1860},{"place":90,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":1847.6},{"place":91,"model":"llava-llama-3-8b","company":"llava","family":"LLaVA","version":"LLaVA-LLaMA-3","score":1818},{"place":92,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":1809},{"place":93,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":1808.6},{"place":94,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":1802.9},{"place":95,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":1798},{"place":96,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":1794.4},{"place":97,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":1794},{"place":98,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":1792.5},{"place":99,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":1781},{"place":100,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":1771.5},{"place":101,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":1765.4},{"place":102,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":1737},{"place":103,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":1736.6},{"place":104,"model":"mini-gemini-2b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini","score":1653},{"place":105,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":1650.2},{"place":106,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":1625.9},{"place":107,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":1611},{"place":108,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":1586.8},{"place":109,"model":"phi-3-vision-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":1537.5},{"place":110,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":1531.6},{"place":111,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":1478},{"place":112,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":1453.2},{"place":113,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":1438}]},{"id":"mme-realworld-cn","name":"MME-RealWorld (cn)","topic":"Real-world perception (CN)","description":"MME-RealWorld Chinese split.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Flash","top_percent":72.62,"top_model_id":"gemini-3-flash","top_generation":"Gemini 3","top_model_base":"Gemini 3 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":72.62},{"place":2,"model":"skywork-r1v4","company":"skywork","family":"Skywork","version":"Skywork R1V4","score":70.8},{"place":3,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":70.59},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.3},{"place":5,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.8},{"place":6,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":68.4},{"place":7,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":68.09},{"place":8,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":66.96},{"place":9,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.67},{"place":10,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.29},{"place":11,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.7},{"place":12,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.63},{"place":13,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":63.5},{"place":14,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.3},{"place":15,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.2},{"place":16,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":60.71},{"place":17,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":59.8},{"place":18,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":59.78},{"place":19,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":58.5},{"place":20,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":58.5},{"place":21,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":58.3},{"place":22,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":56.23},{"place":23,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":55.57},{"place":24,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":55.5},{"place":25,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":55},{"place":26,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":51.2},{"place":27,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":47.9},{"place":28,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":40.6}]},{"id":"mme-realworld-en","name":"MME-RealWorld (en)","topic":"Real-world perception (EN)","description":"MME-RealWorld English split.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Flash","top_percent":74.86,"top_model_id":"gemini-3-flash","top_generation":"Gemini 3","top_model_base":"Gemini 3 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":48,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":74.86},{"place":2,"model":"sensenova-mars-32b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":72.7},{"place":3,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.6},{"place":4,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":71.51},{"place":5,"model":"skywork-r1v4","company":"skywork","family":"Skywork","version":"Skywork R1V4","score":71.4},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.3},{"place":7,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":69.87},{"place":8,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":68.52},{"place":9,"model":"sensenova-mars-8b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":67.9},{"place":10,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.7},{"place":11,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.07},{"place":12,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":66.21},{"place":13,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":66.04},{"place":14,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.96},{"place":15,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":64.04},{"place":16,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":64},{"place":17,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.47},{"place":18,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":63.4},{"place":19,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63},{"place":20,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":63},{"place":21,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":62.9},{"place":22,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":62.8},{"place":23,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.9},{"place":24,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":61.8},{"place":25,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":61.8},{"place":26,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":61.5},{"place":27,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":60.9},{"place":28,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":60.8},{"place":29,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":59.1},{"place":30,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":59.1},{"place":31,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":59.1},{"place":32,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":58.7},{"place":33,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":58.16},{"place":34,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":57.5},{"place":35,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":57.4},{"place":36,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":57.4},{"place":37,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":57.4},{"place":38,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":56.8},{"place":39,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":56.5},{"place":40,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":56.1},{"place":41,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":55.3},{"place":42,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":53.5},{"place":43,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":52.1},{"place":44,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":51.9},{"place":45,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.6},{"place":46,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":50.8},{"place":47,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":49.4},{"place":48,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":48.8},{"place":49,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":47.3},{"place":50,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":45.2},{"place":51,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":44.2},{"place":52,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":44.1},{"place":53,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":40.2},{"place":54,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":38.2}]},{"id":"mmhal-bench","name":"MMHal-Bench (Score)","topic":"Multimodal hallucination","description":"MMHal-Bench GPT-judged response quality score (0-6) for hallucination in vision-language models.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2309.14525","metric":"score","stars":"","top_model":"Qwen3.8-27B","top_percent":5.03,"top_model_id":"qwen3.8-27b","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 27B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":5.03},{"place":2,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":4.96},{"place":3,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":4.72},{"place":4,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":4.7},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4.7},{"place":6,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":4.7},{"place":7,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":4.6},{"place":8,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.6},{"place":9,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":4.6},{"place":10,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":4.34},{"place":11,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":4.2},{"place":12,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.18},{"place":13,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":4},{"place":14,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":3.89},{"place":15,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":3.83},{"place":16,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":3.8},{"place":17,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":3.75},{"place":18,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":3.71},{"place":19,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":3.7},{"place":20,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":3.65},{"place":21,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.6},{"place":22,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":3.6},{"place":23,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":3.55},{"place":24,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.49},{"place":25,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":3.4},{"place":26,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":3.33},{"place":27,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":3.31},{"place":28,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":3.17},{"place":29,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":3.11},{"place":30,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":2.94},{"place":31,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":2.9},{"place":32,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":2.75},{"place":33,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":2.7},{"place":34,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.7},{"place":35,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.62},{"place":36,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":2.52},{"place":37,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.5},{"place":38,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":2.49},{"place":39,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":2.25}]},{"id":"mmhal-bench-hallucination-rate","name":"MMHal-Bench (Hallucination Rate)","topic":"Multimodal hallucination","description":"MMHal-Bench hallucination rate of vision-language model responses; lower is better.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2309.14525","metric":"percent","stars":"","top_model":"MiniCPM-V 4.7 35B-A3B","top_percent":21.88,"top_model_id":"minicpm-v-4.7-35b-a3b","top_generation":"MiniCPM V 4.7","top_model_base":"MiniCPM-V 4.7 35B A3B","top_model_family":"MiniCPM","top_company":"openbmb","top_open_source":1,"lower_is_better":true,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":21.88},{"place":2,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":21.88},{"place":3,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":21.88},{"place":4,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":22.92},{"place":5,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":23.9},{"place":6,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":24.3},{"place":7,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":25},{"place":8,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":25},{"place":9,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":26.04},{"place":10,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.08},{"place":11,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":28.1},{"place":12,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":29.9},{"place":13,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":30.6},{"place":14,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":31.6},{"place":15,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":32.3},{"place":16,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":33.3},{"place":17,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.33},{"place":18,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":34.7},{"place":19,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.62},{"place":20,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.7},{"place":21,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.7},{"place":22,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50},{"place":23,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":59.4}]},{"id":"mmiu","name":"MMIU","topic":"Multi-image understanding","description":"Multi-image understanding benchmark evaluating cross-image reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":72.1,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":40,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.1},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":71},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.9},{"place":4,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":64.5},{"place":5,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":62.4},{"place":6,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":62.4},{"place":7,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.2},{"place":8,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":55.8},{"place":9,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":55.7},{"place":10,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":55.5},{"place":11,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":55.3},{"place":12,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":54.6},{"place":13,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":54.2},{"place":14,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.1},{"place":15,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":53.4},{"place":16,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":53.4},{"place":17,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":51.7},{"place":18,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":51.7},{"place":19,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":50.3},{"place":20,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":49.4},{"place":21,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":49.4},{"place":22,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":49.2},{"place":23,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":48.4},{"place":24,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":47.9},{"place":25,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":46.7},{"place":26,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":46.5},{"place":27,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":44.2},{"place":28,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":43.8},{"place":29,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":43.5},{"place":30,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":43.3},{"place":31,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.2},{"place":32,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":42.6},{"place":33,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":42},{"place":34,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":40.6},{"place":35,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":39.8},{"place":36,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":38.5},{"place":37,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":37.4},{"place":38,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":37.3},{"place":39,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":35.3},{"place":40,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":27.4}]},{"id":"mmlb-niah-128k","name":"MMLB-NIAH (128k)","topic":"Multimodal long-context","description":"MMLB-NIAH 128k long-context multimodal benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":72.2,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":72.2},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.5},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.9},{"place":4,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":62.4}]},{"id":"mmlb-vrag-128k","name":"MMLB-VRAG (128k)","topic":"Multimodal long-context","description":"MMLB-VRAG 128k long-context multimodal benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":88.9,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88.9},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":83.2},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.6},{"place":4,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":75.4}]},{"id":"mmlongbench-128k","name":"MMLongBench-128K","topic":"Long-context multimodal","description":"128K-context variant of MMLongBench evaluating multimodal long-context understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":78.3,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":78.3},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":76.9},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.7},{"place":4,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":64.1},{"place":5,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":63.4}]},{"id":"mmlongbench-doc","name":"MMLongBench-Doc","topic":"Long-context multimodal documents","description":"Evaluates long-context document understanding with mixed text, tables, and figures across multiple pages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Flash-Next","top_percent":67.9,"top_model_id":"qwen3.8-flash-next","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Flash Next","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":52,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67.9},{"place":2,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":65.8},{"place":3,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.7},{"place":4,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":62.82},{"place":5,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62},{"place":6,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.9},{"place":7,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.5},{"place":8,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":60.77},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":60.5},{"place":10,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":60.26},{"place":11,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.2},{"place":12,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.5},{"place":13,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":14,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":58.61},{"place":15,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":58.51},{"place":16,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":58.5},{"place":17,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.7},{"place":18,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":57.5},{"place":19,"model":"nemotron-3-nano-omni-30b-a3b-reasoning","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":57.5},{"place":20,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":56.6},{"place":21,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.2},{"place":22,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.2},{"place":23,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.6},{"place":24,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":55.6},{"place":25,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.4},{"place":26,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":54.9},{"place":27,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":54.5},{"place":28,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.2},{"place":29,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":53.6},{"place":30,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":53},{"place":31,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":52.7},{"place":32,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":52.6},{"place":33,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":52},{"place":34,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":51.5},{"place":35,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.5},{"place":36,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":50.3},{"place":37,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":49.06},{"place":38,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.9},{"place":39,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.4},{"place":40,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":46.5},{"place":41,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.4},{"place":42,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":44.7},{"place":43,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.4},{"place":44,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.5},{"place":45,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":42.4},{"place":46,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":42.1},{"place":47,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":42.1},{"place":48,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":38.3},{"place":49,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":38},{"place":50,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":33.8},{"place":51,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.6},{"place":52,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":31.8},{"place":53,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":31.8},{"place":54,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":31.6},{"place":55,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":28.4},{"place":56,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":22.1}]},{"id":"mmlu","name":"MMLU","topic":"Multi-domain knowledge","description":"57 tasks spanning STEM, humanities, social sciences; broad knowledge and reasoning.","url":"https://github.com/hendrycks/test","leaderboard":"https://www.kaggle.com/benchmarks/open-benchmarks/mmlu","github":"https://github.com/hendrycks/test","paper":"https://arxiv.org/abs/2009.03300","metric":"percent","stars":"1488","top_model":"Gemini 4 Argon","top_percent":95.25,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":760,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":95.25},{"place":2,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":94.54},{"place":3,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":94.52},{"place":4,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":94.42},{"place":5,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":94.17},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":94.16},{"place":7,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":93.97},{"place":8,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":93.94},{"place":9,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":93.86},{"place":10,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":93.83},{"place":11,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":93.8},{"place":12,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.8},{"place":13,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":93.6},{"place":14,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":93.5},{"place":15,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":93.5},{"place":16,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":93.48},{"place":17,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":93.4},{"place":18,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":93.4},{"place":19,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":93.39},{"place":20,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":93.3},{"place":21,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":93.1},{"place":22,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":93.01},{"place":23,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":92.9},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.9},{"place":25,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":92.83},{"place":26,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":92.8},{"place":27,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":92.8},{"place":28,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":92.7},{"place":29,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.4},{"place":30,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.4},{"place":31,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.36},{"place":32,"model":"o3","company":"openai","family":"o3","version":"o3","score":92.3},{"place":33,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":92.3},{"place":34,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":92.3},{"place":35,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":92.27},{"place":36,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":91.92},{"place":37,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":91.9},{"place":38,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":91.89},{"place":39,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":91.82},{"place":40,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":91.8},{"place":41,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":91.7},{"place":42,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":91.7},{"place":43,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":91.65},{"place":44,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":91.6},{"place":45,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":91.6},{"place":46,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":91.5},{"place":47,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":91.4},{"place":48,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":91.4},{"place":49,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":91.39},{"place":50,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":91.25},{"place":51,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":90.94},{"place":52,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":90.6},{"place":53,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":90.5},{"place":54,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":90.4},{"place":55,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":90.31},{"place":56,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":90.31},{"place":57,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":90.3},{"place":58,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":90.3},{"place":59,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":90.3},{"place":60,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":90.3},{"place":61,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":90.3},{"place":62,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":90.2},{"place":63,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":90.2},{"place":64,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":90.17},{"place":65,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":90.11},{"place":66,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":90.1},{"place":67,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.1},{"place":68,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.1},{"place":69,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.1},{"place":70,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":90.04},{"place":71,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":90},{"place":72,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":90},{"place":73,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":90},{"place":74,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":89.9},{"place":75,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":89.9},{"place":76,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":89.62},{"place":77,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89.51},{"place":78,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89.5},{"place":79,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":89.5},{"place":80,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89.5},{"place":81,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":89.5},{"place":82,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.5},{"place":83,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":89.48},{"place":84,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89.4},{"place":85,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":89.4},{"place":86,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":89.28},{"place":87,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":89.2},{"place":88,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":89.16},{"place":89,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.08},{"place":90,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.92},{"place":91,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":88.83},{"place":92,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.8},{"place":93,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.8},{"place":94,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.7},{"place":95,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.7},{"place":96,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":88.7},{"place":97,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":88.6},{"place":98,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":88.6},{"place":99,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":88.6},{"place":100,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.5},{"place":101,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":88.5},{"place":102,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":88.5},{"place":103,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.4},{"place":104,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":88.4},{"place":105,"model":"seed1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":88.35},{"place":106,"model":"glm-5-base","company":"zai","family":"GLM","version":"GLM 5","score":88.3},{"place":107,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":88.3},{"place":108,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":88.24},{"place":109,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":88.2},{"place":110,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":88.1},{"place":111,"model":"glm-5.3-flash-base","company":"zai","family":"GLM","version":"GLM 5.3","score":88.1},{"place":112,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":88.09},{"place":113,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":88.01},{"place":114,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":88},{"place":115,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":88},{"place":116,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":88},{"place":117,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":88},{"place":118,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":88},{"place":119,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":88},{"place":120,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":87.98},{"place":121,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87.9},{"place":122,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":87.9},{"place":123,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":87.9},{"place":124,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":87.82},{"place":125,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":87.81},{"place":126,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":87.8},{"place":127,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":87.8},{"place":128,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":87.8},{"place":129,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":87.8},{"place":130,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":87.8},{"place":131,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":87.73},{"place":132,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":87.73},{"place":133,"model":"gpt-oss-120b-2025-08-05","company":"openai","family":"GPT","version":"GPT-OSS","score":87.7},{"place":134,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":87.7},{"place":135,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":87.69},{"place":136,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":87.69},{"place":137,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.68},{"place":138,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.6},{"place":139,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":87.6},{"place":140,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":87.6},{"place":141,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":87.42},{"place":142,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":87.4},{"place":143,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":87.4},{"place":144,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":87.35},{"place":145,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":87.3},{"place":146,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":87.3},{"place":147,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":87.3},{"place":148,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.26},{"place":149,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.2},{"place":150,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":87.2},{"place":151,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":87.2},{"place":152,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.19},{"place":153,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.13},{"place":154,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":87.1},{"place":155,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87.1},{"place":156,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.09},{"place":157,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":87},{"place":158,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":87},{"place":159,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":86.9},{"place":160,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":86.9},{"place":161,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":86.9},{"place":162,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.87},{"place":163,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":86.82},{"place":164,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.8},{"place":165,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":86.8},{"place":166,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":86.7},{"place":167,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":86.7},{"place":168,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":86.6},{"place":169,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.5},{"place":170,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":86.5},{"place":171,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":86.5},{"place":172,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.5},{"place":173,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":86.5},{"place":174,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":86.4},{"place":175,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":86.4},{"place":176,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":86.4},{"place":177,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":86.3},{"place":178,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":86.2},{"place":179,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":86.11},{"place":180,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":86.1},{"place":181,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.1},{"place":182,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.1},{"place":183,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":86.03},{"place":184,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.01},{"place":185,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":86},{"place":186,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":86},{"place":187,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":85.9},{"place":188,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":85.9},{"place":189,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":85.88},{"place":190,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.8},{"place":191,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":85.8},{"place":192,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.6},{"place":193,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.6},{"place":194,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":85.52},{"place":195,"model":"llama-4-maverick-17b-128e-base","company":"meta","family":"Llama","version":"Llama 4","score":85.5},{"place":196,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":85.5},{"place":197,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.5},{"place":198,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.5},{"place":199,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":85.5},{"place":200,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.4},{"place":201,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.4},{"place":202,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":85.4},{"place":203,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":85.31},{"place":204,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.3},{"place":205,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":85.3},{"place":206,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":85.3},{"place":207,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.3},{"place":208,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.2},{"place":209,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.2},{"place":210,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":85.16},{"place":211,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":85.13},{"place":212,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":85.1},{"place":213,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":85.1},{"place":214,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":85.1},{"place":215,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85},{"place":216,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":85},{"place":217,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85},{"place":218,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.95},{"place":219,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":84.95},{"place":220,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.9},{"place":221,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":84.9},{"place":222,"model":"phi-4-14b","company":"microsoft","family":"Phi","version":"Phi 4","score":84.8},{"place":223,"model":"joyai-llm-flash-base","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":84.7},{"place":224,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.7},{"place":225,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":84.7},{"place":226,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.68},{"place":227,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":84.62},{"place":228,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.6},{"place":229,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":84.4},{"place":230,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":84.4},{"place":231,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":84.3},{"place":232,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":84.2},{"place":233,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":84.14},{"place":234,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":84.13},{"place":235,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":84.07},{"place":236,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":84.05},{"place":237,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":84},{"place":238,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":84},{"place":239,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84},{"place":240,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.97},{"place":241,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":83.96},{"place":242,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":83.95},{"place":243,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":83.93},{"place":244,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":83.8},{"place":245,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":83.7},{"place":246,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.7},{"place":247,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.61},{"place":248,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":83.6},{"place":249,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.6},{"place":250,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":83.6},{"place":251,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":83.59},{"place":252,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":83.55},{"place":253,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":83.5},{"place":254,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":83.5},{"place":255,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":83.4},{"place":256,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":83.4},{"place":257,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":83.3},{"place":258,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":83.3},{"place":259,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":83.3},{"place":260,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":83.3},{"place":261,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.3},{"place":262,"model":"aquif-3-moe-17b-a2.8b","company":"aquif","family":"Aquif","version":"Aquif 3","score":83.2},{"place":263,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":83.15},{"place":264,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":83.1},{"place":265,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83},{"place":266,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":83},{"place":267,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":83},{"place":268,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":82.98},{"place":269,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.8},{"place":270,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":82.8},{"place":271,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":82.75},{"place":272,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.7},{"place":273,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":82.7},{"place":274,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":82.6},{"place":275,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":82.58},{"place":276,"model":"magistral-small-2509","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":82.3},{"place":277,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":82.3},{"place":278,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":82.3},{"place":279,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":82.25},{"place":280,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":82.21},{"place":281,"model":"gpt-oss-20b-2025-08-05","company":"openai","family":"GPT","version":"GPT-OSS","score":82.2},{"place":282,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":82.12},{"place":283,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":82.1},{"place":284,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":82.09},{"place":285,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":82.08},{"place":286,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":82},{"place":287,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":82},{"place":288,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":82},{"place":289,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":82},{"place":290,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":81.9},{"place":291,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":81.9},{"place":292,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":81.8},{"place":293,"model":"instella-moe-16b-a3b-dpo","company":"amd","family":"Instella","version":"Instella-MoE","score":81.74},{"place":294,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":81.7},{"place":295,"model":"baichuan-3","company":"baichuan","family":"Baichuan","version":"Baichuan 3","score":81.7},{"place":296,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":81.66},{"place":297,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":81.61},{"place":298,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":81.51},{"place":299,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":81.5},{"place":300,"model":"glm-4-0116","company":"zai","family":"GLM","version":"GLM 4","score":81.5},{"place":301,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":81.4},{"place":302,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":81.4},{"place":303,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.38},{"place":304,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":81.38},{"place":305,"model":"instella-moe-16b-a3b-think","company":"amd","family":"Instella","version":"Instella-MoE","score":81.3},{"place":306,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":81.2},{"place":307,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.14},{"place":308,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":81.14},{"place":309,"model":"nemotron-4-340b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-4","score":81.1},{"place":310,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.07},{"place":311,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.05},{"place":312,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":81},{"place":313,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":81},{"place":314,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":81},{"place":315,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":81},{"place":316,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":80.98},{"place":317,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":80.9},{"place":318,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":80.9},{"place":319,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":80.9},{"place":320,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.89},{"place":321,"model":"instella-moe-16b-a3b-sft","company":"amd","family":"Instella","version":"Instella-MoE","score":80.82},{"place":322,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.8},{"place":323,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":80.8},{"place":324,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.8},{"place":325,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":80.8},{"place":326,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.7},{"place":327,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":80.7},{"place":328,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":80.62},{"place":329,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":80.6},{"place":330,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":80.53},{"place":331,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":80.5},{"place":332,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":80.5},{"place":333,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":80.5},{"place":334,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":80.45},{"place":335,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":80.4},{"place":336,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":80.4},{"place":337,"model":"qwen3-14b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":80.4},{"place":338,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.4},{"place":339,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":80.4},{"place":340,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":80.4},{"place":341,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":80.4},{"place":342,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":80.3},{"place":343,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":80.16},{"place":344,"model":"gpt-4.1-nano","company":"openai","family":"GPT","version":"GPT-4.1","score":80.1},{"place":345,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":80.1},{"place":346,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":80.1},{"place":347,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":80.1},{"place":348,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":79.91},{"place":349,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":79.8},{"place":350,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.7},{"place":351,"model":"llama-4-scout-17b-16e-base","company":"meta","family":"Llama","version":"Llama 4","score":79.6},{"place":352,"model":"llama-4-scout-17b-base","company":"meta","family":"Llama","version":"Llama 4","score":79.6},{"place":353,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":79.6},{"place":354,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.54},{"place":355,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":79.5},{"place":356,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.5},{"place":357,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":79.5},{"place":358,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":79.5},{"place":359,"model":"ministral-3-14b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":79.4},{"place":360,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":79.3},{"place":361,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":79.3},{"place":362,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":79.3},{"place":363,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":79.2},{"place":364,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":79.14},{"place":365,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":79.1},{"place":366,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":79.1},{"place":367,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":79.09},{"place":368,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":79.07},{"place":369,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":79},{"place":370,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79},{"place":371,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.97},{"place":372,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":78.9},{"place":373,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":78.9},{"place":374,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":78.89},{"place":375,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":78.8},{"place":376,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":78.7},{"place":377,"model":"abab6.5","company":"minimax","family":"abab","version":"abab6.5","score":78.7},{"place":378,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":78.66},{"place":379,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":78.6},{"place":380,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":78.6},{"place":381,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":78.6},{"place":382,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":78.59},{"place":383,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.56},{"place":384,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":78.5},{"place":385,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.48},{"place":386,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":78.45},{"place":387,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":78.44},{"place":388,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":78.43},{"place":389,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":78.4},{"place":390,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":78.4},{"place":391,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":78.24},{"place":392,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":78.2},{"place":393,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":78.2},{"place":394,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":78.1},{"place":395,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":78.1},{"place":396,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":78.02},{"place":397,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":78},{"place":398,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":78},{"place":399,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":77.9},{"place":400,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":77.83},{"place":401,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":77.81},{"place":402,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.8},{"place":403,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":77.8},{"place":404,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":77.8},{"place":405,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.8},{"place":406,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.75},{"place":407,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":77.72},{"place":408,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":77.7},{"place":409,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":77.6},{"place":410,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.6},{"place":411,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77.6},{"place":412,"model":"open-mixtral-8x22b-2404","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.5},{"place":413,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":77.5},{"place":414,"model":"open-mixtral-8x22b-2404","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.49},{"place":415,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":77.4},{"place":416,"model":"skywork-moe-base","company":"skywork","family":"Skywork","version":"Skywork-MoE","score":77.4},{"place":417,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.38},{"place":418,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":77.32},{"place":419,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":77.3},{"place":420,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.3},{"place":421,"model":"qwen-72b","company":"qwen","family":"Qwen","version":"Qwen","score":77.3},{"place":422,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":77.3},{"place":423,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.2},{"place":424,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77.2},{"place":425,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":77.2},{"place":426,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":77.2},{"place":427,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":77.2},{"place":428,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.13},{"place":429,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.1},{"place":430,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":77.1},{"place":431,"model":"apertus-v1.5-70b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":77.1},{"place":432,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":77.1},{"place":433,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":77},{"place":434,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":76.91},{"place":435,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":76.9},{"place":436,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":76.83},{"place":437,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":76.8},{"place":438,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":76.76},{"place":439,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":76.7},{"place":440,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":76.7},{"place":441,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":76.63},{"place":442,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.6},{"place":443,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":76.6},{"place":444,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":76.6},{"place":445,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":76.6},{"place":446,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":76.5},{"place":447,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":76.5},{"place":448,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":76.5},{"place":449,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":76.5},{"place":450,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.49},{"place":451,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":76.3},{"place":452,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":76.3},{"place":453,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":76.2},{"place":454,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":76.2},{"place":455,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":76.13},{"place":456,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":76.1},{"place":457,"model":"ministral-3-8b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":76.1},{"place":458,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.1},{"place":459,"model":"yi-34b-200k","company":"01ai","family":"Yi","version":"Yi","score":76.1},{"place":460,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":76},{"place":461,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":75.95},{"place":462,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":75.83},{"place":463,"model":"acegpt-v2-32b-chat","company":"freedomintelligence","family":"AceGPT","version":"AceGPT-v2","score":75.72},{"place":464,"model":"command-r-plus-08-2024","company":"cohere","family":"Command","version":"Command","score":75.7},{"place":465,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":75.7},{"place":466,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":75.7},{"place":467,"model":"phi-3-small-8k-instruct","company":"microsoft","family":"Phi","version":"Phi-3","score":75.7},{"place":468,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":75.6},{"place":469,"model":"yi-34b-200k","company":"01ai","family":"Yi","version":"Yi","score":75.56},{"place":470,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.44},{"place":471,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.44},{"place":472,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":75.4},{"place":473,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":75.3},{"place":474,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":75.3},{"place":475,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":75.2},{"place":476,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.2},{"place":477,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":75.2},{"place":478,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":75.2},{"place":479,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":75.14},{"place":480,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":75.01},{"place":481,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":75},{"place":482,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":75},{"place":483,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.99},{"place":484,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.9},{"place":485,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":74.9},{"place":486,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":74.83},{"place":487,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":74.8},{"place":488,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.8},{"place":489,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.8},{"place":490,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":74.7},{"place":491,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":74.7},{"place":492,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":74.7},{"place":493,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":74.6},{"place":494,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":74.6},{"place":495,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":74.6},{"place":496,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":74.6},{"place":497,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":74.58},{"place":498,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":74.5},{"place":499,"model":"gemma-3-12b-base","company":"google","family":"Gemma","version":"Gemma 3","score":74.5},{"place":500,"model":"apertus-v1.5-8b-thinking","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":74.5},{"place":501,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":74.4},{"place":502,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":74.3},{"place":503,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.3},{"place":504,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":74.3},{"place":505,"model":"internlm2.5-20b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":74.25},{"place":506,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.2},{"place":507,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":74.18},{"place":508,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":74.01},{"place":509,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":74},{"place":510,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":74},{"place":511,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":73.84},{"place":512,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":73.74},{"place":513,"model":"midm-2.0-base-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":73.7},{"place":514,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":73.7},{"place":515,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":73.7},{"place":516,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":73.7},{"place":517,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":73.69},{"place":518,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.64},{"place":519,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":73.6},{"place":520,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":73.5},{"place":521,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":73.5},{"place":522,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":73.46},{"place":523,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":73.4},{"place":524,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.3},{"place":525,"model":"telechat-12b","company":"teleai","family":"TeleChat","version":"TeleChat","score":73.3},{"place":526,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":73.3},{"place":527,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":73.2},{"place":528,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":73.2},{"place":529,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.19},{"place":530,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":73.02},{"place":531,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":73},{"place":532,"model":"grok-1","company":"xai","family":"Grok","version":"Grok 1","score":73},{"place":533,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":72.9},{"place":534,"model":"aquif-3.5-nano-1b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":72.9},{"place":535,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":72.9},{"place":536,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":72.8},{"place":537,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":72.6},{"place":538,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":72.5},{"place":539,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":72.49},{"place":540,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":72.42},{"place":541,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":72.4},{"place":542,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":72.4},{"place":543,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":72.4},{"place":544,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":72.3},{"place":545,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":72.25},{"place":546,"model":"yuan2.0-m32","company":"yuanlab","family":"Yuan","version":"Yuan2.0-M32","score":72.2},{"place":547,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":72.14},{"place":548,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":72.1},{"place":549,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":71.9},{"place":550,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":71.9},{"place":551,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":71.9},{"place":552,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":71.8},{"place":553,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.7},{"place":554,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":71.6},{"place":555,"model":"internlm2.5-7b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":71.6},{"place":556,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":71.6},{"place":557,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.56},{"place":558,"model":"qwen3-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":71.52},{"place":559,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":71.4},{"place":560,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":71.4},{"place":561,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":71.4},{"place":562,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":71.32},{"place":563,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":71.3},{"place":564,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":71.3},{"place":565,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":71.3},{"place":566,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":71.3},{"place":567,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":71.3},{"place":568,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":71.2},{"place":569,"model":"bielik-11b-v3.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":71.11},{"place":570,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":71.1},{"place":571,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":71},{"place":572,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":71},{"place":573,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":70.9},{"place":574,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":70.9},{"place":575,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":70.86},{"place":576,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":70.81},{"place":577,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":70.8},{"place":578,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":70.8},{"place":579,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":70.7},{"place":580,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":70.7},{"place":581,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":70.65},{"place":582,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":70.63},{"place":583,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":70.6},{"place":584,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":70.5},{"place":585,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":70.5},{"place":586,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":70.5},{"place":587,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":588,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":70.4},{"place":589,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":70.3},{"place":590,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":70.3},{"place":591,"model":"aquif-3.5-2.7b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":70.2},{"place":592,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":70.2},{"place":593,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":70.1},{"place":594,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":70.09},{"place":595,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":70.06},{"place":596,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":70},{"place":597,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":70},{"place":598,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":70},{"place":599,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.9},{"place":600,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":69.9},{"place":601,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":69.81},{"place":602,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":69.8},{"place":603,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.8},{"place":604,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.75},{"place":605,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.7},{"place":606,"model":"rnd1-base-0910","company":"radicalnumerics","family":"RND1","version":"RND1","score":69.6},{"place":607,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.58},{"place":608,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":69.5},{"place":609,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":69.5},{"place":610,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":69.5},{"place":611,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":69.5},{"place":612,"model":"yi-1.5-9b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":69.5},{"place":613,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":69.4},{"place":614,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":69.4},{"place":615,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":69.36},{"place":616,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":69.3},{"place":617,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.2},{"place":618,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":69.2},{"place":619,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.1},{"place":620,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.1},{"place":621,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":69.1},{"place":622,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":69.1},{"place":623,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":69},{"place":624,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":69},{"place":625,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69},{"place":626,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":68.9},{"place":627,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":68.8},{"place":628,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":68.7},{"place":629,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.7},{"place":630,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":68.68},{"place":631,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":68.67},{"place":632,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":68.65},{"place":633,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":68.6},{"place":634,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":68.57},{"place":635,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":68.54},{"place":636,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":68.5},{"place":637,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":68.5},{"place":638,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":68.4},{"place":639,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":68.4},{"place":640,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":68.4},{"place":641,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":68.4},{"place":642,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":68.3},{"place":643,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":68.25},{"place":644,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":68.2},{"place":645,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":68.2},{"place":646,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":68.2},{"place":647,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":68.03},{"place":648,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":68},{"place":649,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":67.9},{"place":650,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":67.9},{"place":651,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":67.85},{"place":652,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":67.8},{"place":653,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":67.8},{"place":654,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":67.79},{"place":655,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":67.7},{"place":656,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":67.7},{"place":657,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":67.7},{"place":658,"model":"codestral-2501","company":"mistral","family":"Codestral","version":"Codestral","score":67.6},{"place":659,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":67.6},{"place":660,"model":"codestral-2501","company":"mistral","family":"Codestral","version":"Codestral","score":67.59},{"place":661,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":67.58},{"place":662,"model":"bielik-11b-v3.0","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":67.55},{"place":663,"model":"bielik-11b-v2.6-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.6","score":67.53},{"place":664,"model":"aquif-3-3.2b","company":"aquif","family":"Aquif","version":"Aquif 3","score":67.5},{"place":665,"model":"bielik-11b-v2.5-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.5","score":67.44},{"place":666,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":67.43},{"place":667,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":67.4},{"place":668,"model":"jamba-v0.1","company":"ai21","family":"Jamba","version":"Jamba","score":67.4},{"place":669,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":67.35},{"place":670,"model":"phi-4-mini-3.8b","company":"microsoft","family":"Phi","version":"Phi 4 mini","score":67.3},{"place":671,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":67.23},{"place":672,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":67.2},{"place":673,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.1},{"place":674,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.1},{"place":675,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.1},{"place":676,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":67.1},{"place":677,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":67.1},{"place":678,"model":"meta-llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":67.07},{"place":679,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":67.02},{"place":680,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":67},{"place":681,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":66.79},{"place":682,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":66.79},{"place":683,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":66.77},{"place":684,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.74},{"place":685,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":66.7},{"place":686,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":66.7},{"place":687,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.7},{"place":688,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":66.7},{"place":689,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":66.7},{"place":690,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":66.7},{"place":691,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":66.7},{"place":692,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":66.6},{"place":693,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":66.6},{"place":694,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":66.6},{"place":695,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":66.6},{"place":696,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":66.52},{"place":697,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":66.5},{"place":698,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":66.5},{"place":699,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":66.5},{"place":700,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":66.4},{"place":701,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":66.4},{"place":702,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":66.4},{"place":703,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":66.4},{"place":704,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":66.3},{"place":705,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":66.21},{"place":706,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":66.11},{"place":707,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":66.03},{"place":708,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":66},{"place":709,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":65.98},{"place":710,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":65.9},{"place":711,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":65.9},{"place":712,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":65.9},{"place":713,"model":"afm-4.5b","company":"arcee","family":"AFM","version":"AFM","score":65.88},{"place":714,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":65.8},{"place":715,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":65.8},{"place":716,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":65.8},{"place":717,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":65.8},{"place":718,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.62},{"place":719,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.6},{"place":720,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":65.54},{"place":721,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.5},{"place":722,"model":"llama-tfree-hat-pretrained-7b-dpo","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":65.4},{"place":723,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":65.3},{"place":724,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":65.3},{"place":725,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65.09},{"place":726,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":65},{"place":727,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":64.98},{"place":728,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":64.9},{"place":729,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":64.84},{"place":730,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":64.84},{"place":731,"model":"openchat-3.5-0106-gemma","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":64.69},{"place":732,"model":"apriel-5b-instruct","company":"servicenow","family":"Apriel","version":"Apriel","score":64.6},{"place":733,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":64.6},{"place":734,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":64.6},{"place":735,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":64.59},{"place":736,"model":"bielik-11b-v2.3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.3","score":64.57},{"place":737,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.5},{"place":738,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":64.42},{"place":739,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":64.41},{"place":740,"model":"bielik-11b-v2.2-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.2","score":64.34},{"place":741,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":64.3},{"place":742,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":64.3},{"place":743,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":64.2},{"place":744,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":64.2},{"place":745,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":64.2},{"place":746,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":64.2},{"place":747,"model":"bielik-11b-v2.1-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.1","score":64.18},{"place":748,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":64.16},{"place":749,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":64.1},{"place":750,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":64.1},{"place":751,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":64.1},{"place":752,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":64.04},{"place":753,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":64},{"place":754,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":64},{"place":755,"model":"yi-6b-200k","company":"01ai","family":"Yi","version":"Yi","score":64},{"place":756,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":63.8},{"place":757,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":63.8},{"place":758,"model":"bielik-11b-v2.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.0","score":63.71},{"place":759,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":63.71},{"place":760,"model":"xverse-7b-chat","company":"xverse","family":"XVERSE","version":"XVERSE","score":63.7},{"place":761,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":63.7},{"place":762,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":63.7},{"place":763,"model":"bielik-4.5b-v3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":63.66},{"place":764,"model":"mistral-7b-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":63.62},{"place":765,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":63.5},{"place":766,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":63.5},{"place":767,"model":"yi-1.5-6b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":63.5},{"place":768,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":63.4},{"place":769,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":63.2},{"place":770,"model":"bielik-11b-v2","company":"SpeakLeash","family":"Bielik","version":"Bielik v2","score":63.06},{"place":771,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63},{"place":772,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":63},{"place":773,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":62.95},{"place":774,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":62.8},{"place":775,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":62.79},{"place":776,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":62.77},{"place":777,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":62.75},{"place":778,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":62.7},{"place":779,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":62.7},{"place":780,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":62.7},{"place":781,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":62.7},{"place":782,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":62.69},{"place":783,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":62.6},{"place":784,"model":"llama-2-34b","company":"meta","family":"Llama","version":"Llama 2","score":62.6},{"place":785,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":62.5},{"place":786,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":62.5},{"place":787,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":62.5},{"place":788,"model":"qwen1.5-moe-a2.7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":62.5},{"place":789,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":62.47},{"place":790,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.46},{"place":791,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":62.4},{"place":792,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.4},{"place":793,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":62.4},{"place":794,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":62.32},{"place":795,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.1},{"place":796,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":62.1},{"place":797,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":62.1},{"place":798,"model":"skywork-13b","company":"skywork","family":"Skywork","version":"Skywork","score":62.1},{"place":799,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":62.05},{"place":800,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":62.03},{"place":801,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":62},{"place":802,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":62},{"place":803,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":62},{"place":804,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":61.8},{"place":805,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":61.74},{"place":806,"model":"yi-6b-200k","company":"01ai","family":"Yi","version":"Yi","score":61.73},{"place":807,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":61.7},{"place":808,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":61.65},{"place":809,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":61.6},{"place":810,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":61.5},{"place":811,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":61.4},{"place":812,"model":"bielik-4.5b-v3","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":61.32},{"place":813,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":61.2},{"place":814,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":61.2},{"place":815,"model":"nemotron-flash-3b","company":"nvidia","family":"Nemotron Flash","version":"Nemotron Flash","score":61.19},{"place":816,"model":"nemotron-flash-3b-tp","company":"nvidia","family":"Nemotron Flash","version":"Nemotron Flash","score":61.19},{"place":817,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":61},{"place":818,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":61},{"place":819,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":61},{"place":820,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.99},{"place":821,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":60.99},{"place":822,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":60.96},{"place":823,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.9},{"place":824,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":60.9},{"place":825,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":60.83},{"place":826,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":60.81},{"place":827,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":60.78},{"place":828,"model":"hrm-text-1b","company":"sapient","family":"HRM","version":"HRM-Text","score":60.7},{"place":829,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":60.6},{"place":830,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":60.6},{"place":831,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":60.51},{"place":832,"model":"aquif-3.5-a0.6b","company":"aquif","family":"Aquif","version":"Aquif 3.5","score":60.5},{"place":833,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":60.5},{"place":834,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":60.5},{"place":835,"model":"exaone-3.5-2.4b","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":60.4},{"place":836,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":60.4},{"place":837,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":60.4},{"place":838,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":60.35},{"place":839,"model":"nemotron-flash-3b","company":"nvidia","family":"Nemotron Flash","version":"Nemotron Flash","score":60.34},{"place":840,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":60.33},{"place":841,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":60.3},{"place":842,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.3},{"place":843,"model":"xverse-13b-chat","company":"xverse","family":"XVERSE","version":"XVERSE","score":60.2},{"place":844,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":60.2},{"place":845,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":60.16},{"place":846,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":60.1},{"place":847,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":60.1},{"place":848,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":60},{"place":849,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":59.9},{"place":850,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":59.9},{"place":851,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":59.89},{"place":852,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":59.86},{"place":853,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":59.84},{"place":854,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.76},{"place":855,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":59.7},{"place":856,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":59.69},{"place":857,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":59.63},{"place":858,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":59.6},{"place":859,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":59.6},{"place":860,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":59.6},{"place":861,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":59.55},{"place":862,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":59.53},{"place":863,"model":"exaone-3.5-2.4b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":59.5},{"place":864,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":59.5},{"place":865,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":59.5},{"place":866,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":59.4},{"place":867,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":59.2},{"place":868,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":59.2},{"place":869,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":59.2},{"place":870,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":59.17},{"place":871,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.11},{"place":872,"model":"gemma-3-4b-base","company":"google","family":"Gemma","version":"Gemma 3","score":58.9},{"place":873,"model":"minicpm-moe-8x2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":58.9},{"place":874,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":58.8},{"place":875,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":58.73},{"place":876,"model":"audio-flamingo-3","company":"nvidia","family":"Audio Flamingo","version":"Audio Flamingo 3","score":58.7},{"place":877,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":58.7},{"place":878,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":58.53},{"place":879,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":58.37},{"place":880,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":58.35},{"place":881,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":58.3},{"place":882,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":58.28},{"place":883,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":58.28},{"place":884,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":58.2},{"place":885,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":58.2},{"place":886,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":58.14},{"place":887,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":58.1},{"place":888,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":58},{"place":889,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":58},{"place":890,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":57.8},{"place":891,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":57.71},{"place":892,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":57.65},{"place":893,"model":"ministral-3b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":57.61},{"place":894,"model":"ministral-3b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":57.6},{"place":895,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":57.5},{"place":896,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":57.45},{"place":897,"model":"kwaiyii-13b-base","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":57.42},{"place":898,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":57.42},{"place":899,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.4},{"place":900,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":57.4},{"place":901,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":57.32},{"place":902,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":57.3},{"place":903,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":57.3},{"place":904,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":57.3},{"place":905,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":57.28},{"place":906,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":57.18},{"place":907,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":57.11},{"place":908,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":57.1},{"place":909,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":57},{"place":910,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":57},{"place":911,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":57},{"place":912,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":56.9},{"place":913,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":56.8},{"place":914,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":56.76},{"place":915,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":56.7},{"place":916,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":56.6},{"place":917,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":56.6},{"place":918,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":56.6},{"place":919,"model":"midm-2.0-mini-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":56.5},{"place":920,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":56.5},{"place":921,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":56.5},{"place":922,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":56.49},{"place":923,"model":"kwaiyii-13b-chat","company":"kuaishou","family":"KwaiYii","version":"KwaiYii","score":56.44},{"place":924,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":56.4},{"place":925,"model":"baichuan2-13b-chat-4bits","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":56.24},{"place":926,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56.2},{"place":927,"model":"chatglm2-12b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":56.2},{"place":928,"model":"chatglm2-12b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":56.18},{"place":929,"model":"qwen1.5-4b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":56.1},{"place":930,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":56.03},{"place":931,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":55.94},{"place":932,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":55.9},{"place":933,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":55.88},{"place":934,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":55.81},{"place":935,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":55.8},{"place":936,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":55.8},{"place":937,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":55.7},{"place":938,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":55.7},{"place":939,"model":"aquif-3-0.4b","company":"aquif","family":"Aquif","version":"Aquif 3","score":55.6},{"place":940,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":55.6},{"place":941,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":55.55},{"place":942,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":55.4},{"place":943,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":55.38},{"place":944,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":55.35},{"place":945,"model":"lfm2-1.2b","company":"liquidai","family":"LFM","version":"LFM2","score":55.23},{"place":946,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":55.21},{"place":947,"model":"bluelm-7b-base","company":"vivo","family":"BlueLM","version":"BlueLM","score":55.2},{"place":948,"model":"granite-swash-2b","company":"IBM","family":"Granite","version":"Granite SWASH","score":55.19},{"place":949,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":55.1},{"place":950,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":55.09},{"place":951,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":55},{"place":952,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":55},{"place":953,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":54.99},{"place":954,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":54.9},{"place":955,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":54.8},{"place":956,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":54.71},{"place":957,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54.7},{"place":958,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54.61},{"place":959,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54.6},{"place":960,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":54.6},{"place":961,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":54.5},{"place":962,"model":"telechat-7b","company":"teleai","family":"TeleChat","version":"TeleChat","score":54.4},{"place":963,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.3},{"place":964,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54.2},{"place":965,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":54.2},{"place":966,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54.16},{"place":967,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54.1},{"place":968,"model":"granite-swash-3b-a600m","company":"IBM","family":"Granite","version":"Granite SWASH","score":54.09},{"place":969,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":53.6},{"place":970,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":53.56},{"place":971,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":53.53},{"place":972,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":53.52},{"place":973,"model":"internlm2.5-1.8b","company":"internlm","family":"InternLM","version":"InternLM2.5","score":53.52},{"place":974,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":53.5},{"place":975,"model":"minicpm-2b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":53.46},{"place":976,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":53.4},{"place":977,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":53.2},{"place":978,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":53.2},{"place":979,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":53.05},{"place":980,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":53},{"place":981,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":52.93},{"place":982,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":52.9},{"place":983,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":52.8},{"place":984,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":52.7},{"place":985,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":52.7},{"place":986,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":52.66},{"place":987,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":52.6},{"place":988,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":52.5},{"place":989,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":52.4},{"place":990,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":52.4},{"place":991,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":52.4},{"place":992,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":52.2},{"place":993,"model":"chatglm2-12b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":52.13},{"place":994,"model":"baichuan-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan","score":52.1},{"place":995,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":52},{"place":996,"model":"vicuna-13b","company":"lmsys","family":"Vicuna-13B","version":"Vicuna-13B","score":52},{"place":997,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":51.9},{"place":998,"model":"baichuan2-7b-chat-4bits","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":51.72},{"place":999,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":51.67},{"place":1000,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":51.6},{"place":1001,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":51.2},{"place":1002,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":51.1},{"place":1003,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":51},{"place":1004,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":51},{"place":1005,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":50.8},{"place":1006,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":50.8},{"place":1007,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":50.73},{"place":1008,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":50.72},{"place":1009,"model":"bluelm-7b-chat","company":"vivo","family":"BlueLM","version":"BlueLM","score":50.7},{"place":1010,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":50.7},{"place":1011,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":50.7},{"place":1012,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":50.5},{"place":1013,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":50.4},{"place":1014,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":50.3},{"place":1015,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.2},{"place":1016,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":50.14},{"place":1017,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":50.1},{"place":1018,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":50.1},{"place":1019,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":50},{"place":1020,"model":"lfm2-700m","company":"liquidai","family":"LFM","version":"LFM2","score":49.9},{"place":1021,"model":"vicuna-7b-v1.5","company":"lmsys","family":"Vicuna","version":"Vicuna","score":49.8},{"place":1022,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":49.7},{"place":1023,"model":"minicpm-1b-sft","company":"openbmb","family":"MiniCPM","version":"MiniCPM","score":49.63},{"place":1024,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":49.5},{"place":1025,"model":"bielik-7b-instruct-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":49.47},{"place":1026,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":49.4},{"place":1027,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":49.4},{"place":1028,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":49.3},{"place":1029,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":49.2},{"place":1030,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":49.1},{"place":1031,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":48.22},{"place":1032,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":48.2},{"place":1033,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":48.2},{"place":1034,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":48.2},{"place":1035,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":47.9},{"place":1036,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":47.9},{"place":1037,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":47.9},{"place":1038,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":47.86},{"place":1039,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":47.86},{"place":1040,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":47.82},{"place":1041,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":47.73},{"place":1042,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":47.7},{"place":1043,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":47.64},{"place":1044,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":47.56},{"place":1045,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.5},{"place":1046,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":47.47},{"place":1047,"model":"mobilellm-r1-950m-base","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":47.4},{"place":1048,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":47.33},{"place":1049,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":47.3},{"place":1050,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":47.3},{"place":1051,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":47.3},{"place":1052,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":47.2},{"place":1053,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":46.9},{"place":1054,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":46.9},{"place":1055,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":46.9},{"place":1056,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":46.8},{"place":1057,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":46.8},{"place":1058,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":46.6},{"place":1059,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":46.56},{"place":1060,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":46.4},{"place":1061,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":46.4},{"place":1062,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":46.3},{"place":1063,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":46.2},{"place":1064,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":46.1},{"place":1065,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.07},{"place":1066,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":46},{"place":1067,"model":"internlm2-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":45.99},{"place":1068,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":45.9},{"place":1069,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":45.9},{"place":1070,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":45.9},{"place":1071,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":45.8},{"place":1072,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":45.8},{"place":1073,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":45.77},{"place":1074,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":45.73},{"place":1075,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":45.5},{"place":1076,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":45.46},{"place":1077,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":45.46},{"place":1078,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":45.4},{"place":1079,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":45.3},{"place":1080,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":45.2},{"place":1081,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":45},{"place":1082,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":44.97},{"place":1083,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":44.93},{"place":1084,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":44.9},{"place":1085,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":44.8},{"place":1086,"model":"glm-130b","company":"zai","family":"GLM","version":"GLM-130B","score":44.75},{"place":1087,"model":"nemotron-flash-1b","company":"nvidia","family":"Nemotron Flash","version":"Nemotron Flash","score":44.63},{"place":1088,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":44.6},{"place":1089,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":44.4},{"place":1090,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":44.32},{"place":1091,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":44.3},{"place":1092,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":44},{"place":1093,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":44},{"place":1094,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":43.9},{"place":1095,"model":"chinese-alpaca-plus-13b","company":"hfl","family":"Chinese-LLaMA-Alpaca","version":"Chinese-Alpaca","score":43.9},{"place":1096,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":43.9},{"place":1097,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":43.81},{"place":1098,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":43.7},{"place":1099,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":43.43},{"place":1100,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":43.37},{"place":1101,"model":"bielik-7b-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":43.2},{"place":1102,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":42.9},{"place":1103,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":42.9},{"place":1104,"model":"qwen2-audio-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Audio","score":42.9},{"place":1105,"model":"ziya-llama-13b-pretrain","company":"idea-ccnl","family":"Ziya","version":"Ziya-LLaMA","score":42.9},{"place":1106,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":42.7},{"place":1107,"model":"olmo-2-0425-1b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":42.4},{"place":1108,"model":"qwen-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":42.4},{"place":1109,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":42.3},{"place":1110,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":42.3},{"place":1111,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":42.3},{"place":1112,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":42},{"place":1113,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":41.5},{"place":1114,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":41.2},{"place":1115,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":41},{"place":1116,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":40.63},{"place":1117,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":40.5},{"place":1118,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":40.08},{"place":1119,"model":"baguettotron-321m","company":"pleias","family":"Baguettotron","version":"Baguettotron","score":40},{"place":1120,"model":"x-omni","company":"tencent","family":"X-Omni","version":"X-Omni","score":40},{"place":1121,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":39.9},{"place":1122,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39.85},{"place":1123,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":39.8},{"place":1124,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":39.7},{"place":1125,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.4},{"place":1126,"model":"qwen1.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":39.2},{"place":1127,"model":"chinese-llama-plus-13b","company":"hfl","family":"LLaMA","version":"Chinese-LLaMA-Alpaca","score":39.2},{"place":1128,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":38.8},{"place":1129,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":38.8},{"place":1130,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":38.7},{"place":1131,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":38.49},{"place":1132,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":37.9},{"place":1133,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":37.2},{"place":1134,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":36.9},{"place":1135,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":36.9},{"place":1136,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":36.6},{"place":1137,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":36.6},{"place":1138,"model":"telechat-1b","company":"teleai","family":"TeleChat","version":"TeleChat","score":36.5},{"place":1139,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":36.4},{"place":1140,"model":"bloomz-7b1","company":"bigscience","family":"BLOOM","version":"BLOOMZ","score":36.1},{"place":1141,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":36},{"place":1142,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":35.6},{"place":1143,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":35.6},{"place":1144,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":35.5},{"place":1145,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":35.2},{"place":1146,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":35.1},{"place":1147,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":35},{"place":1148,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":35},{"place":1149,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":35},{"place":1150,"model":"trlm-135m","company":"loka","family":"TRLM","version":"TRLM","score":34.95},{"place":1151,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":33.5},{"place":1152,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":32.5},{"place":1153,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":32.4},{"place":1154,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":32},{"place":1155,"model":"moss-moon-003-sft","company":"fudan","family":"MOSS","version":"MOSS","score":31.9},{"place":1156,"model":"huginn-3.5b","company":"tomg-umd","family":"Huginn","version":"Huginn","score":31.4},{"place":1157,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":30.8},{"place":1158,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":30.7},{"place":1159,"model":"monad","company":"pleias","family":"Monad","version":"Monad","score":30},{"place":1160,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":29.9},{"place":1161,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":29.6},{"place":1162,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":28.51},{"place":1163,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":28.4},{"place":1164,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":28.07},{"place":1165,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":27.93},{"place":1166,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":27.8},{"place":1167,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":27.06},{"place":1168,"model":"mobilellm-r1-360m-base","company":"meta","family":"MobileLLM","version":"MobileLLM R1","score":26.8},{"place":1169,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":26.8},{"place":1170,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":26.5},{"place":1171,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":26.5},{"place":1172,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":26.39},{"place":1173,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":26.2},{"place":1174,"model":"gemma-3-pt-1b","company":"google","family":"Gemma","version":"Gemma 3","score":26.1},{"place":1175,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":26.03},{"place":1176,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":25.9},{"place":1177,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":25.8},{"place":1178,"model":"bloom-7b1","company":"bigscience","family":"BLOOM","version":"BLOOM","score":25.5},{"place":1179,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":25.2},{"place":1180,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":25},{"place":1181,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":25},{"place":1182,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":24.7},{"place":1183,"model":"tinyllama-1.1b","company":"tinyllama","family":"TinyLlama","version":"TinyLlama","score":24.3},{"place":1184,"model":"moss-moon-003-base","company":"fudan","family":"MOSS","version":"MOSS","score":23.6},{"place":1185,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":8.4}]},{"id":"mmlu-arabic","name":"MMLU Arabic","topic":"Arabic knowledge and reasoning","description":"Arabic-language variant of MMLU evaluating knowledge and reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen 2.5 72B","top_percent":74.1,"top_model_id":"qwen-2.5-72b","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.1},{"place":2,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.32},{"place":3,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":67.65},{"place":4,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":67.4},{"place":5,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":66.8},{"place":6,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":65.5},{"place":7,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":65.4},{"place":8,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":65},{"place":9,"model":"acegpt-v2-32b-chat","company":"freedomintelligence","family":"AceGPT","version":"AceGPT-v2","score":61.1},{"place":10,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":47.8}]},{"id":"mmlu-cloze","name":"MMLU (cloze)","topic":"Multi-domain knowledge (cloze)","description":"Cloze-form MMLU evaluation variant.","url":"https://github.com/hendrycks/test","leaderboard":"","github":"https://github.com/hendrycks/test","paper":"","metric":"percent","stars":"","top_model":"SmolLM2 135M Base","top_percent":31.5,"top_model_id":"smollm2-135m-base","top_generation":"SmolLM2","top_model_base":"SmolLM2 135M","top_model_family":"SmolLM","top_company":"huggingface","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":31.5},{"place":2,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":31.5},{"place":3,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":29.3}]},{"id":"mmlu-fulltext","name":"Full Text MMLU","topic":"Multi-domain knowledge (long-form)","description":"Full-context MMLU variant evaluating reasoning over long passages.","url":"","leaderboard":"","github":"","paper":"","metric":"norm_log_acc","stars":"","top_model":"Llama 3.3 70B Instruct","top_percent":83,"top_model_id":"llama-3.3-70b-instruct","top_generation":"Llama 3.3","top_model_base":"Llama 3.3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":83},{"place":2,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":78.6}]},{"id":"mmlu-med","name":"MMLU Med","topic":"Medical knowledge","description":"Medical subset of MMLU (clinical knowledge, anatomy, college medicine, medical genetics, professional medicine, college biology).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedGemma 27B","top_percent":86.2,"top_model_id":"medgemma-27b-it","top_generation":"MedGemma 1","top_model_base":"MedGemma","top_model_family":"MedGemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":86.2},{"place":2,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":81},{"place":3,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":80.2},{"place":4,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":79},{"place":5,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":75.7},{"place":6,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":74.8},{"place":7,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":71.8},{"place":8,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":70},{"place":9,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":69.6},{"place":10,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":69.6},{"place":11,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":67.2}]},{"id":"mmlu-pro","name":"MMLU-Pro","topic":"Multi-domain knowledge","description":"Harder successor to MMLU with more challenging questions.","url":"https://github.com/TIGER-AI-Lab/MMLU-Pro","leaderboard":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","github":"https://github.com/TIGER-AI-Lab/MMLU-Pro","paper":"https://arxiv.org/abs/2406.01574","metric":"percent","stars":"286","top_model":"Gemini 3.1 Pro","top_percent":91.16,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":779,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":91.16},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":91},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":90.12},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.1},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.8},{"place":8,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":89.8},{"place":9,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.8},{"place":10,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":89.77},{"place":11,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":89.75},{"place":12,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.7},{"place":13,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":89.6},{"place":14,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.5},{"place":15,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.5},{"place":16,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":89.5},{"place":17,"model":"o1","company":"openai","family":"o1","version":"o1","score":89.3},{"place":18,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.3},{"place":19,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.3},{"place":20,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.3},{"place":21,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.1},{"place":22,"model":"claude-opus-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.1},{"place":23,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":89.05},{"place":24,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":89},{"place":25,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":88.6},{"place":26,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":88.5},{"place":27,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":88.5},{"place":28,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.3},{"place":29,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88.2},{"place":30,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":88.2},{"place":31,"model":"darwin-180b-rsi","company":"finalbench","family":"Darwin","version":"Darwin","score":88.12},{"place":32,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":88.1},{"place":33,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":88},{"place":34,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88},{"place":35,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88},{"place":36,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":88},{"place":37,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":87.8},{"place":38,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.8},{"place":39,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":87.7},{"place":40,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.7},{"place":41,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":87.5},{"place":42,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.5},{"place":43,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":87.5},{"place":44,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.5},{"place":45,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.5},{"place":46,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.5},{"place":47,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":87.4},{"place":48,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":87.4},{"place":49,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.4},{"place":50,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.31},{"place":51,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":87.3},{"place":52,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":87.3},{"place":53,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.3},{"place":54,"model":"claude-sonnet-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":87.3},{"place":55,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":87.22},{"place":56,"model":"hunyuan-t1","company":"tencent","family":"Hunyuan","version":"Hunyuan T1","score":87.2},{"place":57,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":87.1},{"place":58,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.1},{"place":59,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.1},{"place":60,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":87.1},{"place":61,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.1},{"place":62,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":87.1},{"place":63,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":87.1},{"place":64,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":87},{"place":65,"model":"seed1.5-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":87},{"place":66,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":87},{"place":67,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":87},{"place":68,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":87},{"place":69,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":87},{"place":70,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":87},{"place":71,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.9},{"place":72,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.88},{"place":73,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.86},{"place":74,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.8},{"place":75,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":86.7},{"place":76,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.7},{"place":77,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":86.6},{"place":78,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":86.6},{"place":79,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":86.6},{"place":80,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":86.6},{"place":81,"model":"seed1.6-thinking","company":"bytedance","family":"Seed","version":"Seed 1.6","score":86.6},{"place":82,"model":"seed1.6-base","company":"bytedance","family":"Seed","version":"Seed 1.6","score":86.6},{"place":83,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":86.59},{"place":84,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.4},{"place":85,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.4},{"place":86,"model":"seed1.6-adaptive-thinking","company":"bytedance","family":"Seed","version":"Seed 1.6","score":86.4},{"place":87,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":86.4},{"place":88,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":86.3},{"place":89,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":86.3},{"place":90,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.2},{"place":91,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.2},{"place":92,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.2},{"place":93,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":86.2},{"place":94,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.2},{"place":95,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":86.2},{"place":96,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":86.1},{"place":97,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.1},{"place":98,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86},{"place":99,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":86},{"place":100,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":86},{"place":101,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":86},{"place":102,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":85.9},{"place":103,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":85.9},{"place":104,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":85.9},{"place":105,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":85.9},{"place":106,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.9},{"place":107,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":85.9},{"place":108,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.9},{"place":109,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":85.8},{"place":110,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.7},{"place":111,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":85.7},{"place":112,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":85.7},{"place":113,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.63},{"place":114,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.31},{"place":115,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.3},{"place":116,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.2},{"place":117,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.2},{"place":118,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.2},{"place":119,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":85.2},{"place":120,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.12},{"place":121,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":85.1},{"place":122,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.01},{"place":123,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":85},{"place":124,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85},{"place":125,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":85},{"place":126,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":85},{"place":127,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":85},{"place":128,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":85},{"place":129,"model":"o3","company":"openai","family":"o3","version":"o3","score":85},{"place":130,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85},{"place":131,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85},{"place":132,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":85},{"place":133,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":84.9},{"place":134,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":84.9},{"place":135,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":84.9},{"place":136,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":84.8},{"place":137,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":84.8},{"place":138,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.8},{"place":139,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":84.8},{"place":140,"model":"cogito-671b-v2.1","company":"deepcogito","family":"Cogito","version":"Cogito 671B v2.1","score":84.69},{"place":141,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":84.6},{"place":142,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.6},{"place":143,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":84.6},{"place":144,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":84.6},{"place":145,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.52},{"place":146,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.52},{"place":147,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.5},{"place":148,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84.5},{"place":149,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.43},{"place":150,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.42},{"place":151,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84.4},{"place":152,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.4},{"place":153,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":84.4},{"place":154,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84.3},{"place":155,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":84.3},{"place":156,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":84.3},{"place":157,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.3},{"place":158,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":84.2},{"place":159,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":84.2},{"place":160,"model":"grok-4.1-fast-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":84.2},{"place":161,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.11},{"place":162,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":84.1},{"place":163,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":84},{"place":164,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":84},{"place":165,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":84},{"place":166,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":84},{"place":167,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.89},{"place":168,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":83.8},{"place":169,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.8},{"place":170,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":83.8},{"place":171,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.8},{"place":172,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.73},{"place":173,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":83.7},{"place":174,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":83.7},{"place":175,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.7},{"place":176,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":83.7},{"place":177,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":83.6},{"place":178,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":83.5},{"place":179,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":83.5},{"place":180,"model":"intern-s1","company":"internlm","family":"Intern","version":"Intern-S1","score":83.5},{"place":181,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":83.45},{"place":182,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":83.44},{"place":183,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.4},{"place":184,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":83.4},{"place":185,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":83.4},{"place":186,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":83.3},{"place":187,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":83.3},{"place":188,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.2},{"place":189,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":83.2},{"place":190,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":83},{"place":191,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83},{"place":192,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":83},{"place":193,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":83},{"place":194,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":83},{"place":195,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83},{"place":196,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":82.93},{"place":197,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.9},{"place":198,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":82.9},{"place":199,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":82.8},{"place":200,"model":"llama-4-behemoth","company":"meta","family":"Llama","version":"Llama 4","score":82.8},{"place":201,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":82.7},{"place":202,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.7},{"place":203,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":82.7},{"place":204,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":82.7},{"place":205,"model":"longcat-flash-chat","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":82.7},{"place":206,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.6},{"place":207,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":82.6},{"place":208,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.5},{"place":209,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":82.4},{"place":210,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":82.4},{"place":211,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.4},{"place":212,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.4},{"place":213,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":82.3},{"place":214,"model":"llama-4-behemoth","company":"meta","family":"Llama","version":"Llama 4","score":82.2},{"place":215,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.2},{"place":216,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":82.16},{"place":217,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":82.1},{"place":218,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":82},{"place":219,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":81.94},{"place":220,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.9},{"place":221,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":81.9},{"place":222,"model":"intellect-3","company":"primeintellect","family":"INTELLECT","version":"INTELLECT","score":81.9},{"place":223,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":81.9},{"place":224,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.9},{"place":225,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.9},{"place":226,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":81.8},{"place":227,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":81.8},{"place":228,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":81.8},{"place":229,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":81.7},{"place":230,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":81.7},{"place":231,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":81.6},{"place":232,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":81.6},{"place":233,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":81.5},{"place":234,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":81.5},{"place":235,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":81.4},{"place":236,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":81.3},{"place":237,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":81.2},{"place":238,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":81.2},{"place":239,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":81.2},{"place":240,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.11},{"place":241,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":81.1},{"place":242,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":81.1},{"place":243,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":81.1},{"place":244,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":81.1},{"place":245,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":81.02},{"place":246,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":81},{"place":247,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":81},{"place":248,"model":"golongrl-30b-a3b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":81},{"place":249,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":81},{"place":250,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.9},{"place":251,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":80.9},{"place":252,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":80.9},{"place":253,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":80.9},{"place":254,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":80.9},{"place":255,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":80.89},{"place":256,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":80.8},{"place":257,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.8},{"place":258,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":80.8},{"place":259,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":80.8},{"place":260,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":80.7},{"place":261,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":80.7},{"place":262,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":80.7},{"place":263,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":80.6},{"place":264,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":80.6},{"place":265,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":80.6},{"place":266,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":80.5},{"place":267,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":80.5},{"place":268,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.5},{"place":269,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":80.4},{"place":270,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":80.4},{"place":271,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":80.4},{"place":272,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":80.3},{"place":273,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.2},{"place":274,"model":"doubao-1.5-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":80.1},{"place":275,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":80.1},{"place":276,"model":"openreasoning-nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":80},{"place":277,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80},{"place":278,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":80},{"place":279,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":80},{"place":280,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":80},{"place":281,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":79.9},{"place":282,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":79.9},{"place":283,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":79.89},{"place":284,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":79.8},{"place":285,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":79.7},{"place":286,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":79.6},{"place":287,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.4},{"place":288,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":79.4},{"place":289,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":79.24},{"place":290,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":79.2},{"place":291,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":79.19},{"place":292,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79.1},{"place":293,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":79.1},{"place":294,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.1},{"place":295,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":79.1},{"place":296,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.07},{"place":297,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":79},{"place":298,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":79},{"place":299,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":79},{"place":300,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":79},{"place":301,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":79},{"place":302,"model":"hunyuan-turbos","company":"tencent","family":"Hunyuan","version":"Hunyuan Turbos","score":79},{"place":303,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.95},{"place":304,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":78.91},{"place":305,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.9},{"place":306,"model":"grok-3-mini-beta","company":"xai","family":"Grok","version":"Grok 3","score":78.9},{"place":307,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.86},{"place":308,"model":"nemotron-labs-3-elastic-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.63},{"place":309,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":78.6},{"place":310,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":78.6},{"place":311,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":78.5},{"place":312,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.5},{"place":313,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.46},{"place":314,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":78.4},{"place":315,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.4},{"place":316,"model":"ernie-4.5-300b-a47b","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":78.4},{"place":317,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.3},{"place":318,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.3},{"place":319,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":78.29},{"place":320,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":78.2},{"place":321,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.2},{"place":322,"model":"nemotron-3-nano-30b-a3b-fp8","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.1},{"place":323,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":78},{"place":324,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78},{"place":325,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":78},{"place":326,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":78},{"place":327,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":77.9},{"place":328,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":77.9},{"place":329,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":77.9},{"place":330,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.8},{"place":331,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":77.8},{"place":332,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":77.6},{"place":333,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.6},{"place":334,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":77.6},{"place":335,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":77.6},{"place":336,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":77.55},{"place":337,"model":"openreasoning-nemotron-14b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":77.5},{"place":338,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":77.3},{"place":339,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.3},{"place":340,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":77.3},{"place":341,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":77.2},{"place":342,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.2},{"place":343,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":77.2},{"place":344,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":77.02},{"place":345,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":77},{"place":346,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":77},{"place":347,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":77},{"place":348,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":77},{"place":349,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":76.84},{"place":350,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":76.8},{"place":351,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":76.8},{"place":352,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":76.8},{"place":353,"model":"superapriel-15b-instruct","company":"servicenow","family":"Apriel","version":"SuperApriel","score":76.8},{"place":354,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":76.8},{"place":355,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":76.67},{"place":356,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":76.65},{"place":357,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":76.6},{"place":358,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":76.59},{"place":359,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":76.5},{"place":360,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":76.5},{"place":361,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":76.5},{"place":362,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":76.48},{"place":363,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":76.4},{"place":364,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":76.25},{"place":365,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":76.24},{"place":366,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":76.12},{"place":367,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":76.1},{"place":368,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.1},{"place":369,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":76.1},{"place":370,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":76.02},{"place":371,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76},{"place":372,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":76},{"place":373,"model":"celeris-1","company":"celeris","family":"Celeris","version":"Celeris-1","score":75.9},{"place":374,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":75.9},{"place":375,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":75.87},{"place":376,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":75.8},{"place":377,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":75.8},{"place":378,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":75.7},{"place":379,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":75.7},{"place":380,"model":"minimax-text-01","company":"minimax","family":"MiniMax","version":"MiniMax-01","score":75.7},{"place":381,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75.65},{"place":382,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":75.6},{"place":383,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":75.5},{"place":384,"model":"grok-2","company":"xai","family":"Grok","version":"Grok 2","score":75.46},{"place":385,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.37},{"place":386,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":75.31},{"place":387,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":75.3},{"place":388,"model":"kanana-2-30b-a3b-thinking","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.3},{"place":389,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":75.3},{"place":390,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":75.2},{"place":391,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":75.2},{"place":392,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.1},{"place":393,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":75},{"place":394,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.8},{"place":395,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":74.79},{"place":396,"model":"pulsar-16b","company":"multiverse","family":"Pulsar","version":"Pulsar","score":74.78},{"place":397,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":74.68},{"place":398,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":74.5},{"place":399,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.43},{"place":400,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":74.3},{"place":401,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":74.3},{"place":402,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.3},{"place":403,"model":"golongrl-4b","company":"kuaishou","family":"GoLongRL","version":"GoLongRL","score":74.3},{"place":404,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":74.3},{"place":405,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.3},{"place":406,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":74.3},{"place":407,"model":"llama-4-scout","company":"meta","family":"Llama","version":"Llama 1","score":74.3},{"place":408,"model":"phi-4-reasoning","company":"microsoft","family":"Phi","version":"Phi 4","score":74.3},{"place":409,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.23},{"place":410,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.21},{"place":411,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74.2},{"place":412,"model":"kanana-2-30b-a3b-thinking-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":74.2},{"place":413,"model":"zaya1-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":74.2},{"place":414,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":74.1},{"place":415,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":74.1},{"place":416,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.08},{"place":417,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":74.04},{"place":418,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":74},{"place":419,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":73.9},{"place":420,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":73.9},{"place":421,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.9},{"place":422,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.88},{"place":423,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":73.7},{"place":424,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":73.6},{"place":425,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":73.6},{"place":426,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":73.6},{"place":427,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":73.6},{"place":428,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.5},{"place":429,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":73.5},{"place":430,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":73.4},{"place":431,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":73.4},{"place":432,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":73.4},{"place":433,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":73.36},{"place":434,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":73.3},{"place":435,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":73.3},{"place":436,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":73.3},{"place":437,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":73.3},{"place":438,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.26},{"place":439,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":73.2},{"place":440,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":73.2},{"place":441,"model":"joyai-llm-flash-base","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":73.14},{"place":442,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":73.14},{"place":443,"model":"athene-v2-chat","company":"nvidia","family":"Athene","version":"Athene V2","score":73.11},{"place":444,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":73},{"place":445,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":73},{"place":446,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":72.7},{"place":447,"model":"minicpm4.1-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4.1","score":72.7},{"place":448,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":72.6},{"place":449,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":72.55},{"place":450,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.5},{"place":451,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":72.1},{"place":452,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":72},{"place":453,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.98},{"place":454,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":71.9},{"place":455,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.9},{"place":456,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":71.9},{"place":457,"model":"grok-2-mini","company":"xai","family":"Grok","version":"Grok 2","score":71.85},{"place":458,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":71.79},{"place":459,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.6},{"place":460,"model":"gemini-2.0-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.0","score":71.6},{"place":461,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.6},{"place":462,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.59},{"place":463,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.3},{"place":464,"model":"openpangu-r-7b-diffusion","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":71.26},{"place":465,"model":"echo-ego-v2-14b","company":"unknown","family":"ECHO","version":"ECHO Ego v2","score":71.24},{"place":466,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":71.1},{"place":467,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":71.1},{"place":468,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.1},{"place":469,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":70.98},{"place":470,"model":"qwq-32b-preview","company":"qwen","family":"QwQ","version":"QwQ","score":70.97},{"place":471,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":70.8},{"place":472,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":70.7},{"place":473,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":70.6},{"place":474,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":70.6},{"place":475,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.5},{"place":476,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":70.5},{"place":477,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":70.41},{"place":478,"model":"phi-4","company":"microsoft","family":"Phi","version":"Phi 3.5","score":70.4},{"place":479,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":70.25},{"place":480,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":70.2},{"place":481,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.14},{"place":482,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":70.1},{"place":483,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":70.09},{"place":484,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":70},{"place":485,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":69.98},{"place":486,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":69.9},{"place":487,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":69.6},{"place":488,"model":"openpangu-embedded-7b-v1.1","company":"huawei","family":"openPangu-Embedded","version":"openPangu-Embedded-V1.1","score":69.6},{"place":489,"model":"ernie-4.5-300b-a47b-base","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":69.5},{"place":490,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.4},{"place":491,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":69.4},{"place":492,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.23},{"place":493,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.2},{"place":494,"model":"sky-t1-32b-preview","company":"novasky","family":"Sky","version":"Sky T1","score":69.2},{"place":495,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.15},{"place":496,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":69.1},{"place":497,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":69.1},{"place":498,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.1},{"place":499,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":69.1},{"place":500,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":69.1},{"place":501,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":69.07},{"place":502,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":69.03},{"place":503,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69},{"place":504,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":69},{"place":505,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":69},{"place":506,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69},{"place":507,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":68.9},{"place":508,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.9},{"place":509,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":68.75},{"place":510,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":68.56},{"place":511,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":68.5},{"place":512,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":68.45},{"place":513,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":68.3},{"place":514,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.3},{"place":515,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":68.2},{"place":516,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":68.18},{"place":517,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":68.18},{"place":518,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":68.1},{"place":519,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.94},{"place":520,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":67.94},{"place":521,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":67.91},{"place":522,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":67.84},{"place":523,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":67.79},{"place":524,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":67.74},{"place":525,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":67.6},{"place":526,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":67.5},{"place":527,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":67.5},{"place":528,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":67.5},{"place":529,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":67.45},{"place":530,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":67.42},{"place":531,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":67.4},{"place":532,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":67.3},{"place":533,"model":"hunyuan-80b-a13b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":67.3},{"place":534,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":67.22},{"place":535,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":67.18},{"place":536,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.1},{"place":537,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":67.1},{"place":538,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":67.04},{"place":539,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.9},{"place":540,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":66.9},{"place":541,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":66.8},{"place":542,"model":"mistral-small-3.1-24b-instruct-2503","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":66.8},{"place":543,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":66.63},{"place":544,"model":"general-reasoner-14b","company":"tiger-lab","family":"General-Reasoner","version":"General-Reasoner","score":66.6},{"place":545,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.5},{"place":546,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":66.5},{"place":547,"model":"seed1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":66.47},{"place":548,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":66.44},{"place":549,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":66.4},{"place":550,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.4},{"place":551,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":66.38},{"place":552,"model":"mistral-small-24b-instruct-2501","company":"mistral","family":"Mistral","version":"Mistral","score":66.3},{"place":553,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":66.2},{"place":554,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":66.02},{"place":555,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":66},{"place":556,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":65.98},{"place":557,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":65.92},{"place":558,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":65.91},{"place":559,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":65.9},{"place":560,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":65.83},{"place":561,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":65.83},{"place":562,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":65.8},{"place":563,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":65.8},{"place":564,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":65.8},{"place":565,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":65.78},{"place":566,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":65.76},{"place":567,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":65.7},{"place":568,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":65.68},{"place":569,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":65.6},{"place":570,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":65.6},{"place":571,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.54},{"place":572,"model":"ernie-4.5-21b-a3b-pt","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":65.5},{"place":573,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":65.5},{"place":574,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":65.3},{"place":575,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":65.2},{"place":576,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":65.2},{"place":577,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":65.1},{"place":578,"model":"seed-oss-36b-base","company":"bytedance","family":"Seed","version":"Seed-OSS","score":65.1},{"place":579,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":65.1},{"place":580,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":65.05},{"place":581,"model":"reka-flash-3","company":"reka","family":"Reka Flash","version":"Reka Flash","score":65},{"place":582,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":64.9},{"place":583,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":64.84},{"place":584,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":64.8},{"place":585,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":64.8},{"place":586,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":64.8},{"place":587,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":64.5},{"place":588,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.49},{"place":589,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":64.4},{"place":590,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":64.4},{"place":591,"model":"qwen2-72b-chat","company":"qwen","family":"Qwen","version":"Qwen2","score":64.38},{"place":592,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.3},{"place":593,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":64.27},{"place":594,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64.2},{"place":595,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":64.1},{"place":596,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":64.09},{"place":597,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":64.09},{"place":598,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":64.09},{"place":599,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":63.98},{"place":600,"model":"magnum-72b-v1","company":"anthracite-org","family":"Magnum","version":"Magnum","score":63.93},{"place":601,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":63.91},{"place":602,"model":"alodlm-8b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":63.9},{"place":603,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":63.9},{"place":604,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63.89},{"place":605,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":63.71},{"place":606,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":63.7},{"place":607,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":63.7},{"place":608,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.7},{"place":609,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.69},{"place":610,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":63.67},{"place":611,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":63.65},{"place":612,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":63.63},{"place":613,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":63.62},{"place":614,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":63.6},{"place":615,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.5},{"place":616,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":63.42},{"place":617,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":63.4},{"place":618,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63.4},{"place":619,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":63.26},{"place":620,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.2},{"place":621,"model":"higgs-llama-3-70b","company":"bosonai","family":"Higgs","version":"Higgs","score":63.16},{"place":622,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":63.1},{"place":623,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":63.1},{"place":624,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":63.09},{"place":625,"model":"azerogpt","company":"soundai","family":"AzeroGPT","version":"AzeroGPT","score":63.07},{"place":626,"model":"llama-4-maverick-17b-128e-base","company":"meta","family":"Llama","version":"Llama 4","score":62.9},{"place":627,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":62.9},{"place":628,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":62.84},{"place":629,"model":"llama-3.1-nemotron-70b-instruct-hf","company":"nvidia","family":"Llama","version":"Llama 3.1","score":62.78},{"place":630,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":62.7},{"place":631,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.6},{"place":632,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":62.59},{"place":633,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":62.4},{"place":634,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":62.38},{"place":635,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":62.3},{"place":636,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.3},{"place":637,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":62.12},{"place":638,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.1},{"place":639,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":62.1},{"place":640,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.1},{"place":641,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":62.1},{"place":642,"model":"rrd2.5-9b","company":"unknown","family":"RRD","version":"RRD2.5","score":61.84},{"place":643,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.83},{"place":644,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":61.83},{"place":645,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":61.76},{"place":646,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":61.7},{"place":647,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":61.6},{"place":648,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":61.6},{"place":649,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":61.6},{"place":650,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":61.5},{"place":651,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":61.5},{"place":652,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.49},{"place":653,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":61.36},{"place":654,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":61.36},{"place":655,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":61.1},{"place":656,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":61.03},{"place":657,"model":"jamba-reasoning-3b","company":"ai21","family":"Jamba","version":"Jamba Reasoning","score":61},{"place":658,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":60.93},{"place":659,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":60.73},{"place":660,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":60.6},{"place":661,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":60.6},{"place":662,"model":"nemotron-h-56b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-H","score":60.5},{"place":663,"model":"seed-oss-36b-base-wosyn","company":"bytedance","family":"Seed","version":"Seed-OSS","score":60.4},{"place":664,"model":"reflection-llama-3.1-70b","company":"mattshumer","family":"Reflection","version":"Reflection","score":60.35},{"place":665,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":60.21},{"place":666,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":60.2},{"place":667,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":60.1},{"place":668,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":60},{"place":669,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":59.84},{"place":670,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":59.8},{"place":671,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":59.3},{"place":672,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":59.12},{"place":673,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":59.1},{"place":674,"model":"openpangu-7b-diffusion-base","company":"huawei","family":"openPangu-Diffusion","version":"openPangu-Diffusion","score":59.05},{"place":675,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":59},{"place":676,"model":"exaone-3.5-32b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":58.91},{"place":677,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":58.9},{"place":678,"model":"general-reasoner-7b","company":"tiger-lab","family":"General-Reasoner","version":"General-Reasoner","score":58.9},{"place":679,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":58.8},{"place":680,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":58.8},{"place":681,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":58.73},{"place":682,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":58.6},{"place":683,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":58.5},{"place":684,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":58.4},{"place":685,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":58.3},{"place":686,"model":"wedlm-8b-instruct","company":"tencent","family":"WeDLM","version":"WeDLM","score":58.3},{"place":687,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.3},{"place":688,"model":"llama-4-scout-17b-16e-base","company":"meta","family":"Llama","version":"Llama 4","score":58.2},{"place":689,"model":"llama-4-scout-17b-base","company":"meta","family":"Llama","version":"Llama 4","score":58.2},{"place":690,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":58.2},{"place":691,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.1},{"place":692,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.1},{"place":693,"model":"yi-large","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":58.09},{"place":694,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":57.9},{"place":695,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":57.8},{"place":696,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.76},{"place":697,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":57.7},{"place":698,"model":"newenai-phi4-sft","company":"newenai","family":"Phi","version":"Phi-4","score":57.7},{"place":699,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":57.6},{"place":700,"model":"internlm3-8b-instruct","company":"internlm","family":"InternLM","version":"InternLM3","score":57.6},{"place":701,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":57.5},{"place":702,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":57.3},{"place":703,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":57.1},{"place":704,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":57},{"place":705,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":57},{"place":706,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":56.9},{"place":707,"model":"sdar-8b-chat","company":"jetlm","family":"SDAR","version":"SDAR","score":56.9},{"place":708,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":56.9},{"place":709,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.8},{"place":710,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":56.8},{"place":711,"model":"ernie-4.5-21b-a3b-pt","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":56.7},{"place":712,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":56.68},{"place":713,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.63},{"place":714,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":56.54},{"place":715,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":56.5},{"place":716,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":56.5},{"place":717,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":56.4},{"place":718,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":56.4},{"place":719,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":56.4},{"place":720,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":56.33},{"place":721,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.3},{"place":722,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":56.2},{"place":723,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":56.14},{"place":724,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":56.14},{"place":725,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":56.1},{"place":726,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":56},{"place":727,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":55.99},{"place":728,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":55.8},{"place":729,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":55.73},{"place":730,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":55.7},{"place":731,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":55.7},{"place":732,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":55.6},{"place":733,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.6},{"place":734,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":55.6},{"place":735,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.6},{"place":736,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":55.59},{"place":737,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":55.5},{"place":738,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":55.47},{"place":739,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":55.3},{"place":740,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.3},{"place":741,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.1},{"place":742,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":55},{"place":743,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.9},{"place":744,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":54.9},{"place":745,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":54.81},{"place":746,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":54.8},{"place":747,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.68},{"place":748,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":54.5},{"place":749,"model":"mistral-small-3-24b-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":54.4},{"place":750,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":54.2},{"place":751,"model":"lfm2-2.6b-exp","company":"liquidai","family":"LFM","version":"LFM2","score":53.87},{"place":752,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":53.8},{"place":753,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":53.8},{"place":754,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.72},{"place":755,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":53.62},{"place":756,"model":"midm-2.0-base-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":53.3},{"place":757,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":53.3},{"place":758,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":53.1},{"place":759,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":53.01},{"place":760,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":53},{"place":761,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":52.8},{"place":762,"model":"phi-4-mini","company":"microsoft","family":"Phi","version":"Phi 4","score":52.8},{"place":763,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":52.8},{"place":764,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":52.8},{"place":765,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":52.8},{"place":766,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":52.78},{"place":767,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":52.7},{"place":768,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":52.64},{"place":769,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":52.61},{"place":770,"model":"qwen3-8b-nothinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":52.5},{"place":771,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":52.47},{"place":772,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":52.4},{"place":773,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":52.31},{"place":774,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":52.3},{"place":775,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":52.3},{"place":776,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":52.29},{"place":777,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":52.2},{"place":778,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":52.11},{"place":779,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":52.1},{"place":780,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":52.08},{"place":781,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.06},{"place":782,"model":"phi-3-medium-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":51.91},{"place":783,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":51.83},{"place":784,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":51.75},{"place":785,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":51.7},{"place":786,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":51.7},{"place":787,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":51.6},{"place":788,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":51.6},{"place":789,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.4},{"place":790,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":51.4},{"place":791,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":51.3},{"place":792,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":51.25},{"place":793,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":51.2},{"place":794,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":51.2},{"place":795,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":51.1},{"place":796,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":50.9},{"place":797,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":50.85},{"place":798,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":50.5},{"place":799,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":50.5},{"place":800,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":50.5},{"place":801,"model":"mammoth2-8x7b-plus","company":"tiger-lab","family":"MAmmoTH","version":"MAmmoTH2","score":50.4},{"place":802,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":50.4},{"place":803,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":50.3},{"place":804,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":50.1},{"place":805,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":50.02},{"place":806,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":49.93},{"place":807,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":49.89},{"place":808,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":49.83},{"place":809,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":49.65},{"place":810,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":49.6},{"place":811,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":49.5},{"place":812,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":49.5},{"place":813,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":49.5},{"place":814,"model":"jamba-1.5-large","company":"ai21","family":"Jamba","version":"Jamba 1.5","score":49.46},{"place":815,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":49.4},{"place":816,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":49.4},{"place":817,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":49.3},{"place":818,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":49.22},{"place":819,"model":"llada2.0-mini-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":49.22},{"place":820,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":49.21},{"place":821,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":49.2},{"place":822,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":49.1},{"place":823,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":49.1},{"place":824,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":48.85},{"place":825,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":48.8},{"place":826,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":48.7},{"place":827,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":48.62},{"place":828,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":48.4},{"place":829,"model":"mistral-small-instruct-2409","company":"mistral","family":"Mistral","version":"Mistral","score":48.4},{"place":830,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":48.3},{"place":831,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":48.3},{"place":832,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":48.3},{"place":833,"model":"dream-7b-base","company":"huawei","family":"Dream","version":"Dream","score":48.15},{"place":834,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.1},{"place":835,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":48.01},{"place":836,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":47.98},{"place":837,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":47.92},{"place":838,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":47.87},{"place":839,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":47.6},{"place":840,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":47.59},{"place":841,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":47.51},{"place":842,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":47.5},{"place":843,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":47.5},{"place":844,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":47.5},{"place":845,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":47.24},{"place":846,"model":"c4ai-aya-vision-32b","company":"cohere","family":"Aya","version":"Aya Vision","score":47.2},{"place":847,"model":"phi-4-mini","company":"microsoft","family":"Phi","version":"Phi 4","score":47},{"place":848,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":46.99},{"place":849,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":46.8},{"place":850,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":46.4},{"place":851,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":46.24},{"place":852,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":46.1},{"place":853,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":45.95},{"place":854,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":45.8},{"place":855,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":45.68},{"place":856,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":45.66},{"place":857,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":45.6},{"place":858,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.6},{"place":859,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":45.5},{"place":860,"model":"aya-expanse-32b","company":"cohere","family":"Aya","version":"Aya Expanse","score":45.41},{"place":861,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":45.4},{"place":862,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":45.33},{"place":863,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":45.3},{"place":864,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":45.3},{"place":865,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":45.1},{"place":866,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":45.1},{"place":867,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45},{"place":868,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":44.94},{"place":869,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":44.9},{"place":870,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":44.81},{"place":871,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":44.7},{"place":872,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":44.7},{"place":873,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":44.7},{"place":874,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":44.5},{"place":875,"model":"fast-dllm-v2-7b","company":"nvidia","family":"Fast-dLLM","version":"Fast-dLLM v2","score":44.42},{"place":876,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":44.35},{"place":877,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":44.3},{"place":878,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":44.25},{"place":879,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":44.2},{"place":880,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.1},{"place":881,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":44.1},{"place":882,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":44.1},{"place":883,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":44.05},{"place":884,"model":"nemotron-h-8b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-H","score":44},{"place":885,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":44},{"place":886,"model":"phi-3-mini-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":43.86},{"place":887,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":43.8},{"place":888,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.73},{"place":889,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":43.7},{"place":890,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.7},{"place":891,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":43.69},{"place":892,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":43.6},{"place":893,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":43.6},{"place":894,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.55},{"place":895,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":43.5},{"place":896,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":43.48},{"place":897,"model":"mammoth2-8b-plus","company":"tiger-lab","family":"MAmmoTH","version":"MAmmoTH2","score":43.35},{"place":898,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":43.3},{"place":899,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":43.3},{"place":900,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":43.27},{"place":901,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":43.24},{"place":902,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43.23},{"place":903,"model":"yi-34b","company":"01ai","family":"Yi","version":"Yi","score":43.03},{"place":904,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":43},{"place":905,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":43},{"place":906,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":43},{"place":907,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":42.91},{"place":908,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.8},{"place":909,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.74},{"place":910,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":42.7},{"place":911,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":42.5},{"place":912,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":42.4},{"place":913,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.3},{"place":914,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":42.29},{"place":915,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":42},{"place":916,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":42},{"place":917,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":42},{"place":918,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":42},{"place":919,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":41.94},{"place":920,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":41.9},{"place":921,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":41.9},{"place":922,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":41.89},{"place":923,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":41.8},{"place":924,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":41.7},{"place":925,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":41.65},{"place":926,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":41.57},{"place":927,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":41.03},{"place":928,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":41.03},{"place":929,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":41},{"place":930,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":41},{"place":931,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":41},{"place":932,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":40.98},{"place":933,"model":"mammoth2-7b-plus","company":"tiger-lab","family":"MAmmoTH","version":"MAmmoTH2","score":40.85},{"place":934,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":40.73},{"place":935,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":40.73},{"place":936,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":40.7},{"place":937,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":40.6},{"place":938,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.2},{"place":939,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":40.2},{"place":940,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":40.1},{"place":941,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":40.1},{"place":942,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":40},{"place":943,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":39.9},{"place":944,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":39.9},{"place":945,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39.88},{"place":946,"model":"mistral-nemo-base-2407","company":"mistral","family":"Mistral","version":"Mistral NeMo","score":39.77},{"place":947,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":39.76},{"place":948,"model":"alodlm-1.7b","company":"amazon","family":"ALoDLM","version":"ALoDLM","score":39.6},{"place":949,"model":"trida-7b","company":"trillionlabs","family":"Trida","version":"Trida","score":39.37},{"place":950,"model":"wizardlm-2-8x22b","company":"microsoft","family":"WizardLM","version":"WizardLM-2","score":39.24},{"place":951,"model":"llada-moe-7b-a1b-base","company":"antgroup","family":"LLaDA","version":"LLaDA-MoE","score":39.16},{"place":952,"model":"exaone-3.5-2.4b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":39.1},{"place":953,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":39},{"place":954,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":38.8},{"place":955,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":38.5},{"place":956,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":38.3},{"place":957,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":38.3},{"place":958,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":38.27},{"place":959,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":38.23},{"place":960,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":38.12},{"place":961,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":38.02},{"place":962,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":38},{"place":963,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":37.93},{"place":964,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":37.9},{"place":965,"model":"starling-lm-7b-beta","company":"berkeley","family":"Starling","version":"Starling LM","score":37.9},{"place":966,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":37.88},{"place":967,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37.87},{"place":968,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":37.8},{"place":969,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":37.53},{"place":970,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":37.42},{"place":971,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.42},{"place":972,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":37.4},{"place":973,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":37.3},{"place":974,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.27},{"place":975,"model":"openchat-3.5-8b","company":"openchat","family":"OpenChat","version":"OpenChat 3.5","score":37.24},{"place":976,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":37.1},{"place":977,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":37.1},{"place":978,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":37.08},{"place":979,"model":"llada-8b-base","company":"antgroup","family":"LLaDA","version":"LLaDA","score":37},{"place":980,"model":"llama-3-smaug-8b","company":"abacusai","family":"Smaug","version":"Smaug","score":36.93},{"place":981,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":36.6},{"place":982,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":36.54},{"place":983,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":36.5},{"place":984,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":36.5},{"place":985,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":36.42},{"place":986,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":36.2},{"place":987,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":35.98},{"place":988,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":35.8},{"place":989,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":35.8},{"place":990,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.63},{"place":991,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":35.6},{"place":992,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":35.4},{"place":993,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":35.36},{"place":994,"model":"deepseek-math-7b-instruct","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":35.3},{"place":995,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.2},{"place":996,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":35.2},{"place":997,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":35},{"place":998,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":34.76},{"place":999,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":34.64},{"place":1000,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":34.61},{"place":1001,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":34.6},{"place":1002,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":34.37},{"place":1003,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":33.9},{"place":1004,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":33.9},{"place":1005,"model":"aya-expanse-8b","company":"cohere","family":"Aya","version":"Aya Expanse","score":33.74},{"place":1006,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":33.73},{"place":1007,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":33.7},{"place":1008,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":33.53},{"place":1009,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":33.5},{"place":1010,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":33.4},{"place":1011,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":33.34},{"place":1012,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":33.2},{"place":1013,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":33.1},{"place":1014,"model":"granite-3.1-8b-base","company":"ibm","family":"Granite","version":"Granite 3.1","score":33.08},{"place":1015,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":33},{"place":1016,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":32.97},{"place":1017,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.76},{"place":1018,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":32.5},{"place":1019,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.4},{"place":1020,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.1},{"place":1021,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":32.03},{"place":1022,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":32},{"place":1023,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":31.97},{"place":1024,"model":"littlelamb-0.3b","company":"multiverse","family":"LittleLamb","version":"LittleLamb","score":31.21},{"place":1025,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":31.1},{"place":1026,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":31.03},{"place":1027,"model":"granite-3.0-8b-base","company":"ibm","family":"Granite","version":"Granite 3.0","score":31.03},{"place":1028,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":30.9},{"place":1029,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":30.88},{"place":1030,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":30.86},{"place":1031,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":30.84},{"place":1032,"model":"audio-flamingo-3","company":"nvidia","family":"Audio Flamingo","version":"Audio Flamingo 3","score":30.8},{"place":1033,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":30.7},{"place":1034,"model":"mistral-7b-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":30.43},{"place":1035,"model":"llama-spark-8b","company":"arcee","family":"Llama Spark","version":"Llama Spark 8B","score":30.23},{"place":1036,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":29.9},{"place":1037,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":29.87},{"place":1038,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.8},{"place":1039,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.75},{"place":1040,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":29.71},{"place":1041,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.71},{"place":1042,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.7},{"place":1043,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":29.11},{"place":1044,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":29.1},{"place":1045,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":29.06},{"place":1046,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":28.84},{"place":1047,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":28.74},{"place":1048,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":28.6},{"place":1049,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28.5},{"place":1050,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28.35},{"place":1051,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":28.08},{"place":1052,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":27.7},{"place":1053,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":27.64},{"place":1054,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":27.44},{"place":1055,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":27},{"place":1056,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":26.7},{"place":1057,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":26.51},{"place":1058,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":26.5},{"place":1059,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":25.96},{"place":1060,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":25.85},{"place":1061,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":25.75},{"place":1062,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.72},{"place":1063,"model":"granite-3.1-3b-a800m-instruct","company":"ibm","family":"Granite","version":"Granite 3.1","score":25.42},{"place":1064,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":25.34},{"place":1065,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":25.3},{"place":1066,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":25.2},{"place":1067,"model":"littlelamb-0.3b","company":"multiverse","family":"LittleLamb","version":"LittleLamb","score":25.11},{"place":1068,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":24.3},{"place":1069,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":23.9},{"place":1070,"model":"granite-3.1-2b-base","company":"ibm","family":"Granite","version":"Granite 3.1","score":23.89},{"place":1071,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.54},{"place":1072,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":23.45},{"place":1073,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":23.1},{"place":1074,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":23.1},{"place":1075,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":23},{"place":1076,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":22.9},{"place":1077,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":22.9},{"place":1078,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":22.9},{"place":1079,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":22.62},{"place":1080,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":22.56},{"place":1081,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":22.25},{"place":1082,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":22.17},{"place":1083,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":21.8},{"place":1084,"model":"granite-3.0-2b-base","company":"ibm","family":"Granite","version":"Granite 3.0","score":21.72},{"place":1085,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":21.61},{"place":1086,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":21.6},{"place":1087,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":20.8},{"place":1088,"model":"granite-3.1-3b-a800m-base","company":"ibm","family":"Granite","version":"Granite 3.1","score":20.39},{"place":1089,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":20.32},{"place":1090,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":20.25},{"place":1091,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":20.01},{"place":1092,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":20},{"place":1093,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":20},{"place":1094,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":19.9},{"place":1095,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":19.32},{"place":1096,"model":"x-omni","company":"tencent","family":"X-Omni","version":"X-Omni","score":19.3},{"place":1097,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":19.29},{"place":1098,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":18.73},{"place":1099,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":18.49},{"place":1100,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":18.4},{"place":1101,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":18.4},{"place":1102,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":18.31},{"place":1103,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":18.2},{"place":1104,"model":"falcon-e-1b-base","company":"tii","family":"Falcon","version":"Falcon E","score":17.82},{"place":1105,"model":"qwen2-audio-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Audio","score":17.5},{"place":1106,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":17.22},{"place":1107,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":17.2},{"place":1108,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":17.2},{"place":1109,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":16.95},{"place":1110,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":16.7},{"place":1111,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":16.27},{"place":1112,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":16.2},{"place":1113,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":16.1},{"place":1114,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":16.1},{"place":1115,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":15.93},{"place":1116,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":15.9},{"place":1117,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":15.85},{"place":1118,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":15.7},{"place":1119,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":15.6},{"place":1120,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":15.6},{"place":1121,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":15.5},{"place":1122,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":15},{"place":1123,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":14.97},{"place":1124,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":14.92},{"place":1125,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":14.7},{"place":1126,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":14.7},{"place":1127,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":14.7},{"place":1128,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":14.65},{"place":1129,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":14.46},{"place":1130,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":14.4},{"place":1131,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":14.04},{"place":1132,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":14.04},{"place":1133,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.98},{"place":1134,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":13.6},{"place":1135,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":13.57},{"place":1136,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":13.3},{"place":1137,"model":"granite-3.1-1b-a400m-instruct","company":"ibm","family":"Granite","version":"Granite 3.1","score":13.27},{"place":1138,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":13.14},{"place":1139,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":12.84},{"place":1140,"model":"granite-3.1-1b-a400m-base","company":"ibm","family":"Granite","version":"Granite 3.1","score":12.34},{"place":1141,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":11.95},{"place":1142,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":11.93},{"place":1143,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":11.8},{"place":1144,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":11.4},{"place":1145,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":11.38},{"place":1146,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":11.31},{"place":1147,"model":"smollm-135m","company":"huggingface","family":"SmolLM","version":"SmolLM","score":11.22},{"place":1148,"model":"smollm-360m","company":"huggingface","family":"SmolLM","version":"SmolLM","score":10.95},{"place":1149,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":10.85},{"place":1150,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":10.8},{"place":1151,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":10.6},{"place":1152,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":9.9},{"place":1153,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":6.23},{"place":1154,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":3.91},{"place":1155,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":3.91},{"place":1156,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1.88}]},{"id":"mmlu-pro-mcf","name":"MMLU Pro MCF","topic":"Multi-domain knowledge (few-shot)","description":"MMLU-Pro common format (MCF) few-shot evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-4B-Base","top_percent":41.07,"top_model_id":"qwen3-4b-base","top_generation":"Qwen3","top_model_base":"Qwen3 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":41.07},{"place":2,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.2},{"place":3,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":19.4},{"place":4,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":19.3},{"place":5,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":13.7},{"place":6,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":12.7},{"place":7,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":11.7},{"place":8,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":11.7},{"place":9,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":10.8}]},{"id":"mmlu-prox","name":"MMLU-ProX","topic":"Multi-domain knowledge","description":"Cross-lingual and robust variant of MMLU-Pro.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":87.7,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":58,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.7},{"place":2,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":87},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.4},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86.1},{"place":5,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":85.8},{"place":6,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.7},{"place":7,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.6},{"place":8,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.5},{"place":9,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":85.4},{"place":10,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.06},{"place":11,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":85},{"place":12,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.7},{"place":13,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.7},{"place":14,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84.3},{"place":15,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":84},{"place":16,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":83.9},{"place":17,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.9},{"place":18,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":83.7},{"place":19,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":83.7},{"place":20,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.2},{"place":21,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":83.1},{"place":22,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.1},{"place":23,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83},{"place":24,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83},{"place":25,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":83},{"place":26,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":82.3},{"place":27,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.2},{"place":28,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.2},{"place":29,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81},{"place":30,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81},{"place":31,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":80.6},{"place":32,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.2},{"place":33,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.5},{"place":34,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.4},{"place":35,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.4},{"place":36,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.36},{"place":37,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":78.7},{"place":38,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":78.5},{"place":39,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":78.5},{"place":40,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":78.4},{"place":41,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.9},{"place":42,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.6},{"place":43,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":77.5},{"place":44,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":76.91},{"place":45,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":76.9},{"place":46,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":76.7},{"place":47,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":76.59},{"place":48,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":76.4},{"place":49,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.3},{"place":50,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.1},{"place":51,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":74.6},{"place":52,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.5},{"place":53,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":73.6},{"place":54,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":72.5},{"place":55,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":72},{"place":56,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.5},{"place":57,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.9},{"place":58,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":69.3},{"place":59,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":69.1},{"place":60,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":69.1},{"place":61,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":68.7},{"place":62,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":67.3},{"place":63,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.4},{"place":64,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":62.4},{"place":65,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":61.6},{"place":66,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":61.2},{"place":67,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":59.5},{"place":68,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.4},{"place":69,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":58},{"place":70,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.3},{"place":71,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":49.4},{"place":72,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.6}]},{"id":"mmlu-prox-ja","name":"MMLU-ProX (Japanese)","topic":"Multi-domain knowledge (Japanese)","description":"Japanese subset of MMLU-ProX (JMMLU-ProX).","url":"https://mmluprox.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-235B-A22B-Thinking-2507","top_percent":81.9,"top_model_id":"qwen3-235b-a22b-thinking-2507","top_generation":"Qwen3","top_model_base":"Qwen3 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":41,"total_models":3854,"placements":[{"place":1,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.9},{"place":2,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":80.5},{"place":3,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":79.7},{"place":4,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":77.5},{"place":5,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":75.6},{"place":6,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":75.4},{"place":7,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":74.7},{"place":8,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":74.6},{"place":9,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.8},{"place":10,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.7},{"place":11,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":73.5},{"place":12,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":72.9},{"place":13,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":72.3},{"place":14,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":72.2},{"place":15,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":71.3},{"place":16,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":71.2},{"place":17,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":71.1},{"place":18,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":70.2},{"place":19,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":69.6},{"place":20,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":69.5},{"place":21,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":67.7},{"place":22,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":67.5},{"place":23,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":66.9},{"place":24,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":65.3},{"place":25,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":62.8},{"place":26,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":60.9},{"place":27,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":51.2},{"place":28,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":48.5},{"place":29,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":45.7},{"place":30,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":36.9},{"place":31,"model":"lfm2.5-1.2b-jp-202606","company":"liquidai","family":"LFM","version":"LFM2.5","score":36.23},{"place":32,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":31.9},{"place":33,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":31.42},{"place":34,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":30.78},{"place":35,"model":"tinyswallow-1.5b-instruct","company":"sakana","family":"TinySwallow","version":"TinySwallow","score":21.51},{"place":36,"model":"sarashina2.2-1b-instruct-v0.1","company":"sbintuitions","family":"Sarashina","version":"Sarashina2.2","score":18.3},{"place":37,"model":"llm-jp-3.1-1.8b-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":17.44},{"place":38,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":15.91},{"place":39,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":15.32},{"place":40,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":14.12},{"place":41,"model":"rakutenai-2.0-mini-instruct","company":"rakuten","family":"RakutenAI","version":"RakutenAI 2.0","score":11.46}]},{"id":"mmlu-redux","name":"MMLU-Redux","topic":"Multi-domain knowledge","description":"Updated MMLU-style evaluation with revised questions and scoring.","url":"","leaderboard":"https://huggingface.co/spaces/allenai/ZeroEval","github":"","paper":"","metric":"percent","stars":"","top_model":"GRM-3.2-Sky","top_percent":96.9,"top_model_id":"grm-3.2-sky","top_generation":"GRM-3.2","top_model_base":"GRM-3.2 Sky","top_model_family":"GRM","top_company":"orionllm","top_open_source":1,"lower_is_better":false,"bench_models":272,"total_models":3854,"placements":[{"place":1,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":96.9},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":95.9},{"place":3,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":95.6},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":95.6},{"place":5,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":95.3},{"place":6,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":95.3},{"place":7,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":95.2},{"place":8,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":95},{"place":9,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":95},{"place":10,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":95},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94.9},{"place":12,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.8},{"place":13,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":94.5},{"place":14,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":94.5},{"place":15,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":94.5},{"place":16,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":94.5},{"place":17,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":94.4},{"place":18,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":94.4},{"place":19,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":94.3},{"place":20,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":94.2},{"place":21,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":94.2},{"place":22,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94},{"place":23,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.8},{"place":24,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.8},{"place":25,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":93.7},{"place":26,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.7},{"place":27,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":93.7},{"place":28,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":93.7},{"place":29,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":93.6},{"place":30,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":93.5},{"place":31,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93.35},{"place":32,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.3},{"place":33,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":93.3},{"place":34,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.2},{"place":35,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":93.1},{"place":36,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":92.84},{"place":37,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":92.8},{"place":38,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":92.8},{"place":39,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":92.7},{"place":40,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":92.7},{"place":41,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":92.7},{"place":42,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":92.7},{"place":43,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":92.5},{"place":44,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":92.4},{"place":45,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.1},{"place":46,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.1},{"place":47,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.7},{"place":48,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.46},{"place":49,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":91.4},{"place":50,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":91.3},{"place":51,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":91.2},{"place":52,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.1},{"place":53,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":91},{"place":54,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.9},{"place":55,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":90.9},{"place":56,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.9},{"place":57,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.8},{"place":58,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.6},{"place":59,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":90.6},{"place":60,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":90.5},{"place":61,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.4},{"place":62,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90.4},{"place":63,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":90.2},{"place":64,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":90.02},{"place":65,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":90},{"place":66,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":90},{"place":67,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":90},{"place":68,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":89.8},{"place":69,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":89.7},{"place":70,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.5},{"place":71,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.5},{"place":72,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.4},{"place":73,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.3},{"place":74,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":89.2},{"place":75,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":89.2},{"place":76,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":89.2},{"place":77,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":89.1},{"place":78,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":89.09},{"place":79,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":88.93},{"place":80,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":88.91},{"place":81,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":88.9},{"place":82,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":88.89},{"place":83,"model":"chatgpt-4o-latest-20240903","company":"openai","family":"GPT","version":"GPT-4o","score":88.88},{"place":84,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.8},{"place":85,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.8},{"place":86,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.7},{"place":87,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.6},{"place":88,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.4},{"place":89,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":88.4},{"place":90,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.3},{"place":91,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":88.3},{"place":92,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":88.26},{"place":93,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":88.01},{"place":94,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":88},{"place":95,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":87.8},{"place":96,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":87.8},{"place":97,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":87.5},{"place":98,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.5},{"place":99,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":87.4},{"place":100,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":87.3},{"place":101,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":87.2},{"place":102,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":87.18},{"place":103,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":86.9},{"place":104,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":86.86},{"place":105,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.81},{"place":106,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":86.8},{"place":107,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.8},{"place":108,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":86.72},{"place":109,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":86.6},{"place":110,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":86.56},{"place":111,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":86.5},{"place":112,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":86.3},{"place":113,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.3},{"place":114,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":86.22},{"place":115,"model":"llama-3.1-405b-instruct-bf16","company":"meta","family":"Llama","version":"Llama 3.1","score":86.21},{"place":116,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":86.2},{"place":117,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":86.2},{"place":118,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":86.2},{"place":119,"model":"gemini-1.5-pro-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":86.14},{"place":120,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.1},{"place":121,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":86},{"place":122,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":86},{"place":123,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":85.9},{"place":124,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.7},{"place":125,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":85.64},{"place":126,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.6},{"place":127,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":85.57},{"place":128,"model":"gemini-1.5-pro-exp-0801","company":"google","family":"Gemini","version":"Gemini 1.0","score":85.53},{"place":129,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":85.31},{"place":130,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.3},{"place":131,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.9},{"place":132,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.9},{"place":133,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":84.8},{"place":134,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":84.7},{"place":135,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":84.4},{"place":136,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84.2},{"place":137,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":84.2},{"place":138,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":84.1},{"place":139,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.9},{"place":140,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.9},{"place":141,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.8},{"place":142,"model":"qwen3-14b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":83.7},{"place":143,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":83.7},{"place":144,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.66},{"place":145,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":83.5},{"place":146,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.41},{"place":147,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.2},{"place":148,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":83},{"place":149,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":83},{"place":150,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":82.97},{"place":151,"model":"mistral-large-2407","company":"mistral","family":"Mistral","version":"Mistral","score":82.97},{"place":152,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":82.76},{"place":153,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":82.54},{"place":154,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":82.15},{"place":155,"model":"gemini-1.5-flash-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":82.11},{"place":156,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":82},{"place":157,"model":"ministral-3-14b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":82},{"place":158,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82},{"place":159,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81.7},{"place":160,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":81.64},{"place":161,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":81.61},{"place":162,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":81.6},{"place":163,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.5},{"place":164,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":81.5},{"place":165,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":81.5},{"place":166,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":81.3},{"place":167,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.2},{"place":168,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.17},{"place":169,"model":"yi-large","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":81.17},{"place":170,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.9},{"place":171,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":80.81},{"place":172,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":80.5},{"place":173,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.4},{"place":174,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":80.4},{"place":175,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":80.35},{"place":176,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":80.3},{"place":177,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":80.24},{"place":178,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":80.1},{"place":179,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":80},{"place":180,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80},{"place":181,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":80},{"place":182,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80},{"place":183,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":79.9},{"place":184,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":79.88},{"place":185,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.8},{"place":186,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":79.7},{"place":187,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":79.63},{"place":188,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":79.63},{"place":189,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.6},{"place":190,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79.5},{"place":191,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":79.4},{"place":192,"model":"ministral-3-8b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":79.3},{"place":193,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":78.9},{"place":194,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":78.68},{"place":195,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":78.1},{"place":196,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":78.1},{"place":197,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":78.01},{"place":198,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":77.9},{"place":199,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":77.5},{"place":200,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":77.4},{"place":201,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":77.36},{"place":202,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":77.14},{"place":203,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":76.8},{"place":204,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":76.7},{"place":205,"model":"athene-70b","company":"nvidia","family":"Athene","version":"Athene V2","score":76.64},{"place":206,"model":"gemma-3-12b-base","company":"google","family":"Gemma","version":"Gemma 3","score":76.6},{"place":207,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.6},{"place":208,"model":"reka-core-20240501","company":"reka","family":"Reka","version":"Reka Core","score":76.42},{"place":209,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":76.2},{"place":210,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":75.9},{"place":211,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":75.8},{"place":212,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":75.7},{"place":213,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":75.67},{"place":214,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":75.6},{"place":215,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":75.6},{"place":216,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.4},{"place":217,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.13},{"place":218,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":75},{"place":219,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":74.9},{"place":220,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":74.87},{"place":221,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":74.8},{"place":222,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.1},{"place":223,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":74.1},{"place":224,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":73.9},{"place":225,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.9},{"place":226,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":73.8},{"place":227,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":73.5},{"place":228,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":73.5},{"place":229,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":73.3},{"place":230,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":72.9},{"place":231,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":72.82},{"place":232,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":72.8},{"place":233,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":72.79},{"place":234,"model":"rnd1-base-0910","company":"radicalnumerics","family":"RND1","version":"RND1","score":72.6},{"place":235,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":72.6},{"place":236,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":72.4},{"place":237,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":72.4},{"place":238,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":72.32},{"place":239,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":71.9},{"place":240,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.8},{"place":241,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":71.8},{"place":242,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":71.5},{"place":243,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":71.3},{"place":244,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.1},{"place":245,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":70.34},{"place":246,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":70.06},{"place":247,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":69.85},{"place":248,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":69.6},{"place":249,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":69},{"place":250,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":68.9},{"place":251,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":68.61},{"place":252,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":68.5},{"place":253,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":68.36},{"place":254,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":68.1},{"place":255,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":67.9},{"place":256,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":67.7},{"place":257,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":67.67},{"place":258,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":67.3},{"place":259,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":67.24},{"place":260,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":67.2},{"place":261,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":66.92},{"place":262,"model":"moonlight-instruct","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":66.9},{"place":263,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":66.88},{"place":264,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":66.6},{"place":265,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":66.08},{"place":266,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":65.05},{"place":267,"model":"reka-flash-21b-20240226","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226","score":64.72},{"place":268,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.4},{"place":269,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":64.4},{"place":270,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":64.25},{"place":271,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.7},{"place":272,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":63.17},{"place":273,"model":"gemma-3-4b-base","company":"google","family":"Gemma","version":"Gemma 3","score":62.6},{"place":274,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.4},{"place":275,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.2},{"place":276,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":61.66},{"place":277,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":61.6},{"place":278,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.5},{"place":279,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":61.12},{"place":280,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":60.07},{"place":281,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":59.9},{"place":282,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.5},{"place":283,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":59.5},{"place":284,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.5},{"place":285,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":58.3},{"place":286,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":58.1},{"place":287,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.6},{"place":288,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.47},{"place":289,"model":"llama-3-instruct-8b-simpo-v0.2","company":"princeton-nlp","family":"Llama","version":"Llama 3","score":55.22},{"place":290,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":54.16},{"place":291,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":53},{"place":292,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":52.7},{"place":293,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":51.94},{"place":294,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":51.9},{"place":295,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":51.8},{"place":296,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":51.2},{"place":297,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":50.9},{"place":298,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":50.9},{"place":299,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.7},{"place":300,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":48.8},{"place":301,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":48},{"place":302,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.1},{"place":303,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":43.79},{"place":304,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":41.2},{"place":305,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":41.2},{"place":306,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":41.11},{"place":307,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":40.7},{"place":308,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":40.6},{"place":309,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":38.7},{"place":310,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":38.6},{"place":311,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":38.1},{"place":312,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":37},{"place":313,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":36.5},{"place":314,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":24.5},{"place":315,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.1},{"place":316,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":12.9}]},{"id":"mmlu-stem","name":"MMLU-STEM","topic":"STEM knowledge","description":"STEM subset of MMLU.","url":"https://github.com/hendrycks/test","leaderboard":"","github":"","paper":"","metric":"percent","stars":"1488","top_model":"Qwen3-8B","top_percent":92.5,"top_model_id":"qwen3-8b","top_generation":"Qwen3","top_model_base":"Qwen3 8B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":106,"total_models":3854,"placements":[{"place":1,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":92.5},{"place":2,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":92.2},{"place":3,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":84.4},{"place":4,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":83.57},{"place":5,"model":"qwen2.5-math-72b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":82.8},{"place":6,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":82.7},{"place":7,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.7},{"place":8,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.59},{"place":9,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.37},{"place":10,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":82},{"place":11,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.64},{"place":12,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":80.9},{"place":13,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":80.8},{"place":14,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":80.4},{"place":15,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":80},{"place":16,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":79.9},{"place":17,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":79.9},{"place":18,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":79.6},{"place":19,"model":"qwen2-math-72b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":79.1},{"place":20,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":78.1},{"place":21,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":77.61},{"place":22,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":76.7},{"place":23,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.4},{"place":24,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":76},{"place":25,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":75.2},{"place":26,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":75.1},{"place":27,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":74.88},{"place":28,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":73.9},{"place":29,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":73.7},{"place":30,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":73.55},{"place":31,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":72.6},{"place":32,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.3},{"place":33,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":71.9},{"place":34,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":71.7},{"place":35,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":71},{"place":36,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":70.57},{"place":37,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":69.93},{"place":38,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":69.8},{"place":39,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.36},{"place":40,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":68.6},{"place":41,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":68.2},{"place":42,"model":"qwen2.5-math-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":67.8},{"place":43,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":67.6},{"place":44,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":67.6},{"place":45,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":67.6},{"place":46,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.46},{"place":47,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":67.43},{"place":48,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":67.3},{"place":49,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.89},{"place":50,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.54},{"place":51,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.5},{"place":52,"model":"qwen2-math-7b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":65.7},{"place":53,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":65.1},{"place":54,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":64.8},{"place":55,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":64.6},{"place":56,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":64.5},{"place":57,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":64.2},{"place":58,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":64.2},{"place":59,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":64.13},{"place":60,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":64},{"place":61,"model":"minerva-540b","company":"google","family":"Minerva","version":"Minerva","score":63.9},{"place":62,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":63.8},{"place":63,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":63.5},{"place":64,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":63.5},{"place":65,"model":"internlm2-math-base-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math","score":63},{"place":66,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":62.8},{"place":67,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.5},{"place":68,"model":"numinamath-7b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":60.8},{"place":69,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":60.5},{"place":70,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.78},{"place":71,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.7},{"place":72,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":59.5},{"place":73,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":59.31},{"place":74,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":58.5},{"place":75,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":58.1},{"place":76,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":57.5},{"place":77,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":56.5},{"place":78,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":56.11},{"place":79,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":56},{"place":80,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":55.7},{"place":81,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":55.6},{"place":82,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":55.3},{"place":83,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":55.2},{"place":84,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":54.9},{"place":85,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.8},{"place":86,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":54.55},{"place":87,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.3},{"place":88,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.04},{"place":89,"model":"minerva-62b","company":"google","family":"Minerva","version":"Minerva","score":53.9},{"place":90,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":53.2},{"place":91,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":53.1},{"place":92,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":52.9},{"place":93,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":52.4},{"place":94,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":52.17},{"place":95,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":51.92},{"place":96,"model":"qwen2.5-math-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":51.3},{"place":97,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":51.1},{"place":98,"model":"qwen2-math-1.5b","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":50.4},{"place":99,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":50.1},{"place":100,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":49.2},{"place":101,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":49},{"place":102,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":46.2},{"place":103,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":45.8},{"place":104,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":44.8},{"place":105,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":43.1},{"place":106,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":42.7},{"place":107,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39.83},{"place":108,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":39.8},{"place":109,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":39.8},{"place":110,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":39.64},{"place":111,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":39.6},{"place":112,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.5},{"place":113,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.3},{"place":114,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":39.16},{"place":115,"model":"minerva-8b","company":"google","family":"Minerva","version":"Minerva","score":35.6},{"place":116,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":35.39},{"place":117,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":34.9},{"place":118,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":34.4},{"place":119,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":34.2},{"place":120,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":27.5},{"place":121,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":24.5}]},{"id":"mmmb","name":"MMMB","topic":"Multilingual MMBench","description":"Multilingual Multimodal Benchmark (MMMB) average score.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-4B","top_percent":83.4,"top_model_id":"qwen3.5-4b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.4},{"place":2,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":83},{"place":3,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82},{"place":4,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":81.9},{"place":5,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":81.5},{"place":6,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.5},{"place":7,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.4},{"place":8,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":76.96},{"place":9,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.4},{"place":10,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.3},{"place":11,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.9},{"place":12,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.7},{"place":13,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.5},{"place":14,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.3},{"place":15,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.6},{"place":16,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":73.4},{"place":17,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.3},{"place":18,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":72.8},{"place":19,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.3},{"place":20,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":72.13},{"place":21,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":71.7},{"place":22,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":68.93},{"place":23,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":68.6},{"place":24,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":68.09},{"place":25,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":64.84},{"place":26,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":57.7},{"place":27,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":54.29},{"place":28,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":46.79}]},{"id":"mmmlu","name":"MMMLU","topic":"Multi-domain knowledge (multilingual)","description":"Massively multilingual MMLU-style evaluation across many languages.","url":"https://huggingface.co/LiquidAI/LFM2-350M","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Mythos Preview","top_percent":92.7,"top_model_id":"claude-mythos-preview","top_generation":"Claude Mythos Preview","top_model_base":"Claude Mythos Preview","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":114,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":92.7},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":92.6},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.8},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":91.8},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.8},{"place":6,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":91.5},{"place":7,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.1},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.1},{"place":9,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":91},{"place":10,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91},{"place":11,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.8},{"place":12,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.8},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.6},{"place":14,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":90.6},{"place":15,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.6},{"place":16,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":90.3},{"place":17,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.3},{"place":18,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":90.3},{"place":19,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.1},{"place":20,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.9},{"place":21,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":89.7},{"place":22,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":89.6},{"place":23,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":89.6},{"place":24,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":89.6},{"place":25,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.6},{"place":26,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":89.5},{"place":27,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":89.5},{"place":28,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":89.5},{"place":29,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.5},{"place":30,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.5},{"place":31,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.5},{"place":32,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":89.4},{"place":33,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.3},{"place":34,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.1},{"place":35,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.1},{"place":36,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":89},{"place":37,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":88.9},{"place":38,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.8},{"place":39,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.5},{"place":40,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.4},{"place":41,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":88.1},{"place":42,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":88},{"place":43,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":87.9},{"place":44,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.9},{"place":45,"model":"o1","company":"openai","family":"o1","version":"o1","score":87.7},{"place":46,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":87.7},{"place":47,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":87.5},{"place":48,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":87.3},{"place":49,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":87.2},{"place":50,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":86.8},{"place":51,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.7},{"place":52,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.6},{"place":53,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":86.6},{"place":54,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":86.6},{"place":55,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":86.5},{"place":56,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":86.3},{"place":57,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":86.3},{"place":58,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":86.2},{"place":59,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":86.2},{"place":60,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":86},{"place":61,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.9},{"place":62,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":85.7},{"place":63,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":85.5},{"place":64,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.2},{"place":65,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":85.1},{"place":66,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":84.9},{"place":67,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.5},{"place":68,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.4},{"place":69,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":83.8},{"place":70,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.4},{"place":71,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":83.4},{"place":72,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":83.2},{"place":73,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83},{"place":74,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":81.6},{"place":75,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":81.5},{"place":76,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":81.3},{"place":77,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.2},{"place":78,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":80.15},{"place":79,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":79.54},{"place":80,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":79.4},{"place":81,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":79.26},{"place":82,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":78.4},{"place":83,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":78.2},{"place":84,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":77.63},{"place":85,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.6},{"place":86,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.1},{"place":87,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":74.8},{"place":88,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":73.8},{"place":89,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":73.71},{"place":90,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":73.7},{"place":91,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":71.53},{"place":92,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.3},{"place":93,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.8},{"place":94,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":70.7},{"place":95,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":69.7},{"place":96,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":69.69},{"place":97,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":69.4},{"place":98,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":68.68},{"place":99,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":68.1},{"place":100,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":67.4},{"place":101,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":64.9},{"place":102,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":64.84},{"place":103,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":64.76},{"place":104,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":64},{"place":105,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.1},{"place":106,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":62.76},{"place":107,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":62.3},{"place":108,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60.67},{"place":109,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":59.9},{"place":110,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":57.61},{"place":111,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":57.37},{"place":112,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":57},{"place":113,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":56.6},{"place":114,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":56.59},{"place":115,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":56.5},{"place":116,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":56.4},{"place":117,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":56.13},{"place":118,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":55.39},{"place":119,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":55.26},{"place":120,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":55.14},{"place":121,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":50.14},{"place":122,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":50.02},{"place":123,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":49.6},{"place":124,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":49},{"place":125,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49},{"place":126,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":47.92},{"place":127,"model":"lfm2-1.2b","company":"liquidai","family":"LFM","version":"LFM2","score":46.73},{"place":128,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.7},{"place":129,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.51},{"place":130,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.3},{"place":131,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":44.1},{"place":132,"model":"lfm2-700m","company":"liquidai","family":"LFM","version":"LFM2","score":43.28},{"place":133,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":39.4},{"place":134,"model":"llama-3.2-1.24b","company":"meta","family":"Llama","version":"Llama 3.2","score":38.15},{"place":135,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":37.99},{"place":136,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":34.43},{"place":137,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":30.84},{"place":138,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.783},{"place":139,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.715}]},{"id":"mmmlu-es","name":"MMMLU (ES)","topic":"Multilingual knowledge","description":"Spanish MMMLU benchmark","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"SmolLM3-3B","top_percent":64.7,"top_model_id":"smollm3-3b","top_generation":"SmollM3","top_model_base":"SmolLM3 3B","top_model_family":"SmolLM","top_company":"huggingface","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":64.7},{"place":2,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.5},{"place":3,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":62.4},{"place":4,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":51.4},{"place":5,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":48.8}]},{"id":"mmmu","name":"MMMU","topic":"Multimodal understanding","description":"Multi-discipline multimodal understanding benchmark.","url":"https://mmmu-benchmark.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":87.2,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":317,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.2},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.7},{"place":4,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":85.4},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85.2},{"place":7,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85},{"place":8,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.3},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.22},{"place":10,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":84.2},{"place":11,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.9},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.89},{"place":13,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":83.4},{"place":14,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.3},{"place":15,"model":"o3","company":"openai","family":"o3","version":"o3","score":82.9},{"place":16,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":82.9},{"place":17,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.3},{"place":18,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":82},{"place":19,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.8},{"place":20,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.7},{"place":21,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.7},{"place":22,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.4},{"place":23,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":81.33},{"place":24,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":80.9},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.9},{"place":26,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.7},{"place":27,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.6},{"place":28,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.6},{"place":29,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.4},{"place":30,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":80.22},{"place":31,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":80.11},{"place":32,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":80.11},{"place":33,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":80.1},{"place":34,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":79.89},{"place":35,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":79.8},{"place":36,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":79.8},{"place":37,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.6},{"place":38,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.6},{"place":39,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":79.11},{"place":40,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.1},{"place":41,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":79},{"place":42,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":79},{"place":43,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":79},{"place":44,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.7},{"place":45,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":78.7},{"place":46,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.7},{"place":47,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":78.7},{"place":48,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78.44},{"place":49,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.4},{"place":50,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":78.4},{"place":51,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":78.11},{"place":52,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":78.11},{"place":53,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.1},{"place":54,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":77.9},{"place":55,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.8},{"place":56,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.7},{"place":57,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.6},{"place":58,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":77.44},{"place":59,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":77.3},{"place":60,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":77.2},{"place":61,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":77.11},{"place":62,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":77.1},{"place":63,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":76.9},{"place":64,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":76.9},{"place":65,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.3},{"place":66,"model":"llama-4-behemoth","company":"meta","family":"Llama","version":"Llama 4","score":76.1},{"place":67,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76},{"place":68,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":76},{"place":69,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76},{"place":70,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76},{"place":71,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":75.9},{"place":72,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":75.8},{"place":73,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":75.6},{"place":74,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":75.6},{"place":75,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":75.4},{"place":76,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.33},{"place":77,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":75.2},{"place":78,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":75.1},{"place":79,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":75.1},{"place":80,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.9},{"place":81,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":74.4},{"place":82,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":74.4},{"place":83,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":74.4},{"place":84,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":74.33},{"place":85,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":74.2},{"place":86,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.2},{"place":87,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.1},{"place":88,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":73.66},{"place":89,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.53},{"place":90,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.44},{"place":91,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":73.4},{"place":92,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":73.4},{"place":93,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":73.4},{"place":94,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.4},{"place":95,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.2},{"place":96,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.2},{"place":97,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":72.9},{"place":98,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":72.8},{"place":99,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.7},{"place":100,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":72.7},{"place":101,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.7},{"place":102,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":72.67},{"place":103,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":72.6},{"place":104,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":72.6},{"place":105,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":72.2},{"place":106,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":72.2},{"place":107,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.2},{"place":108,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":72},{"place":109,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":71.7},{"place":110,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":71.69},{"place":111,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":71.4},{"place":112,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":71.17},{"place":113,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":71.14},{"place":114,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":71.1},{"place":115,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.8},{"place":116,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":70.7},{"place":117,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.66},{"place":118,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":70.6},{"place":119,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.6},{"place":120,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":70.4},{"place":121,"model":"qvq-72b","company":"qwen","family":"QvQ","version":"QvQ 72B","score":70.3},{"place":122,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":70.22},{"place":123,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":70.2},{"place":124,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":70.2},{"place":125,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":70.11},{"place":126,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":70.1},{"place":127,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":70},{"place":128,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":69.8},{"place":129,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.6},{"place":130,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":69.4},{"place":131,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":69.4},{"place":132,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":69.3},{"place":133,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":69.2},{"place":134,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":69.2},{"place":135,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":69.1},{"place":136,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69.1},{"place":137,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":69.1},{"place":138,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":69.1},{"place":139,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":68.6},{"place":140,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":68.6},{"place":141,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":68.3},{"place":142,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":68.3},{"place":143,"model":"r-4b-base","company":"tencent","family":"R","version":"R","score":68.1},{"place":144,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":68},{"place":145,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":68},{"place":146,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":68},{"place":147,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":68},{"place":148,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":67.9},{"place":149,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":67.7},{"place":150,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":67.6},{"place":151,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.4},{"place":152,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":66.8},{"place":153,"model":"mimo-vl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":66.7},{"place":154,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":66.7},{"place":155,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":66.66},{"place":156,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":66.6},{"place":157,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":66.1},{"place":158,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":65.9},{"place":159,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":65.9},{"place":160,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.3},{"place":161,"model":"command-a-vision-07-2025","company":"cohere","family":"Command","version":"Command","score":65.3},{"place":162,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":65.3},{"place":163,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":65.2},{"place":164,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":64.9},{"place":165,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":64.9},{"place":166,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":64.6},{"place":167,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.6},{"place":168,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":64.5},{"place":169,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":64.5},{"place":170,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.2},{"place":171,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":64},{"place":172,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":64},{"place":173,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":64},{"place":174,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":63.9},{"place":175,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":63.4},{"place":176,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":63.1},{"place":177,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":63.1},{"place":178,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":63.1},{"place":179,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":62.7},{"place":180,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":62.7},{"place":181,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":62.5},{"place":182,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":62.3},{"place":183,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":62.2},{"place":184,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":62.2},{"place":185,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":62},{"place":186,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":62},{"place":187,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":61.89},{"place":188,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":61.7},{"place":189,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":61.7},{"place":190,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.4},{"place":191,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":61.1},{"place":192,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":60.89},{"place":193,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":60.7},{"place":194,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":60.6},{"place":195,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":60.3},{"place":196,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":60.2},{"place":197,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":60},{"place":198,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":60},{"place":199,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":60},{"place":200,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":59.9},{"place":201,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":59.7},{"place":202,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":59.6},{"place":203,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":59.6},{"place":204,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":59.4},{"place":205,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":59.4},{"place":206,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":59.11},{"place":207,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":59},{"place":208,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":58.9},{"place":209,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":58.6},{"place":210,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":58.6},{"place":211,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":58.5},{"place":212,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":58.2},{"place":213,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":57.8},{"place":214,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":57.6},{"place":215,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.9},{"place":216,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":56.89},{"place":217,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":56.8},{"place":218,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":56.8},{"place":219,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":56.1},{"place":220,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56},{"place":221,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":56},{"place":222,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":55.8},{"place":223,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":55.3},{"place":224,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":55.3},{"place":225,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":55.3},{"place":226,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":55.2},{"place":227,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":55.2},{"place":228,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":55.1},{"place":229,"model":"ovis1.6-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":55},{"place":230,"model":"aria","company":"rhymes","family":"Aria","version":"Aria","score":54.9},{"place":231,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":54.9},{"place":232,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":54.7},{"place":233,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":54.67},{"place":234,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":54.4},{"place":235,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":54.3},{"place":236,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":54.2},{"place":237,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":54.1},{"place":238,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":54.1},{"place":239,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":54.1},{"place":240,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":53.9},{"place":241,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":53.8},{"place":242,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":53.7},{"place":243,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.4},{"place":244,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":53.1},{"place":245,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":53.1},{"place":246,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":53},{"place":247,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":53},{"place":248,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":52.7},{"place":249,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":52.6},{"place":250,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":52.6},{"place":251,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":52.5},{"place":252,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":52.3},{"place":253,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":52.3},{"place":254,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":52},{"place":255,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":52},{"place":256,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":52},{"place":257,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":51.8},{"place":258,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":51.8},{"place":259,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":51.78},{"place":260,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":51.67},{"place":261,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":51.6},{"place":262,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":51.4},{"place":263,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":51.4},{"place":264,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":51.4},{"place":265,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":51.3},{"place":266,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":51.3},{"place":267,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":51.2},{"place":268,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":51.2},{"place":269,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":51.1},{"place":270,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":51.1},{"place":271,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":50.9},{"place":272,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":50.8},{"place":273,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":50.7},{"place":274,"model":"gemini-1.5-flash-8b-0827","company":"google","family":"Gemini","version":"Gemini 1.5","score":50.7},{"place":275,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":50.7},{"place":276,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":50.4},{"place":277,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":50.4},{"place":278,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":50.4},{"place":279,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":50.4},{"place":280,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.3},{"place":281,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":50.2},{"place":282,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":50.1},{"place":283,"model":"llava-next-110b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":50.1},{"place":284,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":50},{"place":285,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":49.9},{"place":286,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":49.8},{"place":287,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":49.7},{"place":288,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":49.7},{"place":289,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":49.3},{"place":290,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":49.3},{"place":291,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.2},{"place":292,"model":"llava-next-110b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":49.1},{"place":293,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49},{"place":294,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49},{"place":295,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":49},{"place":296,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":48.9},{"place":297,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":48.9},{"place":298,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":48.8},{"place":299,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":48.8},{"place":300,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":48.8},{"place":301,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":48.8},{"place":302,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":48.7},{"place":303,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":48.6},{"place":304,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":48.4},{"place":305,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":48.3},{"place":306,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":48},{"place":307,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":48},{"place":308,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":47.9},{"place":309,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":47.9},{"place":310,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":47.9},{"place":311,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47.7},{"place":312,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":47.4},{"place":313,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.4},{"place":314,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.4},{"place":315,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":47.4},{"place":316,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":47.3},{"place":317,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":47.2},{"place":318,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":47.2},{"place":319,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":47},{"place":320,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":46.9},{"place":321,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":46.8},{"place":322,"model":"blip-3o-4b","company":"salesforce","family":"BLIP","version":"BLIP-3O","score":46.6},{"place":323,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":46.5},{"place":324,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":46.1},{"place":325,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":46},{"place":326,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":45.89},{"place":327,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":45.8},{"place":328,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":45.8},{"place":329,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":45.8},{"place":330,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":45.6},{"place":331,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":45.4},{"place":332,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":45.33},{"place":333,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":45.3},{"place":334,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":45.3},{"place":335,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":45.2},{"place":336,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":45.2},{"place":337,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":45.2},{"place":338,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":45.1},{"place":339,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":44.9},{"place":340,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":44.7},{"place":341,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":44.3},{"place":342,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.1},{"place":343,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":43.6},{"place":344,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":43.2},{"place":345,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":43},{"place":346,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":43},{"place":347,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":42.9},{"place":348,"model":"cogvlm2-llama3-chinese-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":42.8},{"place":349,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":42.7},{"place":350,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":42.6},{"place":351,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":42.3},{"place":352,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":42},{"place":353,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":41.89},{"place":354,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":41.8},{"place":355,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":41.8},{"place":356,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":41.7},{"place":357,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":41.6},{"place":358,"model":"bunny-4b","company":"baai","family":"Bunny","version":"Bunny","score":41.4},{"place":359,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":41.4},{"place":360,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":41.3},{"place":361,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":41.2},{"place":362,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":41.1},{"place":363,"model":"blip-3-4b","company":"salesforce","family":"BLIP","version":"BLIP-3","score":41.1},{"place":364,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.1},{"place":365,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":41.1},{"place":366,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":41.1},{"place":367,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":41.1},{"place":368,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":41},{"place":369,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":40.9},{"place":370,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":40.7},{"place":371,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":40.7},{"place":372,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":40.6},{"place":373,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":40.56},{"place":374,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":40.4},{"place":375,"model":"phi-3-vision-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":40.4},{"place":376,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":40.3},{"place":377,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":39.9},{"place":378,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":39.7},{"place":379,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":39.67},{"place":380,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":39.4},{"place":381,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":39.4},{"place":382,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":39.3},{"place":383,"model":"llava-llama-3-8b","company":"llava","family":"LLaVA","version":"LLaVA-LLaMA-3","score":39.2},{"place":384,"model":"harmon-1.5b","company":"harmonai","family":"Harmon","version":"Harmon-1.5B","score":38.9},{"place":385,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":38.78},{"place":386,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":38.3},{"place":387,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":38.3},{"place":388,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":38.2},{"place":389,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":38},{"place":390,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":37.9},{"place":391,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":37.8},{"place":392,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":37.8},{"place":393,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":37.3},{"place":394,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":37.2},{"place":395,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":37.1},{"place":396,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":37},{"place":397,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":37},{"place":398,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":36.7},{"place":399,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":36.6},{"place":400,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":36.6},{"place":401,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":36.4},{"place":402,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":36.3},{"place":403,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":36.3},{"place":404,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":36.3},{"place":405,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":36.2},{"place":406,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":35.9},{"place":407,"model":"llava-next-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":35.8},{"place":408,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":35.8},{"place":409,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":35.7},{"place":410,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":35.6},{"place":411,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":35.4},{"place":412,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":34.9},{"place":413,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":34.9},{"place":414,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":34.44},{"place":415,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":34.3},{"place":416,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":34.1},{"place":417,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":34.1},{"place":418,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":33.9},{"place":419,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":33.8},{"place":420,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":33.6},{"place":421,"model":"vila1.5-3b","company":"nvidia","family":"VILA","version":"VILA 1.5","score":33.3},{"place":422,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":32.9},{"place":423,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":32.9},{"place":424,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":32.9},{"place":425,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":32.67},{"place":426,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":32.6},{"place":427,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":32.3},{"place":428,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":32.2},{"place":429,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":32.1},{"place":430,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":32.1},{"place":431,"model":"mini-gemini-2b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini","score":31.7},{"place":432,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":31.6},{"place":433,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":31.4},{"place":434,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":30.6},{"place":435,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":28.4},{"place":436,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":27.44},{"place":437,"model":"fuyu-8b","company":"adept","family":"Fuyu","version":"Fuyu","score":27.4},{"place":438,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":26.3},{"place":439,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":24},{"place":440,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":22.7}]},{"id":"mmmu-med","name":"MMMU-Med","topic":"Medical QA","description":"Medical/health subset of MMMU (validation).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedMO-8B-Next","top_percent":69.3,"top_model_id":"medmo-8b-next","top_generation":"MedMO-Next","top_model_base":"MedMO","top_model_family":"MedMO","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":69.3},{"place":2,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":64.6},{"place":3,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":63.3},{"place":4,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":63.3},{"place":5,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":58.7},{"place":6,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":54.6},{"place":7,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":54}]},{"id":"mmmu-pro","name":"MMMU PRO","topic":"Multimodal understanding (hard)","description":"Professional/advanced subset of MMMU for multimodal reasoning.","url":"https://mmmu-benchmark.github.io/","leaderboard":"https://mmmu-benchmark.github.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra (max)","top_percent":86.7,"top_model_id":"gpt-6-astra-max","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":252,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":86.7},{"place":2,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":86.5},{"place":3,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":86.4},{"place":4,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":86.3},{"place":5,"model":"gpt-6.1-sol-high","company":"openai","family":"GPT","version":"GPT-6.1","score":85.8},{"place":6,"model":"gpt-6.1-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":85.8},{"place":7,"model":"gpt-6.1-terra-max","company":"openai","family":"GPT","version":"GPT-6.1","score":85.5},{"place":8,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":85.5},{"place":9,"model":"gpt-6.1-terra-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":85.4},{"place":10,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":85.3},{"place":11,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":85.3},{"place":12,"model":"gpt-6.1-terra-high","company":"openai","family":"GPT","version":"GPT-6.1","score":85},{"place":13,"model":"gpt-6.1-sol-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":84.7},{"place":14,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":84.6},{"place":15,"model":"gpt-6.1-terra-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":84.6},{"place":16,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.5},{"place":17,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84.2},{"place":18,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":84},{"place":19,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.99},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.9},{"place":21,"model":"gpt-6.1-terra-low","company":"openai","family":"GPT","version":"GPT-6.1","score":83.7},{"place":22,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":83.6},{"place":23,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83},{"place":24,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83},{"place":25,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82.5},{"place":26,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.3},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82},{"place":28,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":81.8},{"place":29,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.73},{"place":30,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.73},{"place":31,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":81.7},{"place":32,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":81.68},{"place":33,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.68},{"place":34,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":81.6},{"place":35,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":81.6},{"place":36,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":81.5},{"place":37,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":81.2},{"place":38,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":81.2},{"place":39,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.2},{"place":40,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.2},{"place":41,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81},{"place":42,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81},{"place":43,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":81},{"place":44,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.9},{"place":45,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":80.7},{"place":46,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.5},{"place":47,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":80.5},{"place":48,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":80.46},{"place":49,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":80.4},{"place":50,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":80.4},{"place":51,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.29},{"place":52,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.1},{"place":53,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":79.9},{"place":54,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":79.5},{"place":55,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":79.5},{"place":56,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":79.5},{"place":57,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":79.5},{"place":58,"model":"darwin-180b-rsi","company":"finalbench","family":"Darwin","version":"Darwin","score":79.48},{"place":59,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":79.4},{"place":60,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":79.4},{"place":61,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":79.2},{"place":62,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":79.1},{"place":63,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79},{"place":64,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":79},{"place":65,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":79},{"place":66,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":79},{"place":67,"model":"ling-3.0-flash-vl","company":"antgroup","family":"Ling","version":"Ling 3.0","score":79},{"place":68,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":78.9},{"place":69,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78.8},{"place":70,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":78.7},{"place":71,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":78.6},{"place":72,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.5},{"place":73,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.5},{"place":74,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":78.4},{"place":75,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":78.4},{"place":76,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":78.4},{"place":77,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":78.4},{"place":78,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":78.2},{"place":79,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":78.1},{"place":80,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":77.92},{"place":81,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":77.9},{"place":82,"model":"gpt-6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":77.9},{"place":83,"model":"gpt-5.6-terra-high","company":"openai","family":"GPT","version":"GPT-5.6","score":77.5},{"place":84,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.4},{"place":85,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.3},{"place":86,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":77},{"place":87,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.9},{"place":88,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.9},{"place":89,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":76.88},{"place":90,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":76.88},{"place":91,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.8},{"place":92,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":76.8},{"place":93,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":76.6},{"place":94,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.5},{"place":95,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":76.5},{"place":96,"model":"o3","company":"openai","family":"o3","version":"o3","score":76.4},{"place":97,"model":"gpt-5.6-terra-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":76.4},{"place":98,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.07},{"place":99,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":76},{"place":100,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76},{"place":101,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76},{"place":102,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":76},{"place":103,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":76},{"place":104,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75.8},{"place":105,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75.6},{"place":106,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":75.49},{"place":107,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":75.4},{"place":108,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75.3},{"place":109,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":75.2},{"place":110,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":75.2},{"place":111,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.1},{"place":112,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":75.1},{"place":113,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75},{"place":114,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75},{"place":115,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":75},{"place":116,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":74.9},{"place":117,"model":"gpt-5.6-terra-low","company":"openai","family":"GPT","version":"GPT-5.6","score":74.9},{"place":118,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":74.73},{"place":119,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":74.5},{"place":120,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.28},{"place":121,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":74.1},{"place":122,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74},{"place":123,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":74},{"place":124,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":74},{"place":125,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":74},{"place":126,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.9},{"place":127,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.9},{"place":128,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":73.9},{"place":129,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.82},{"place":130,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.8},{"place":131,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":73.5},{"place":132,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":73.5},{"place":133,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":73.2},{"place":134,"model":"interfaze-1.1-lite","company":"interfaze","family":"Interfaze","version":"Interfaze 1.1","score":73.2},{"place":135,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73},{"place":136,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":72.8},{"place":137,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":72.77},{"place":138,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.21},{"place":139,"model":"interfaze","company":"interfaze","family":"Interfaze","version":"Interfaze 1","score":71.1},{"place":140,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.92},{"place":141,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.6},{"place":142,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.6},{"place":143,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":70.11},{"place":144,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":70.1},{"place":145,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.1},{"place":146,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":69.97},{"place":147,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.9},{"place":148,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":69.88},{"place":149,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":69.74},{"place":150,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":69.71},{"place":151,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.3},{"place":152,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.3},{"place":153,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":69.2},{"place":154,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.1},{"place":155,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":69},{"place":156,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69},{"place":157,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":68.9},{"place":158,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.8},{"place":159,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":68.7},{"place":160,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":68.63},{"place":161,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":68.6},{"place":162,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.4},{"place":163,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.28},{"place":164,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":68.2},{"place":165,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.1},{"place":166,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.1},{"place":167,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":68},{"place":168,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68},{"place":169,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68},{"place":170,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":68},{"place":171,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.86},{"place":172,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":67.6},{"place":173,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":67.6},{"place":174,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":67.5},{"place":175,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":67.4},{"place":176,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":67.3},{"place":177,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":67.3},{"place":178,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":66.88},{"place":179,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.7},{"place":180,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.3},{"place":181,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":66.3},{"place":182,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":66.3},{"place":183,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":66.1},{"place":184,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":66.06},{"place":185,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":66},{"place":186,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":65.6},{"place":187,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.3},{"place":188,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":65.2},{"place":189,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.19},{"place":190,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.86},{"place":191,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":64.8},{"place":192,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":64.5},{"place":193,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":64.16},{"place":194,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.1},{"place":195,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.02},{"place":196,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":63.5},{"place":197,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":63.41},{"place":198,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.4},{"place":199,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.4},{"place":200,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.12},{"place":201,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":63},{"place":202,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63},{"place":203,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":63},{"place":204,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":62.72},{"place":205,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":62.7},{"place":206,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":61.8},{"place":207,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":61.61},{"place":208,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":61.4},{"place":209,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.9},{"place":210,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":60.6},{"place":211,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.4},{"place":212,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":60.3},{"place":213,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":60.28},{"place":214,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":60},{"place":215,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":59.9},{"place":216,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":59.9},{"place":217,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.7},{"place":218,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":59.6},{"place":219,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":59.6},{"place":220,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":58.6},{"place":221,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.6},{"place":222,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58},{"place":223,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":57.2},{"place":224,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":57.1},{"place":225,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57},{"place":226,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":57},{"place":227,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":56.5},{"place":228,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":56.5},{"place":229,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":56.1},{"place":230,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.9},{"place":231,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.6},{"place":232,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":55.38},{"place":233,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":54.3},{"place":234,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":54},{"place":235,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":53.7},{"place":236,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.2},{"place":237,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.6},{"place":238,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":52.6},{"place":239,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":52.4},{"place":240,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":52.2},{"place":241,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":52.2},{"place":242,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":51.91},{"place":243,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":51.9},{"place":244,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":51.9},{"place":245,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.5},{"place":246,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":51.5},{"place":247,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":51.1},{"place":248,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":51},{"place":249,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.3},{"place":250,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":49.7},{"place":251,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":49.1},{"place":252,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":48.84},{"place":253,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":48.6},{"place":254,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":46.9},{"place":255,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":46.42},{"place":256,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":46.36},{"place":257,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":46.3},{"place":258,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":46.3},{"place":259,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":46.3},{"place":260,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":46.2},{"place":261,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":46.2},{"place":262,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":46.2},{"place":263,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":46},{"place":264,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":45.6},{"place":265,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":45.2},{"place":266,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.2},{"place":267,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":44},{"place":268,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":43.8},{"place":269,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.5},{"place":270,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":43.5},{"place":271,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":43},{"place":272,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.5},{"place":273,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":40.4},{"place":274,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":40.2},{"place":275,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":40},{"place":276,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":39.7},{"place":277,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.1},{"place":278,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":38.79},{"place":279,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":38.4},{"place":280,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":38.3},{"place":281,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":38.21},{"place":282,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":38.03},{"place":283,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":38},{"place":284,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":37.8},{"place":285,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":37.6},{"place":286,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37.5},{"place":287,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":37.4},{"place":288,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":37.1},{"place":289,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":37.1},{"place":290,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":36.5},{"place":291,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.5},{"place":292,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":36.5},{"place":293,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":36.3},{"place":294,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":36.07},{"place":295,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36},{"place":296,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":35.5},{"place":297,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":35.2},{"place":298,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":34.7},{"place":299,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.5},{"place":300,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":34.3},{"place":301,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":34.2},{"place":302,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":34},{"place":303,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.8},{"place":304,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":33.5},{"place":305,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":32.7},{"place":306,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.6},{"place":307,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":31.6},{"place":308,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":31.6},{"place":309,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":31.4},{"place":310,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.4},{"place":311,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.2},{"place":312,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":31},{"place":313,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":30.5},{"place":314,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":30.5},{"place":315,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":30},{"place":316,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":29},{"place":317,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":28.7},{"place":318,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":28.3},{"place":319,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":28},{"place":320,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":27.4},{"place":321,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":27.4},{"place":322,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":27.34},{"place":323,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":27.2},{"place":324,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.9},{"place":325,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":25},{"place":326,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.9},{"place":327,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":24.7},{"place":328,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":24.7},{"place":329,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":23.7},{"place":330,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":23.24},{"place":331,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":22.7},{"place":332,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":21.3},{"place":333,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":21.2},{"place":334,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":20.8},{"place":335,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":20.6},{"place":336,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":20.3},{"place":337,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":20.1},{"place":338,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":19.8},{"place":339,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":19.7},{"place":340,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":19.4},{"place":341,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":18.2},{"place":342,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":15.61},{"place":343,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":14.8}]},{"id":"mmmu-pro-vision","name":"MMMU-Pro (vision)","topic":"Multimodal understanding (vision)","description":"MMMU-Pro vision-only setting.","url":"https://mmmu-benchmark.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":66.93,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":66.93},{"place":2,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":61.5},{"place":3,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.27},{"place":4,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":60.11},{"place":5,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":59.71},{"place":6,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":57.68},{"place":7,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.76},{"place":8,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":52.89},{"place":9,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":49.7},{"place":10,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":48.21},{"place":11,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":48},{"place":12,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":45.9},{"place":13,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":45.8},{"place":14,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":44.4},{"place":15,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":44},{"place":16,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":43.53},{"place":17,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":43.3},{"place":18,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":42.25},{"place":19,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":40.75},{"place":20,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":40.3},{"place":21,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":39.4},{"place":22,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":38},{"place":23,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":37.8},{"place":24,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":36.1},{"place":25,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":35.8},{"place":26,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":32.6},{"place":27,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.1},{"place":28,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":30.4},{"place":29,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":29.4},{"place":30,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":29},{"place":31,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":28.09},{"place":32,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":27.1},{"place":33,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":27},{"place":34,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":25.95},{"place":35,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":25.4},{"place":36,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":24.9},{"place":37,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":24.2},{"place":38,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":24},{"place":39,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":22.94},{"place":40,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":21.3},{"place":41,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":20.1},{"place":42,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":19.9},{"place":43,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":17.2},{"place":44,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":15.5},{"place":45,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":14.9},{"place":46,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":14.1},{"place":47,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":13.6},{"place":48,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":13.47},{"place":49,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":13.1}]},{"id":"mmmu-pro-with-tools","name":"MMMU Pro (with tools)","topic":"Multimodal understanding (with tools)","description":"MMMU-Pro benchmark evaluated with tool access.","url":"https://mmmu-benchmark.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":86.5,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.5},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":84.6},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":83.4},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":83.2},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":82.7},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":82.1},{"place":8,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":82},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":81.5},{"place":10,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":80.4},{"place":11,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":80.4},{"place":12,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.1},{"place":13,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":79.5},{"place":14,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":78},{"place":15,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77.7},{"place":16,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.3},{"place":17,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.3},{"place":18,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.6},{"place":19,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":74.1},{"place":20,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.9},{"place":21,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.9},{"place":22,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":69.5},{"place":23,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.9},{"place":24,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.9}]},{"id":"mmmu-test","name":"MMMU (test)","topic":"Multimodal understanding","description":"MMMU test-set accuracy (multi-discipline college-level multimodal questions).","url":"https://mmmu-benchmark.github.io/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2311.16502","metric":"percent","stars":"","top_model":"InternVL2.5-78B","top_percent":61.8,"top_model_id":"internvl2.5-78b","top_generation":"InternVL2.5","top_model_base":"InternVL2.5-78B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":61.8},{"place":2,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":57.6},{"place":3,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":55.7},{"place":4,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":55.1},{"place":5,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":54.6},{"place":6,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":51.8},{"place":7,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":49.3},{"place":8,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":48.9},{"place":9,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":46.9},{"place":10,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":46.3},{"place":11,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":44.3},{"place":12,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":43.8},{"place":13,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":41.6},{"place":14,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":41.4},{"place":15,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":41},{"place":16,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":40.8},{"place":17,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":38.2},{"place":18,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":37.8},{"place":19,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":35.8},{"place":20,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":34.7},{"place":21,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":34.1},{"place":22,"model":"blip-2-flan-t5-xxl","company":"salesforce","family":"BLIP","version":"BLIP-2","score":34},{"place":23,"model":"instructblip-flan-t5-xxl","company":"salesforce","family":"BLIP","version":"InstructBLIP","score":33.8},{"place":24,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":33.6},{"place":25,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":32.9},{"place":26,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.8},{"place":27,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":32.1},{"place":28,"model":"blip-2-flan-t5-xl","company":"salesforce","family":"BLIP","version":"BLIP-2","score":31},{"place":29,"model":"instructblip-flan-t5-xl","company":"salesforce","family":"BLIP","version":"InstructBLIP","score":30.6},{"place":30,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":30.1}]},{"id":"mmsearch","name":"MMSearch","topic":"Multimodal search","description":"Benchmark for multimodal search engines / LMMs answering queries via image+web search.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2.6 Thinking","top_percent":80,"top_model_id":"kimi-k2.6-thinking","top_generation":"Kimi K2.6","top_model_base":"Kimi K2.6","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80},{"place":2,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":79.7},{"place":3,"model":"ling-3.0-flash-vl","company":"antgroup","family":"Ling","version":"Ling 3.0","score":79},{"place":4,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":78.67},{"place":5,"model":"sensenova-mars-32b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":74.27},{"place":6,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":72.9},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.9},{"place":8,"model":"sensenova-mars-8b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":67.84},{"place":9,"model":"skywork-r1v4","company":"skywork","family":"Skywork","version":"Skywork R1V4","score":66.1},{"place":10,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.9},{"place":11,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":63.8},{"place":12,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.57},{"place":13,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":58.7},{"place":14,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":57.31},{"place":15,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48},{"place":16,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":43.27},{"place":17,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":35.09},{"place":18,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":23.39},{"place":19,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.64},{"place":20,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":18.7},{"place":21,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":16.96},{"place":22,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":15.79},{"place":23,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":11.7},{"place":24,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":11.7},{"place":25,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":7.6}]},{"id":"mmsearch-plus","name":"MMSearch-Plus","topic":"Multimodal search","description":"Harder MMSearch variant requiring fine-grained visual reasoning plus multi-step search.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-5V-Turbo","top_percent":30,"top_model_id":"glm-5v-turbo","top_generation":"GLM 5V","top_model_base":"GLM-5V Turbo","top_model_family":"GLM","top_company":"zai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":30},{"place":2,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":25.6},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":25.6}]},{"id":"mmsi-bench","name":"MMSI-Bench","topic":"Spatial reasoning","description":"Multi-image spatial intelligence benchmark (standard, non-circular evaluation).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":57.9,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":57.9},{"place":2,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":52.8},{"place":3,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":47.2},{"place":4,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":46},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.2},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":44.1},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":41.3},{"place":8,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":41},{"place":9,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":39},{"place":10,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.7},{"place":11,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":37.8},{"place":12,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":35.8},{"place":13,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":35.7},{"place":14,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":32.18},{"place":15,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":31.8},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.8},{"place":17,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":30.7},{"place":18,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":30.1},{"place":19,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":29.4},{"place":20,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":29.2}]},{"id":"mmsibench-circular","name":"MMSIBench (circular)","topic":"Spatial understanding","description":"MMSIBench circular subset for spatial reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":36,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":36},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":35.9},{"place":3,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":31.4},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":27.4},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":25.4},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":22.3},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":17.6},{"place":8,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":17.4},{"place":9,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":17.2},{"place":10,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":11.7}]},{"id":"mmstar","name":"MMStar","topic":"Multimodal reasoning","description":"Broad evaluation of multimodal LLMs across diverse tasks.","url":"https://mmstar-benchmark.github.io/","leaderboard":"","github":"https://github.com/MMStar-Benchmark/MMStar","paper":"https://arxiv.org/abs/2403.20330","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":85.9,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":211,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":85.9},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.8},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":83.78},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":83.6},{"place":6,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.3},{"place":7,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":83.2},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":83.1},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":82.96},{"place":10,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.9},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":82.5},{"place":12,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":82.1},{"place":13,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.9},{"place":14,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":81.8},{"place":15,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.4},{"place":16,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81},{"place":17,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.7},{"place":18,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":80.67},{"place":19,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":80.5},{"place":20,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.5},{"place":21,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.7},{"place":22,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":79.4},{"place":23,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.4},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.18},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.73},{"place":26,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.7},{"place":27,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.7},{"place":28,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":78.33},{"place":29,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.3},{"place":30,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":77.91},{"place":31,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":77.9},{"place":32,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.8},{"place":33,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":77.8},{"place":34,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":77.8},{"place":35,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":77.74},{"place":36,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.7},{"place":37,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":77.64},{"place":38,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.5},{"place":39,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":77.48},{"place":40,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":77.48},{"place":41,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":77.3},{"place":42,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.3},{"place":43,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":77.1},{"place":44,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":77},{"place":45,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.88},{"place":46,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.8},{"place":47,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":76.8},{"place":48,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":76.7},{"place":49,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":76.67},{"place":50,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.5},{"place":51,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.47},{"place":52,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":76.4},{"place":53,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.33},{"place":54,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":76},{"place":55,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":75.9},{"place":56,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":75.87},{"place":57,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":75.87},{"place":58,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.8},{"place":59,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":75.7},{"place":60,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.7},{"place":61,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":75.7},{"place":62,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":75.54},{"place":63,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.5},{"place":64,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":75.5},{"place":65,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.33},{"place":66,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":75.3},{"place":67,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":75.3},{"place":68,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.3},{"place":69,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.13},{"place":70,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.93},{"place":71,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":74.9},{"place":72,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":74.9},{"place":73,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":74.88},{"place":74,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":74.7},{"place":75,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":74.46},{"place":76,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.4},{"place":77,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.3},{"place":78,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":74.26},{"place":79,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":74.1},{"place":80,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":74.1},{"place":81,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":74.1},{"place":82,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.86},{"place":83,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.8},{"place":84,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.6},{"place":85,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":73.6},{"place":86,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.58},{"place":87,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":73.53},{"place":88,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.3},{"place":89,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":73.2},{"place":90,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.2},{"place":91,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.2},{"place":92,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":73.13},{"place":93,"model":"r-4b-base","company":"tencent","family":"R","version":"R","score":73.1},{"place":94,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":73.1},{"place":95,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":72.93},{"place":96,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":72.9},{"place":97,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":72.8},{"place":98,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.3},{"place":99,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.1},{"place":100,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":72.1},{"place":101,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":72.1},{"place":102,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":72},{"place":103,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.7},{"place":104,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":71.6},{"place":105,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.3},{"place":106,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":71.13},{"place":107,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":71.13},{"place":108,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":71.1},{"place":109,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":71.1},{"place":110,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.93},{"place":111,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.9},{"place":112,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":70.9},{"place":113,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":70.8},{"place":114,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":70.66},{"place":115,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":70.4},{"place":116,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":70.2},{"place":117,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":70.2},{"place":118,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":70.1},{"place":119,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":70},{"place":120,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.9},{"place":121,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":69.83},{"place":122,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.8},{"place":123,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.73},{"place":124,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":69.66},{"place":125,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":69.6},{"place":126,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":69.6},{"place":127,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":69.53},{"place":128,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":69.5},{"place":129,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":69.3},{"place":130,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":69.3},{"place":131,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.1},{"place":132,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":69},{"place":133,"model":"internvl3-8b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":68.7},{"place":134,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":68.6},{"place":135,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":68.5},{"place":136,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":68.5},{"place":137,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":68.3},{"place":138,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":68.3},{"place":139,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.1},{"place":140,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":68},{"place":141,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.9},{"place":142,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":67.9},{"place":143,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":67.87},{"place":144,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":67.73},{"place":145,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":67.4},{"place":146,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.4},{"place":147,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":67.32},{"place":148,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":67},{"place":149,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":66.67},{"place":150,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":66.5},{"place":151,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":65.8},{"place":152,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":65.5},{"place":153,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":65.4},{"place":154,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":65.3},{"place":155,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":65.27},{"place":156,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":65.2},{"place":157,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":65.1},{"place":158,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":65},{"place":159,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":64.93},{"place":160,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":64.8},{"place":161,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":64.7},{"place":162,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":64.7},{"place":163,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":64.5},{"place":164,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":64.13},{"place":165,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":64.1},{"place":166,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":64.1},{"place":167,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":64.1},{"place":168,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":64},{"place":169,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":63.9},{"place":170,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":63.9},{"place":171,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":63.9},{"place":172,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":63.6},{"place":173,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":63.5},{"place":174,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":63.4},{"place":175,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":63.3},{"place":176,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":63.3},{"place":177,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":63.07},{"place":178,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":62.9},{"place":179,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":62.8},{"place":180,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":62.2},{"place":181,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":62.2},{"place":182,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.04},{"place":183,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62},{"place":184,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":62},{"place":185,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":61.93},{"place":186,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.9},{"place":187,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":61.5},{"place":188,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.4},{"place":189,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":61.3},{"place":190,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":61.24},{"place":191,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":61.2},{"place":192,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":61.1},{"place":193,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":61},{"place":194,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":61},{"place":195,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":60.7},{"place":196,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":60.7},{"place":197,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":60.1},{"place":198,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":60},{"place":199,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":60},{"place":200,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":59.9},{"place":201,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":59.9},{"place":202,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":59.63},{"place":203,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":59.4},{"place":204,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.3},{"place":205,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":59.1},{"place":206,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":58.7},{"place":207,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.3},{"place":208,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.3},{"place":209,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.3},{"place":210,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":58.3},{"place":211,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.1},{"place":212,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":58},{"place":213,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.9},{"place":214,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":57.73},{"place":215,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":57.7},{"place":216,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57.7},{"place":217,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57.67},{"place":218,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57.5},{"place":219,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":57.5},{"place":220,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":57.3},{"place":221,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":57.13},{"place":222,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":57.1},{"place":223,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":57.1},{"place":224,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":57},{"place":225,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":56.13},{"place":226,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":56},{"place":227,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":56},{"place":228,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.9},{"place":229,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55.7},{"place":230,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":55.4},{"place":231,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.1},{"place":232,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":54.7},{"place":233,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":54.3},{"place":234,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":54.2},{"place":235,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":54.1},{"place":236,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":53.7},{"place":237,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":53.13},{"place":238,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":53.1},{"place":239,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.9},{"place":240,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.9},{"place":241,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":51.8},{"place":242,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":51.8},{"place":243,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":51.6},{"place":244,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":51},{"place":245,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":50.8},{"place":246,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":50.7},{"place":247,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":50.67},{"place":248,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":50.6},{"place":249,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":50.5},{"place":250,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":50.33},{"place":251,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":50.27},{"place":252,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":50.1},{"place":253,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":50.1},{"place":254,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":50},{"place":255,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":49.87},{"place":256,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":49.8},{"place":257,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":49.7},{"place":258,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":49.5},{"place":259,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":49.5},{"place":260,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":48},{"place":261,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":48},{"place":262,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":47.5},{"place":263,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":46},{"place":264,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":45.9},{"place":265,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":45.9},{"place":266,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":45.7},{"place":267,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":45.7},{"place":268,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.3},{"place":269,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":43},{"place":270,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":42.6},{"place":271,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":41.3},{"place":272,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":40.87},{"place":273,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":39.9},{"place":274,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":38.6},{"place":275,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":38.3},{"place":276,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":38.3},{"place":277,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":38.2},{"place":278,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":37.7},{"place":279,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":37.5},{"place":280,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":36.5},{"place":281,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":34.3},{"place":282,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":33},{"place":283,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":32.8},{"place":284,"model":"granite-docling-258m","company":"IBM","family":"Granite","version":"Granite Docling","score":30},{"place":285,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":26.13},{"place":286,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":22.4},{"place":287,"model":"smoldocling-256m-preview","company":"IBM","family":"Docling","version":"SMoLDocling","score":17}]},{"id":"mmt-bench","name":"MMT-Bench","topic":"Multimodal multitask understanding","description":"Large-scale multimodal multitask benchmark covering diverse meta-tasks for LVLMs.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.16006","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":75.73,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":63,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.73},{"place":2,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":75.47},{"place":3,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":73.58},{"place":4,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":72.82},{"place":5,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":72.7},{"place":6,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":72.53},{"place":7,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":71.8},{"place":8,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":71.7},{"place":9,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.9},{"place":10,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":70.8},{"place":11,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.7},{"place":12,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":70.4},{"place":13,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":70},{"place":14,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":70},{"place":15,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":69.7},{"place":16,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":69.7},{"place":17,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.1},{"place":18,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.4},{"place":19,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":66.9},{"place":20,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":66.7},{"place":21,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":66.7},{"place":22,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":66.2},{"place":23,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":65.5},{"place":24,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":65.4},{"place":25,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":64.5},{"place":26,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":64.3},{"place":27,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":64},{"place":28,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":63.7},{"place":29,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":63.7},{"place":30,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":63.6},{"place":31,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":63.4},{"place":32,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":62.9},{"place":33,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":62.5},{"place":34,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":62.4},{"place":35,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":62.3},{"place":36,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":62.3},{"place":37,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":62},{"place":38,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":61.69},{"place":39,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":61.6},{"place":40,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.9},{"place":41,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":60.8},{"place":42,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":60.8},{"place":43,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":60.6},{"place":44,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":60},{"place":45,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":60},{"place":46,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":59},{"place":47,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":58},{"place":48,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.2},{"place":49,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":56.7},{"place":50,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":55.7},{"place":51,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":55.7},{"place":52,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":55.1},{"place":53,"model":"blip-2-flan-t5-xxl","company":"salesforce","family":"BLIP","version":"BLIP-2","score":54.8},{"place":54,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":54.5},{"place":55,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":54.5},{"place":56,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":54.5},{"place":57,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":54.4},{"place":58,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":54.2},{"place":59,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":54.1},{"place":60,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":53.6},{"place":61,"model":"monkey-chat","company":"hust","family":"Monkey","version":"Monkey-Chat","score":53.4},{"place":62,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.2},{"place":63,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":53.2},{"place":64,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":53.2},{"place":65,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":52.2},{"place":66,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":51.6},{"place":67,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.9},{"place":68,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":50.4},{"place":69,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":50.3},{"place":70,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":49.5}]},{"id":"mmvet","name":"MMVet","topic":"Multimodal evaluation","description":"Comprehensive evaluation suite for assessing multimodal LLM capabilities.","url":"https://mm-vet.github.io/","leaderboard":"","github":"https://github.com/yuweihao/MM-Vet","paper":"https://arxiv.org/abs/2308.02490","metric":"percent","stars":"","top_model":"R-4B-Base","top_percent":85.9,"top_model_id":"r-4b-base","top_generation":"R","top_model_base":"R-4B","top_model_family":"R","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":107,"total_models":3854,"placements":[{"place":1,"model":"r-4b-base","company":"tencent","family":"R","version":"R","score":85.9},{"place":2,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":85.64},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.3},{"place":4,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":83.1},{"place":5,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":82.3},{"place":6,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.4},{"place":7,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.2},{"place":8,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":78.8},{"place":9,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":78},{"place":10,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":77.6},{"place":11,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":76.9},{"place":12,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.4},{"place":13,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":74.8},{"place":14,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":74.8},{"place":15,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":74.6},{"place":16,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":74.4},{"place":17,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":74},{"place":18,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":74},{"place":19,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":73.85},{"place":20,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.7},{"place":21,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":73.6},{"place":22,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":72.3},{"place":23,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":71.1},{"place":24,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":70.4},{"place":25,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":70.1},{"place":26,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.8},{"place":27,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":69.1},{"place":28,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":69.1},{"place":29,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":69},{"place":30,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":68.8},{"place":31,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.3},{"place":32,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":67.7},{"place":33,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":67.6},{"place":34,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":67.5},{"place":35,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":67.5},{"place":36,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":66.9},{"place":37,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":66.9},{"place":38,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":66.6},{"place":39,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":66},{"place":40,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":66},{"place":41,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":65.7},{"place":42,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":65.5},{"place":43,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":65.4},{"place":44,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":65},{"place":45,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":64.6},{"place":46,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":64.3},{"place":47,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":64.3},{"place":48,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":64},{"place":49,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":63.3},{"place":50,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":62.8},{"place":51,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":62.8},{"place":52,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":62.1},{"place":53,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":62},{"place":54,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":62},{"place":55,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":61.8},{"place":56,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":61.5},{"place":57,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":61.1},{"place":58,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":60.8},{"place":59,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":60.6},{"place":60,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":60.6},{"place":61,"model":"cogvlm2-llama3-chinese-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":60.5},{"place":62,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":60.4},{"place":63,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":60},{"place":64,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":60},{"place":65,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":59.3},{"place":66,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":59.2},{"place":67,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":58.1},{"place":68,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":58},{"place":69,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":57.4},{"place":70,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":56.8},{"place":71,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":56.8},{"place":72,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":55.7},{"place":73,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":55.4},{"place":74,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":54.9},{"place":75,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":54.5},{"place":76,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":54.3},{"place":77,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":54.2},{"place":78,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":53.2},{"place":79,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":53.2},{"place":80,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":52.8},{"place":81,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":52.8},{"place":82,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":52},{"place":83,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":52},{"place":84,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":51.7},{"place":85,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":51.7},{"place":86,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":51.2},{"place":87,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":51.1},{"place":88,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":51},{"place":89,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":50.7},{"place":90,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":49.9},{"place":91,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":49.5},{"place":92,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":49.5},{"place":93,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":48.9},{"place":94,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":48.8},{"place":95,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":48.7},{"place":96,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":48.5},{"place":97,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":48.4},{"place":98,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":47.3},{"place":99,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":46.7},{"place":100,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":44.9},{"place":101,"model":"llava-next-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":43.9},{"place":102,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":43.2},{"place":103,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":41.6},{"place":104,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":41.5},{"place":105,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":41.1},{"place":106,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":40.2},{"place":107,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":39.7},{"place":108,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":39.5},{"place":109,"model":"vila-13b","company":"nvidia","family":"VILA","version":"VILA","score":38.8},{"place":110,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":38.3},{"place":111,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":37.6},{"place":112,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":37.2},{"place":113,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":36.3},{"place":114,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":36.2},{"place":115,"model":"dreamllm-7b","company":"megvii","family":"DreamLLM","version":"DreamLLM","score":35.9},{"place":116,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":35.4},{"place":117,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":35.2},{"place":118,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":34.8},{"place":119,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":33.85},{"place":120,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":33},{"place":121,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.7},{"place":122,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":32.2},{"place":123,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":31.1},{"place":124,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":31},{"place":125,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":30.5},{"place":126,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":29.9},{"place":127,"model":"llava-phi","company":"midea","family":"LLaVA","version":"LLaVA-Phi","score":28.9},{"place":128,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":26.7},{"place":129,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":26.2},{"place":130,"model":"instructblip-13b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":25.6},{"place":131,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":24.8},{"place":132,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":22.1}]},{"id":"mmvet-v2","name":"MM-Vet v2","topic":"Multimodal evaluation","description":"MM-Vet v2: integrated capabilities incl. image-text sequence understanding; GPT-4 graded.","url":"https://github.com/yuweihao/MM-Vet","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2408.00765","metric":"percent","stars":"","top_model":"Claude 3.5 Sonnet 20240620","top_percent":71.8,"top_model_id":"claude-3.5-sonnet-20240620","top_generation":"Claude 3.5","top_model_base":"Claude 3.5 Sonnet","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":71.8},{"place":2,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":71},{"place":3,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":68.4},{"place":4,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":66.9},{"place":5,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":66.9},{"place":6,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":66.3},{"place":7,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":65.5},{"place":8,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":63.8},{"place":9,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":62.1},{"place":10,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":60.8},{"place":11,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":58.1},{"place":12,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":57.2},{"place":13,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":55.8},{"place":14,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":55.4},{"place":15,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":52.3},{"place":16,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":52.3},{"place":17,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":51.5},{"place":18,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":46.6},{"place":19,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":43.2},{"place":20,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":39.6},{"place":21,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":36.1}]},{"id":"mmvp","name":"MMVP","topic":"Multimodal video perception","description":"Benchmark for multimodal video understanding and perception.","url":"https://mmvp-benchmark.github.io/","leaderboard":"","github":"https://github.com/Metaverse-AI-Lab-THU/MMVP-Dataset","paper":"https://arxiv.org/abs/2308.16154","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":91.6,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":91.6},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.3},{"place":4,"model":"r-4b-rl","company":"tencent","family":"R","version":"R","score":80.7},{"place":5,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":77},{"place":6,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":74.7},{"place":7,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":73.33},{"place":8,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":72},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.7},{"place":10,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":69.3},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.33},{"place":12,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":66}]},{"id":"mmvu","name":"MMVU","topic":"Video understanding","description":"Multimodal video understanding benchmark (MMVU).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":87.34,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":69,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":87.34},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":83.7},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.4},{"place":4,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":82.3},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":82.1},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.7},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":81.2},{"place":8,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":81.1},{"place":9,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":80.8},{"place":10,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":80.8},{"place":11,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":80.7},{"place":12,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":80.5},{"place":13,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":80.4},{"place":14,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":80.4},{"place":15,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.4},{"place":16,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":79.9},{"place":17,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":79.2},{"place":18,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78.88},{"place":19,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":78.2},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":77.9},{"place":21,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":77.9},{"place":22,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77.5},{"place":23,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.3},{"place":24,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.3},{"place":25,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":76.7},{"place":26,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":76.6},{"place":27,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.3},{"place":28,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.1},{"place":29,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":75.8},{"place":30,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.4},{"place":31,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":75},{"place":32,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.7},{"place":33,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.3},{"place":34,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":73.1},{"place":35,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72.7},{"place":36,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.3},{"place":37,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":72.24},{"place":38,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":72},{"place":39,"model":"reka-edge-2603","company":"reka","family":"Reka Edge","version":"Reka Edge","score":71.68},{"place":40,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.1},{"place":41,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.1},{"place":42,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.6},{"place":43,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":70.1},{"place":44,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":69.8},{"place":45,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":69},{"place":46,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":68.7},{"place":47,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.64},{"place":48,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.8},{"place":49,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":67.5},{"place":50,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":67.4},{"place":51,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.1},{"place":52,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.3},{"place":53,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.9},{"place":54,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":63.1},{"place":55,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":62.7},{"place":56,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":60.2},{"place":57,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":60},{"place":58,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":59.4},{"place":59,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.7},{"place":60,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.6},{"place":61,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":57.7},{"place":62,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":57.5},{"place":63,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":53.9},{"place":64,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":53.1},{"place":65,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":51.52},{"place":66,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":51.5},{"place":67,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":51},{"place":68,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":50.2},{"place":69,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.9},{"place":70,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.6},{"place":71,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":42.7},{"place":72,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":42.7},{"place":73,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.7},{"place":74,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":34.5},{"place":75,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.3},{"place":76,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":33.5}]},{"id":"mobile-actions","name":"Mobile Actions","topic":"Tool use","description":"Google Mobile Actions dataset: function calling for on-device Android actions (FunctionGemma eval).","url":"https://huggingface.co/datasets/google/mobile-actions","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-9B","top_percent":91.78,"top_model_id":"qwen3.5-9b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 9B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.78},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.39},{"place":3,"model":"reka-edge-2603","company":"reka","family":"Reka Edge","version":"Reka Edge","score":88.4},{"place":4,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":77.94}]},{"id":"mobileworld","name":"MobileWorld","topic":"Mobile GUI agents","description":"Benchmark of agents completing tasks in mobile (Android) app environments.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":85.5,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85.5},{"place":2,"model":"qwen-ui-agent-27b","company":"qwen","family":"Qwen","version":"Qwen-UI-Agent","score":82.1},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":77.8},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":76.9},{"place":5,"model":"ui-venus-2-27b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":76.1},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":67.5},{"place":7,"model":"ui-venus-2-9b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":65.8},{"place":8,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.6},{"place":9,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.2},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":58.1},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":57.3},{"place":12,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":56.4},{"place":13,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":52.1},{"place":14,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":51.2},{"place":15,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.8},{"place":16,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":36.8},{"place":17,"model":"llada-ui","company":"antgroup","family":"LLaDA","version":"LLaDA-UI","score":25.6},{"place":18,"model":"mai-ui-8b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":24.9},{"place":19,"model":"doubao-1.5-ui-tars","company":"bytedance","family":"UI-TARS","version":"UI-TARS-1.5","score":20.9},{"place":20,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18},{"place":21,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":17.9},{"place":22,"model":"ui-venus-1.5-30b-a3b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":17.1},{"place":23,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":10.4},{"place":24,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":9.5},{"place":25,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":9.4},{"place":26,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":9},{"place":27,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":8.5},{"place":28,"model":"gui-owl-7b","company":"alibaba","family":"GUI","version":"GUI","score":7.7},{"place":29,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":7},{"place":30,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":5.5},{"place":31,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":5.5},{"place":32,"model":"gui-owl-32b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl","score":5.5},{"place":33,"model":"gui-owl-7b","company":"alibaba","family":"GUI","version":"GUI","score":4.5}]},{"id":"mol-instructions","name":"Mol-Instructions","topic":"Bio-molecular instruction following","description":"Instruction-following benchmark for bio-molecular understanding and generation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-S2-397B","top_percent":53.95,"top_model_id":"intern-s2-397b","top_generation":"Intern-S2","top_model_base":"Intern-S2-397B","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":53.95},{"place":2,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":52.37},{"place":3,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":48.82},{"place":4,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":48.8},{"place":5,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":45.73},{"place":6,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":44.58},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":40.49},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":38.84},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":38.35},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":34.6},{"place":11,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":24.56},{"place":12,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.7},{"place":13,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":20},{"place":14,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":19.58},{"place":15,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":16.67},{"place":16,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":13.54},{"place":17,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":12.3},{"place":18,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":12.06},{"place":19,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":11.65},{"place":20,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":9.65},{"place":21,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":8.9},{"place":22,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":7.87},{"place":23,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":6.55},{"place":24,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":5.89}]},{"id":"molbench-bind","name":"MolBench-bind","topic":"Molecular science agents","description":"MolBench binding-affinity subset: scientific agentic tasks on molecular binding prediction.","url":"https://huggingface.co/InternScience/Agents-A1","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":62.2,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":62.2},{"place":2,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":56.8},{"place":3,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":51.4},{"place":4,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":48.7},{"place":5,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46},{"place":6,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":45.95},{"place":7,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.8},{"place":8,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":21.6}]},{"id":"molecular-iq","name":"MolecularIQ","topic":"Molecular structure reasoning","description":"Benchmark of molecular structure reasoning for chemistry-capable LLMs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":76.41,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":76.41},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":66.78},{"place":3,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":62.35},{"place":4,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":61.49},{"place":5,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":60.91},{"place":6,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":59.29},{"place":7,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":57.26},{"place":8,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":52.81},{"place":9,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":46.25},{"place":10,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":45.94},{"place":11,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":45.72},{"place":12,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.43},{"place":13,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.48},{"place":14,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":38.94},{"place":15,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.97},{"place":16,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":32.62},{"place":17,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":31.74},{"place":18,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.13},{"place":19,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":25.31}]},{"id":"motionbench","name":"MotionBench","topic":"Video motion understanding","description":"Video motion and temporal reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":75.2,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":55,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":75.2},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":74.9},{"place":3,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":74.8},{"place":4,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":72.4},{"place":5,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":70.9},{"place":6,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":70.6},{"place":7,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":70.6},{"place":8,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":70.4},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.3},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":69.9},{"place":11,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":69.11},{"place":12,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":68.9},{"place":13,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":68.8},{"place":14,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":68.12},{"place":15,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.87},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.3},{"place":17,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65.4},{"place":18,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.11},{"place":19,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":65.1},{"place":20,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":64.8},{"place":21,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62.67},{"place":22,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.6},{"place":23,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":62.4},{"place":24,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":62.3},{"place":25,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":62.2},{"place":26,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62},{"place":27,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":61.7},{"place":28,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":61.6},{"place":29,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":61.4},{"place":30,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":61.4},{"place":31,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":61.4},{"place":32,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":60.6},{"place":33,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":60.6},{"place":34,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":60.4},{"place":35,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60.3},{"place":36,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":60.25},{"place":37,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":60.08},{"place":38,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":60.05},{"place":39,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":59.9},{"place":40,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":59.7},{"place":41,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":59.56},{"place":42,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.3},{"place":43,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":59},{"place":44,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":59},{"place":45,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.6},{"place":46,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.5},{"place":47,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.4},{"place":48,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.9},{"place":49,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":56.6},{"place":50,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":56.5},{"place":51,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":55.7},{"place":52,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":55.1},{"place":53,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":54.55},{"place":54,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":54.3},{"place":55,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":54.2},{"place":56,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":54.2},{"place":57,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.6},{"place":58,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":49.18},{"place":59,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":47.8},{"place":60,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.5},{"place":61,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":28.3}]},{"id":"mpdocbench-truncated-table-teds","name":"MPDocBench-Parse Truncated Table TEDS","topic":"Cross-page tables","description":"MPDocBench-Parse: TEDS on truncated (page-split) tables.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OvisOCR3","top_percent":92.04,"top_model_id":"ovisocr3","top_generation":"OvisOCR3","top_model_base":"OvisOCR3","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":92.04},{"place":2,"model":"mineru2.5-pro-popo","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":91.87},{"place":3,"model":"mineru2.5-pro","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":91.44},{"place":4,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":89.57},{"place":5,"model":"logics-parsing-v3","company":"alibaba","family":"Logics-Parsing","version":"Logics-Parsing-V3","score":88.05},{"place":6,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":83.39}]},{"id":"mrcr-128k","name":"OpenAI-MRCR (128k)","topic":"Long-context reasoning","description":"OpenAI Multi-Round Chain Reasoning benchmark with 128k context window.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"K-EXAONE 2.0","top_percent":94.4,"top_model_id":"k-exaone-2.0","top_generation":"K-EXAONE 2.0","top_model_base":"K-EXAONE 2.0","top_model_family":"K-EXAONE","top_company":"lg","top_open_source":1,"lower_is_better":false,"bench_models":44,"total_models":3854,"placements":[{"place":1,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":94.4},{"place":2,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93},{"place":3,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":92.9},{"place":4,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":92.5},{"place":5,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":90.8},{"place":6,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":90.1},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.7},{"place":8,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.5},{"place":9,"model":"qwenlong-l1.5-30b-a3b","company":"qwen","family":"QwenLong","version":"QwenLong","score":82.99},{"place":10,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":81.9},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.92},{"place":12,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.84},{"place":13,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":77.29},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77},{"place":15,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.8},{"place":16,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":76.1},{"place":17,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":73.4},{"place":18,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":71.5},{"place":19,"model":"qwen3-max-thinking-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":71.24},{"place":20,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":67.2},{"place":21,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":66.17},{"place":22,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":64.88},{"place":23,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":61.6},{"place":24,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":58.6},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":58},{"place":26,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":57.7},{"place":27,"model":"o3","company":"openai","family":"o3","version":"o3","score":56.5},{"place":28,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":56.1},{"place":29,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":55.5},{"place":30,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.4},{"place":31,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":54.6},{"place":32,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":54.3},{"place":33,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.3},{"place":34,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":52.3},{"place":35,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":51.5},{"place":36,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.27},{"place":37,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":48.9},{"place":38,"model":"qwenlong-l1","company":"qwen","family":"QwenLong","version":"QwenLong","score":47.86},{"place":39,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.1},{"place":40,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.1},{"place":41,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":45.7},{"place":42,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.2},{"place":43,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":43.88},{"place":44,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":40.8},{"place":45,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":39.68},{"place":46,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":39.2},{"place":47,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":35.8},{"place":48,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":29.9},{"place":49,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.7},{"place":50,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":27.7},{"place":51,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":20.1}]},{"id":"mrcr-128k-2n","name":"MRCR 128K-2N","topic":"Long-context reasoning","description":"Multi-Round Coreference Resolution benchmark at 128k context with 2 needles.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ministral-3-R 8B","top_percent":50.3,"top_model_id":"ministral-3-r-8b","top_generation":"Ministral 3","top_model_base":"Ministral 3 R 8B","top_model_family":"Ministral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":50.3},{"place":2,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":28.62},{"place":3,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.5},{"place":4,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":14.61},{"place":5,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":9.17}]},{"id":"mrcr-128k-4n","name":"MRCR 128K-4N","topic":"Long-context reasoning","description":"Multi-Round Coreference Resolution benchmark at 128k context with 4 needles.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ministral-3-R 8B","top_percent":22.66,"top_model_id":"ministral-3-r-8b","top_generation":"Ministral 3","top_model_base":"Ministral 3 R 8B","top_model_family":"Ministral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":22.66},{"place":2,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":19.62},{"place":3,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":14.75},{"place":4,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":12.2},{"place":5,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":8.22}]},{"id":"mrcr-128k-8n","name":"MRCR 128K-8N","topic":"Long-context reasoning","description":"Multi-Round Coreference Resolution benchmark at 128k context with 8 needles.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.7 Flash","top_percent":97,"top_model_id":"gemini-3.7-flash","top_generation":"Gemini 3.7","top_model_base":"Gemini 3.7 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":44,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":97},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":94.8},{"place":3,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":93.5},{"place":4,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":91.8},{"place":5,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":91.7},{"place":6,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":90.4},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":86},{"place":8,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.9},{"place":9,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":85.6},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.9},{"place":11,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84.9},{"place":12,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84},{"place":13,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":83.8},{"place":14,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":83.1},{"place":15,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.5},{"place":16,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":81.4},{"place":17,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":77.3},{"place":18,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77},{"place":19,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":74.8},{"place":20,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.4},{"place":21,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":72.2},{"place":22,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":71.6},{"place":23,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":67.2},{"place":24,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":66.4},{"place":25,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":63.1},{"place":26,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":62},{"place":27,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":60.1},{"place":28,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":59.3},{"place":29,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":54.6},{"place":30,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.3},{"place":31,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":52.5},{"place":32,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":47.7},{"place":33,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":44.2},{"place":34,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.1},{"place":35,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.4},{"place":36,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":42.7},{"place":37,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":35.3},{"place":38,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":35.1},{"place":39,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":32},{"place":40,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":30.6},{"place":41,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25.4},{"place":42,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":19.1},{"place":43,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":14.47},{"place":44,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":13.5},{"place":45,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":12.15},{"place":46,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":10.12},{"place":47,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":7.55},{"place":48,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":7.54}]},{"id":"mrcr-16k-8n","name":"MRCR 16K-8N","topic":"Long-context reasoning","description":"OpenAI MRCR v2 8-needle, 8K-16K context bucket.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":93,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":93},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":91.4},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":89.3}]},{"id":"mrcr-1m","name":"OpenAI-MRCR (1M)","topic":"Long-context reasoning","description":"OpenAI Multi-Round Chain Reasoning benchmark with 1M context window.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":92.9,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":92.9},{"place":2,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.5},{"place":3,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.3},{"place":4,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.7},{"place":5,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.9},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.3},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":58.8},{"place":8,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":58.6},{"place":9,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":56.2},{"place":10,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":54},{"place":11,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.7},{"place":12,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.5},{"place":13,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":26.6},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":26.3},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":26.3},{"place":16,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":22.1},{"place":17,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":21.3},{"place":18,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":21},{"place":19,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.4},{"place":20,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":12.3},{"place":21,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":9.6},{"place":22,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":6.1},{"place":23,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":5.4}]},{"id":"mrcr-1m-8n","name":"MRCR 1M-8N","topic":"Long-context reasoning","description":"OpenAI MRCR v2, 8 needles, 512K-1M context bucket.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Spark 1.3","top_percent":98.1,"top_model_id":"muse-spark-1.3","top_generation":"Muse Spark 1.3","top_model_base":"Muse Spark 1.3","top_model_family":"Muse","top_company":"meta","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":98.1},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":96.3},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":74},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.8},{"place":5,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":72.5},{"place":6,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":55.5},{"place":7,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":41.3},{"place":8,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":36.6},{"place":9,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":32.2}]},{"id":"mrcr-256k-8n","name":"MRCR 256K-8N","topic":"Long-context reasoning","description":"OpenAI MRCR v2 8-needle, 128K-256K context bucket.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":93.8,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":93.8},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":92.9},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":87.5},{"place":4,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":86.7},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":83.2},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":79.3},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":77},{"place":8,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":59.2},{"place":9,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":33.6},{"place":10,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":33.1},{"place":11,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":19.4}]},{"id":"mrcr-32k-8n","name":"MRCR 32K-8N","topic":"Long-context reasoning","description":"OpenAI MRCR v2 8-needle, 16K-32K context bucket.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.4","top_percent":97.2,"top_model_id":"gpt-5.4","top_generation":"GPT-5.4","top_model_base":"GPT-5.4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":97.2},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":96.5},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":95.3}]},{"id":"mrcr-512k-8n","name":"MRCR 512K-8N","topic":"Long-context reasoning","description":"OpenAI MRCR v2, 8 needles, 256K-512K context bucket.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":100,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":2,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":98.5},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":91.5},{"place":4,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":89.6},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":81.5},{"place":6,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":66.3},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":57.5},{"place":8,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":41.3}]},{"id":"mrcr-64k-2n","name":"MRCR 64K-2N","topic":"Long-context reasoning","description":"Multi-Round Coreference Resolution benchmark at 64k context with 2 needles.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ministral-3-R 8B","top_percent":44.02,"top_model_id":"ministral-3-r-8b","top_generation":"Ministral 3","top_model_base":"Ministral 3 R 8B","top_model_family":"Ministral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":44.02},{"place":2,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":29.77},{"place":3,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.2},{"place":4,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":20.91},{"place":5,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":13.18}]},{"id":"mrcr-64k-4n","name":"MRCR 64K-4N","topic":"Long-context reasoning","description":"Multi-Round Coreference Resolution benchmark at 64k context with 4 needles.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ministral-3-R 8B","top_percent":35.8,"top_model_id":"ministral-3-r-8b","top_generation":"Ministral 3","top_model_base":"Ministral 3 R 8B","top_model_family":"Ministral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":35.8},{"place":2,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.56},{"place":3,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":20.57},{"place":4,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":13.69},{"place":5,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":9.06}]},{"id":"mrcr-64k-8n","name":"MRCR 64K-8N","topic":"Long-context reasoning","description":"Multi-Round Coreference Resolution benchmark at 64k context with 8 needles.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2","top_percent":92,"top_model_id":"gpt-5.2","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":92},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":90.5},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":90},{"place":4,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":17.82},{"place":5,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":17.23},{"place":6,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":16.56},{"place":7,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":13.24},{"place":8,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":6.93}]},{"id":"mrcr-8k-8n","name":"MRCR 8K-8N","topic":"Long-context reasoning","description":"OpenAI MRCR v2 8-needle, 4K-8K context bucket.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2","top_percent":98.2,"top_model_id":"gpt-5.2","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":98.2},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98.1},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":97.3}]},{"id":"mrcr-v2","name":"MRCR v2","topic":"Multimodal reasoning","description":"Multi-round multimodal chain-of-reasoning evaluation (v2).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":94.8,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":94.8},{"place":2,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":93.6},{"place":3,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":89.4},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":87.9},{"place":5,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":86.6},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.9},{"place":7,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.7},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":79.7},{"place":9,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":79},{"place":10,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":78.4},{"place":11,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":75.5},{"place":12,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":74.4},{"place":13,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":74},{"place":14,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":66.9},{"place":15,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":62.72},{"place":16,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.2},{"place":17,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":55},{"place":18,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":54},{"place":19,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":51.4},{"place":20,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":50.8},{"place":21,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":50.1},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.1},{"place":23,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":33.6}]},{"id":"ms-cxr-t","name":"MS-CXR-T","topic":"Medical imaging","description":"Temporal chest X-ray disease progression classification, macro accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedGemma 1.5 4B","top_percent":65.7,"top_model_id":"medgemma-1.5-4b-it","top_generation":"MedGemma 1.5","top_model_base":"MedGemma","top_model_family":"MedGemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":65.7},{"place":2,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":61.11},{"place":3,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":59},{"place":4,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":50.1}]},{"id":"msearth-mcq","name":"MSEarth-MCQ","topic":"Earth science","description":"Earth science multiple-choice question benchmark for scientific AI models.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":65.8,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65.8},{"place":2,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":65.2},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":62.6},{"place":4,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":61.9},{"place":5,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.7}]},{"id":"msvd-qa","name":"MSVD-QA","topic":"Video QA (open-ended)","description":"Open-ended QA on MSVD video clips; GPT-judged accuracy.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1702.00002","metric":"percent","stars":"","top_model":"Baichuan-Omni","top_percent":72.2,"top_model_id":"baichuan-omni","top_generation":"Baichuan-Omni","top_model_base":"Baichuan-Omni","top_model_family":"Baichuan","top_company":"baichuan","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":72.2},{"place":2,"model":"videollama2-7b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":70.9},{"place":3,"model":"video-llava-7b","company":"pku","family":"Video-LLaVA","version":"Video-LLaVA","score":70.7},{"place":4,"model":"videochat2-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":70},{"place":5,"model":"llava-next-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":67.4},{"place":6,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":63.9},{"place":7,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":61.1}]},{"id":"mt-bench","name":"MT-Bench","topic":"Chat ability","description":"Multi-turn chat evaluation via GPT-4 grading.","url":"https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2306.05685v4","metric":"percent","stars":"39074","top_model":"Apriel Nemotron 15B Thinker","top_percent":85.7,"top_model_id":"apriel-nemotron-15b-thinker","top_generation":"Apriel Nemotron","top_model_base":"Apriel Nemotron 15B Thinker","top_model_family":"Apriel","top_company":"servicenow","top_open_source":1,"lower_is_better":false,"bench_models":149,"total_models":3854,"placements":[{"place":1,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":85.7},{"place":2,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":83.9},{"place":3,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":83.8},{"place":4,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":83.1},{"place":5,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":74.2},{"place":6,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":9.4},{"place":7,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.35},{"place":8,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.3},{"place":9,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":9.26},{"place":10,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":9.2},{"place":11,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.2},{"place":12,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.16},{"place":13,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":9.12},{"place":14,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":9.1},{"place":15,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":9.1},{"place":16,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.09},{"place":17,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":9.08},{"place":18,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.05},{"place":19,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":9.02},{"place":20,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":9},{"place":21,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":8.98},{"place":22,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":8.98},{"place":23,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":8.97},{"place":24,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":8.95},{"place":25,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":8.91},{"place":26,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":8.89},{"place":27,"model":"telechat2-115b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":8.89},{"place":28,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":8.88},{"place":29,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.88},{"place":30,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.86},{"place":31,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":8.85},{"place":32,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":8.85},{"place":33,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":8.85},{"place":34,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.81},{"place":35,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":8.8},{"place":36,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":8.79},{"place":37,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":8.77},{"place":38,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":8.75},{"place":39,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.75},{"place":40,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":8.75},{"place":41,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":8.74},{"place":42,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":8.73},{"place":43,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":8.73},{"place":44,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":8.72},{"place":45,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":8.71},{"place":46,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":8.71},{"place":47,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":8.69},{"place":48,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":8.66},{"place":49,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":8.62},{"place":50,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":8.62},{"place":51,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.62},{"place":52,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":8.61},{"place":53,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":8.61},{"place":54,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":8.61},{"place":55,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":8.61},{"place":56,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":8.6},{"place":57,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":8.6},{"place":58,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":8.6},{"place":59,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":8.6},{"place":60,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":8.59},{"place":61,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":8.56},{"place":62,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":8.55},{"place":63,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":8.53},{"place":64,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":8.53},{"place":65,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":8.5},{"place":66,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":8.49},{"place":67,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":8.46},{"place":68,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":8.46},{"place":69,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":8.46},{"place":70,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":8.45},{"place":71,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":8.45},{"place":72,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":8.43},{"place":73,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":8.42},{"place":74,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":8.41},{"place":75,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":8.41},{"place":76,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":8.4},{"place":77,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":8.39},{"place":78,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":8.38},{"place":79,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":8.36},{"place":80,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":8.35},{"place":81,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":8.35},{"place":82,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":8.32},{"place":83,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":8.3},{"place":84,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":8.3},{"place":85,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":8.3},{"place":86,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":8.29},{"place":87,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":8.28},{"place":88,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":8.26},{"place":89,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":8.24},{"place":90,"model":"llm-jp-4-33b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":8.24},{"place":91,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":8.23},{"place":92,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":8.23},{"place":93,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":8.23},{"place":94,"model":"telechat2-35b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":8.2},{"place":95,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":8.2},{"place":96,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":8.17},{"place":97,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":8.1},{"place":98,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":8.1},{"place":99,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":8.05},{"place":100,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":8},{"place":101,"model":"llm-jp-4.1-33b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4.1","score":7.98},{"place":102,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":7.96},{"place":103,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.91},{"place":104,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":7.9},{"place":105,"model":"tulu-2-dpo-70b","company":"ai2","family":"Tulu","version":"Tulu 2 DPO 70B","score":7.89},{"place":106,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":7.88},{"place":107,"model":"llm-jp-4-32b-a3b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":7.86},{"place":108,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":7.85},{"place":109,"model":"llm-jp-4.1-32b-a3b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4.1","score":7.85},{"place":110,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":7.81},{"place":111,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":7.79},{"place":112,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.79},{"place":113,"model":"llm-jp-4-8b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":7.79},{"place":114,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":7.7},{"place":115,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.7},{"place":116,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":7.69},{"place":117,"model":"llm-jp-4.1-8b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4.1","score":7.67},{"place":118,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":7.61},{"place":119,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.6},{"place":120,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":7.6},{"place":121,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":7.57},{"place":122,"model":"xwin-lm-70b-v0.1","company":"xwin-lm","family":"Xwin-LM","version":"Xwin-LM V0.1","score":7.53},{"place":123,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":7.5},{"place":124,"model":"yi-1.5-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":7.5},{"place":125,"model":"gemma-1.1-7b-it","company":"google","family":"Gemma","version":"gemma-1.1","score":7.5},{"place":126,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":7.46},{"place":127,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":7.44},{"place":128,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":7.37},{"place":129,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":7.37},{"place":130,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":7.35},{"place":131,"model":"llm-jp-3.1-8x13b-32k-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":7.31},{"place":132,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":7.3},{"place":133,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":7.3},{"place":134,"model":"telechat2-7b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":7.2},{"place":135,"model":"qwen1.5-moe-a2.7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.17},{"place":136,"model":"kanana-2-3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":7.15},{"place":137,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":7.15},{"place":138,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":7.1},{"place":139,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":7.1},{"place":140,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":7.1},{"place":141,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":7.1},{"place":142,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":7.06},{"place":143,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":7.03},{"place":144,"model":"xwin-lm-13b-v0.2","company":"xwin-lm","family":"Xwin-LM","version":"Xwin-LM V0.2","score":7.01},{"place":145,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":7},{"place":146,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":6.98},{"place":147,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":6.96},{"place":148,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":6.96},{"place":149,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":6.93},{"place":150,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.87},{"place":151,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":6.86},{"place":152,"model":"kanana-2-1.3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":6.83},{"place":153,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":6.76},{"place":154,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":6.7},{"place":155,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":6.65},{"place":156,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":6.6},{"place":157,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":6.52},{"place":158,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":6.48},{"place":159,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":6.37},{"place":160,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":6.3},{"place":161,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":6.27},{"place":162,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":6.13},{"place":163,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":6.12},{"place":164,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":6.03},{"place":165,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.75},{"place":166,"model":"telechat2-3b","company":"teleai","family":"TeleChat","version":"TeleChat2","score":5.72},{"place":167,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":5.58},{"place":168,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":5.5},{"place":169,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":5.48},{"place":170,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":5.3},{"place":171,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":5.2},{"place":172,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":4.71},{"place":173,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":4.33},{"place":174,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1.98}]},{"id":"mt-bench-ja","name":"Japanese MT-Bench","topic":"Multi-turn chat (Japanese)","description":"Japanese adaptation of MT-Bench multi-turn conversational benchmark, LLM-as-judge score on a 1-10 scale.","url":"https://github.com/Stability-AI/FastChat/tree/jp-stable/fastchat/llm_judge","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"GPT-5.4","top_percent":8.87,"top_model_id":"gpt-5.4","top_generation":"GPT-5.4","top_model_base":"GPT-5.4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":8.87},{"place":2,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":8.46},{"place":3,"model":"plamo-3.0-prime-beta","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":8.38},{"place":4,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":8.35},{"place":5,"model":"plamo-3.0-prime-thinking","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":8.27},{"place":6,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":8.13},{"place":7,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":8.09},{"place":8,"model":"llm-jp-4-33b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":8},{"place":9,"model":"llm-jp-4-32b-a3b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":7.82},{"place":10,"model":"llm-jp-4.1-33b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4.1","score":7.76},{"place":11,"model":"llm-jp-4.1-32b-a3b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4.1","score":7.69},{"place":12,"model":"llm-jp-4.1-8b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4.1","score":7.58},{"place":13,"model":"llm-jp-4-8b-thinking","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":7.54},{"place":14,"model":"llm-jp-3.1-8x13b-32k-instruct4","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-3.1","score":7.48},{"place":15,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":7.33},{"place":16,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":7.29},{"place":17,"model":"plamo-3.0-prime","company":"pfn","family":"PLaMo","version":"PLaMo 3.0","score":7.18},{"place":18,"model":"plamo-2.2-prime","company":"pfn","family":"PLaMo","version":"PLaMo 2.2","score":6.82}]},{"id":"mtalk-bench","name":"MTalk-Bench","topic":"Spoken multi-turn dialogue","description":"MTalk-Bench: multi-turn speech-to-speech dialogue (semantic, paralinguistic, ambient) evaluation (%).","url":"https://arxiv.org/abs/2508.18240","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"StepAudio 3 Realtime","top_percent":72.8,"top_model_id":"stepaudio-3-realtime","top_generation":"StepAudio 3","top_model_base":"StepAudio 3 Realtime","top_model_family":"Step","top_company":"stepfun","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":72.8},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.6},{"place":3,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":66.8},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":66.7}]},{"id":"mtob-full-book","name":"MTOB (full book)","topic":"Long-form reasoning","description":"Long-context book understanding benchmark (full-book setting).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 4 Maverick","top_percent":50.8,"top_model_id":"llama-4-maverick","top_generation":"Llama 4","top_model_base":"Llama 4 Maverick 17B 128E","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":50.8},{"place":2,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":50.8},{"place":3,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":39.7},{"place":4,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":39.7}]},{"id":"mtob-half-book","name":"MTOB (half book)","topic":"Long-form reasoning","description":"Long-context book understanding benchmark (half-book setting).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 4 Maverick","top_percent":54,"top_model_id":"llama-4-maverick","top_generation":"Llama 4","top_model_base":"Llama 4 Maverick 17B 128E","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":54},{"place":2,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":54},{"place":3,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":42.2},{"place":4,"model":"llama-4-scout-17b-16e","company":"meta","family":"Llama","version":"Llama 4","score":42.2}]},{"id":"mtvqa","name":"MTVQA","topic":"Multilingual text-centric VQA","description":"Multilingual text-centric visual question answering across 9 languages (average accuracy).","url":"https://bytedance.github.io/MTVQA/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2405.11985","metric":"percent","stars":"","top_model":"InternVL2.5-78B","top_percent":31.9,"top_model_id":"internvl2.5-78b","top_generation":"InternVL2.5","top_model_base":"InternVL2.5-78B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":31.9},{"place":2,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":31.7},{"place":3,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":30.9},{"place":4,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":30.9},{"place":5,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":28.5},{"place":6,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":28.4},{"place":7,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":27.8},{"place":8,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":27.6},{"place":9,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":25.7},{"place":10,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":25.6},{"place":11,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":25.6},{"place":12,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":22},{"place":13,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":22},{"place":14,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":21.8},{"place":15,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":21.4},{"place":16,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":20.9},{"place":17,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":20.6},{"place":18,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":20.5},{"place":19,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":20},{"place":20,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":18.1},{"place":21,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":17.7},{"place":22,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":15.3},{"place":23,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":12.6},{"place":24,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":10.9}]},{"id":"muirbench","name":"MUIRBENCH","topic":"Multimodal robustness","description":"Evaluates multimodal understanding robustness and reliability.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":86.1,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":80,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.1},{"place":2,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.1},{"place":3,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":79.77},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":78.7},{"place":5,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":78.6},{"place":6,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":78.6},{"place":7,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":78.58},{"place":8,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":78.5},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.2},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78.2},{"place":11,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.6},{"place":12,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":77.5},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.2},{"place":14,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":77.1},{"place":15,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":75.7},{"place":16,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":75.3},{"place":17,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":75},{"place":18,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":74.7},{"place":19,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":74.7},{"place":20,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":74.7},{"place":21,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.5},{"place":22,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.5},{"place":23,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.5},{"place":24,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.8},{"place":25,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":72.3},{"place":26,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":72},{"place":27,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":71.8},{"place":28,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":71.4},{"place":29,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":71.3},{"place":30,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":70.7},{"place":31,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.5},{"place":32,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":70.5},{"place":33,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":69.38},{"place":34,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":68},{"place":35,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":67},{"place":36,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67},{"place":37,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":66.6},{"place":38,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":65.69},{"place":39,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.4},{"place":40,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":63.8},{"place":41,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.8},{"place":42,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":63.7},{"place":43,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":63.5},{"place":44,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.9},{"place":45,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":62.7},{"place":46,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":62.5},{"place":47,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":62.3},{"place":48,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62},{"place":49,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":61.9},{"place":50,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":61.8},{"place":51,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":61.6},{"place":52,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":61.1},{"place":53,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":60.5},{"place":54,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":60.2},{"place":55,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.6},{"place":56,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":58.4},{"place":57,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":58.4},{"place":58,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":58.3},{"place":59,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":57.5},{"place":60,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":55.8},{"place":61,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":54.8},{"place":62,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":54.4},{"place":63,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.04},{"place":64,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":53.5},{"place":65,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":53.4},{"place":66,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":53.4},{"place":67,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":53.3},{"place":68,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":53.1},{"place":69,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.8},{"place":70,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":51.2},{"place":71,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":51.2},{"place":72,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":51.1},{"place":73,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":50.6},{"place":74,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":50.3},{"place":75,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49},{"place":76,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.9},{"place":77,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":48.7},{"place":78,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.2},{"place":79,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.4},{"place":80,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.6},{"place":81,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":45.7},{"place":82,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.3},{"place":83,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":45.2},{"place":84,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":45},{"place":85,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.8},{"place":86,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.7},{"place":87,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":40.6},{"place":88,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":40.5},{"place":89,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.1},{"place":90,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":38.5},{"place":91,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":34.9},{"place":92,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.9},{"place":93,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.5},{"place":94,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":29.9},{"place":95,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":29.5},{"place":96,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":29.4},{"place":97,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":29.3},{"place":98,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":25.7},{"place":99,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":25.5},{"place":100,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":23.5}]},{"id":"multi-if","name":"Multi-IF","topic":"Instruction following (multi-task)","description":"Composite instruction-following evaluation across multiple tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 31B (IT)","top_percent":89.7,"top_model_id":"gemma-4-31b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 31B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":129,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":89.7},{"place":2,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":89.3},{"place":3,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":88.44},{"place":4,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":87.8},{"place":5,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":87.7},{"place":6,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":87.28},{"place":7,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.6},{"place":8,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":86.2},{"place":9,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":85.56},{"place":10,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":85.37},{"place":11,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":84.8},{"place":12,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":84.6},{"place":13,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":84.6},{"place":14,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":84.38},{"place":15,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.32},{"place":16,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":83.7},{"place":17,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":83.7},{"place":18,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":83.34},{"place":19,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":83.15},{"place":20,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.03},{"place":21,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":82.95},{"place":22,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":82.9},{"place":23,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.49},{"place":24,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":82.34},{"place":25,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.3},{"place":26,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.19},{"place":27,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.06},{"place":28,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":81.9},{"place":29,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.53},{"place":30,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.15},{"place":31,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.03},{"place":32,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.92},{"place":33,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":80.07},{"place":34,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80},{"place":35,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":79.93},{"place":36,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.84},{"place":37,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":79.5},{"place":38,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":79.04},{"place":39,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":78.2},{"place":40,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.93},{"place":41,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":77.88},{"place":42,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.8},{"place":43,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.58},{"place":44,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.4},{"place":45,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.35},{"place":46,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":77.18},{"place":47,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":76.91},{"place":48,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":76.8},{"place":49,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":76.64},{"place":50,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":76.6},{"place":51,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":76.4},{"place":52,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.1},{"place":53,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":75.97},{"place":54,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":75.9},{"place":55,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":75.81},{"place":56,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":75.54},{"place":57,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":74.8},{"place":58,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.4},{"place":59,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":73.76},{"place":60,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.6},{"place":61,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73.2},{"place":62,"model":"lfm2-2.6b-exp","company":"liquidai","family":"LFM","version":"LFM2","score":73.05},{"place":63,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":73},{"place":64,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73},{"place":65,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":72.9},{"place":66,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.9},{"place":67,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.9},{"place":68,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":71.8},{"place":69,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":71.4},{"place":70,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":71.17},{"place":71,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":71.13},{"place":72,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":70.8},{"place":73,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":70.5},{"place":74,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":70.4},{"place":75,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":70.3},{"place":76,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":70.2},{"place":77,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.2},{"place":78,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":70},{"place":79,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":69.93},{"place":80,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":69.81},{"place":81,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.7},{"place":82,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.44},{"place":83,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.4},{"place":84,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":69.33},{"place":85,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":68.7},{"place":86,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":68.52},{"place":87,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":68.51},{"place":88,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":67.9},{"place":89,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":67.8},{"place":90,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":67.7},{"place":91,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.43},{"place":92,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":66.9},{"place":93,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":66.8},{"place":94,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.7},{"place":95,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.61},{"place":96,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.5},{"place":97,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.1},{"place":98,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":65.9},{"place":99,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":65.6},{"place":100,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":65},{"place":101,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64.8},{"place":102,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":64.7},{"place":103,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":64},{"place":104,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.55},{"place":105,"model":"lfm2.5-1.2b-instruct","company":"liquidai","family":"LFM","version":"LFM2.5","score":60.98},{"place":106,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":60.58},{"place":107,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":60.46},{"place":108,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":60.33},{"place":109,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":60.29},{"place":110,"model":"lfm2-2.6b","company":"liquidai","family":"LFM","version":"LFM2","score":60.26},{"place":111,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":59.6},{"place":112,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":59.4},{"place":113,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":59},{"place":114,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":58.86},{"place":115,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":58.54},{"place":116,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":58.43},{"place":117,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":58.19},{"place":118,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":57.96},{"place":119,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.1},{"place":120,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":57.03},{"place":121,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.48},{"place":122,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":56.4},{"place":123,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.67},{"place":124,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":55.61},{"place":125,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.5},{"place":126,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":52.99},{"place":127,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.3},{"place":128,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":50.93},{"place":129,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":50.91},{"place":130,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":48.8},{"place":131,"model":"o1","company":"openai","family":"o1","version":"o1","score":48.8},{"place":132,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":48.4},{"place":133,"model":"granite-4.0-h-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":47.56},{"place":134,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":47},{"place":135,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":46.5},{"place":136,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.4},{"place":137,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.9},{"place":138,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":44.92},{"place":139,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":44.31},{"place":140,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":44.3},{"place":141,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":44.25},{"place":142,"model":"granite-4.0-1b","company":"IBM","family":"Granite","version":"Granite 4.0","score":43.65},{"place":143,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":43.54},{"place":144,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.68},{"place":145,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.3},{"place":146,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":37.7},{"place":147,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":37.3},{"place":148,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.56},{"place":149,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":34.63},{"place":150,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":32.92},{"place":151,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.31},{"place":152,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":30.4},{"place":153,"model":"llama-3.2-1b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":30.16},{"place":154,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":28.7},{"place":155,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.44},{"place":156,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":26.21},{"place":157,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":24.21},{"place":158,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":23.6},{"place":159,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":16.9},{"place":160,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":16.3},{"place":161,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":6.82}]},{"id":"multi-ifeval","name":"Multi-IFEval","topic":"Instruction following (multi-task)","description":"Multi-task variant of instruction-following evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 3.3 70B","top_percent":88.7,"top_model_id":"llama-3.3-70b","top_generation":"Llama 3.3","top_model_base":"Llama 3.3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":88.7},{"place":2,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":80.6},{"place":3,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":77.8},{"place":4,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.5},{"place":5,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":76.4},{"place":6,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":75.8},{"place":7,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.4},{"place":8,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":73},{"place":9,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.7},{"place":10,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":67.9},{"place":11,"model":"exaone-deep-2.4b","company":"lg","family":"EXAONE","version":"EXAONE Deep","score":54.5},{"place":12,"model":"exaone-4.0-1.2b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":53.9},{"place":13,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.5},{"place":14,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":47.5},{"place":15,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.5}]},{"id":"multi-swe-bench","name":"Multi-SWE-Bench","topic":"Code repair (multi-repo)","description":"Multi-repository SWE-Bench variant.","url":"https://multi-swe-bench.github.io","leaderboard":"","github":"","paper":"","metric":"percent","stars":"246","top_model":"MiniMax M2.7","top_percent":52.7,"top_model_id":"minimax-m2.7","top_generation":"MiniMax M2.7","top_model_base":"MiniMax M2.7","top_model_family":"MiniMax","top_company":"minimax","top_open_source":1,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":52.7},{"place":2,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":51.3},{"place":3,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":51},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":50.3},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50},{"place":6,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":49.4},{"place":7,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":49},{"place":8,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":47.2},{"place":9,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.3},{"place":10,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.3},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":42.7},{"place":12,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":42},{"place":13,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":41.9},{"place":14,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":41.7},{"place":15,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":39.3},{"place":16,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":36.2},{"place":17,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":35.7},{"place":18,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":33.5},{"place":19,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":33.5},{"place":20,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":33.5},{"place":21,"model":"qwen3-coder-480b-a35b","company":"qwen","family":"Qwen","version":"Qwen3","score":32.7},{"place":22,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":31.7},{"place":23,"model":"kimi-k2-instruct-0711","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":31.3},{"place":24,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":30.6},{"place":25,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":30.6},{"place":26,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":30},{"place":27,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":29.2},{"place":28,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":29},{"place":29,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":20.7},{"place":30,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":18.3},{"place":31,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":14},{"place":32,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":11.7},{"place":33,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":9},{"place":34,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":8}]},{"id":"multichallenge","name":"MultiChallenge","topic":"Instruction following","description":"Multi-domain instruction-following benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nova 2 Pro","top_percent":77.7,"top_model_id":"nova-2-pro","top_generation":"Nova 2","top_model_base":"Nova 2 Pro","top_model_family":"Nova","top_company":"amazon","top_open_source":0,"lower_is_better":false,"bench_models":136,"total_models":3854,"placements":[{"place":1,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":77.7},{"place":2,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":76.6},{"place":3,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":75.5},{"place":4,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":73.6},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":72.2},{"place":6,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":72.12},{"place":7,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":71.1},{"place":8,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":69.9},{"place":9,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":69.78},{"place":10,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":69.6},{"place":11,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":69.6},{"place":12,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":69.3},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68.7},{"place":14,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":68.4},{"place":15,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":68.3},{"place":16,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":67.8},{"place":17,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.6},{"place":18,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":67.4},{"place":19,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":66.7},{"place":20,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":66.4},{"place":21,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":66.32},{"place":22,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":65.98},{"place":23,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":64.98},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":64.2},{"place":25,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.1},{"place":26,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.9},{"place":27,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":63.89},{"place":28,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63.8},{"place":29,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":63.6},{"place":30,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":63.5},{"place":31,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":63.4},{"place":32,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":63.3},{"place":33,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.2},{"place":34,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":63.1},{"place":35,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.1},{"place":36,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":63},{"place":37,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":62.9},{"place":38,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":62.7},{"place":39,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":62.6},{"place":40,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.6},{"place":41,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":62.5},{"place":42,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.5},{"place":43,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.3},{"place":44,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62},{"place":45,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.5},{"place":46,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":61.1},{"place":47,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":61},{"place":48,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.8},{"place":49,"model":"o3","company":"openai","family":"o3","version":"o3","score":60.4},{"place":50,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":60.35},{"place":51,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60.3},{"place":52,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60},{"place":53,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":59.5},{"place":54,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59},{"place":55,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":59},{"place":56,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":59},{"place":57,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":59},{"place":58,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":58.4},{"place":59,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":58.3},{"place":60,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":58.2},{"place":61,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":57.9},{"place":62,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":57.9},{"place":63,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":57.9},{"place":64,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.3},{"place":65,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.2},{"place":66,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.1},{"place":67,"model":"o3","company":"openai","family":"o3","version":"o3","score":56.5},{"place":68,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":55.98},{"place":69,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":55.6},{"place":70,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.4},{"place":71,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":54.95},{"place":72,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":54.9},{"place":73,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.5},{"place":74,"model":"deepseek-v3.1-terminus-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":54.4},{"place":75,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.2},{"place":76,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":54.1},{"place":77,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":53.11},{"place":78,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":53.1},{"place":79,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":52.48},{"place":80,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.23},{"place":81,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":52.21},{"place":82,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":52.2},{"place":83,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":52.2},{"place":84,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":52.01},{"place":85,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":51.9},{"place":86,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":51.8},{"place":87,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.76},{"place":88,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":51.5},{"place":89,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":51.49},{"place":90,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":51.3},{"place":91,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":51.28},{"place":92,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.2},{"place":93,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":49.8},{"place":94,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49.4},{"place":95,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49.4},{"place":96,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.08},{"place":97,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":49},{"place":98,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49},{"place":99,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":47.3},{"place":100,"model":"pacore-8b","company":"stepfun","family":"Step","version":"PaCoRe","score":47},{"place":101,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":46.9},{"place":102,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":46.8},{"place":103,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":46.5},{"place":104,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":46.15},{"place":105,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":45.8},{"place":106,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":45.8},{"place":107,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":45.3},{"place":108,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":45},{"place":109,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":44.7},{"place":110,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":44.7},{"place":111,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":44.5},{"place":112,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":43.59},{"place":113,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":43},{"place":114,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":42.5},{"place":115,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.49},{"place":116,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":42.43},{"place":117,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.08},{"place":118,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":41.8},{"place":119,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":41.76},{"place":120,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":41.7},{"place":121,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":41.39},{"place":122,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":41.2},{"place":123,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":41.14},{"place":124,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":40.7},{"place":125,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":40.5},{"place":126,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":40.3},{"place":127,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":40.1},{"place":128,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":40},{"place":129,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":39.71},{"place":130,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":39.5},{"place":131,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":39.36},{"place":132,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.2},{"place":133,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":39},{"place":134,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":38.72},{"place":135,"model":"lg-exaone-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":38.5},{"place":136,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":38.46},{"place":137,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":37.73},{"place":138,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":37.7},{"place":139,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.97},{"place":140,"model":"apriel-nemotron-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel Nemotron","score":36.6},{"place":141,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":36.4},{"place":142,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.4},{"place":143,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.3},{"place":144,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.8},{"place":145,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":35.3},{"place":146,"model":"kanana-2-30b-a3b-instruct-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":35.16},{"place":147,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":35.16},{"place":148,"model":"kanana-2-30b-a3b-instruct","company":"kakao","family":"Kanana","version":"Kanana 2","score":34.8},{"place":149,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":34.53},{"place":150,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":34.43},{"place":151,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":34},{"place":152,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.7},{"place":153,"model":"rlvr-8b-0926","company":"stepfun","family":"Step","version":"PaCoRe","score":33.3},{"place":154,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":31.4},{"place":155,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":30.8},{"place":156,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.84},{"place":157,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":27.2},{"place":158,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":26.7},{"place":159,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":23.97},{"place":160,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":23.28},{"place":161,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":22},{"place":162,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":19.48},{"place":163,"model":"kanana-1.5-32.5b-instruct","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":19.05},{"place":164,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":18.97},{"place":165,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.9},{"place":166,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":18.7},{"place":167,"model":"llama-3.1-nemotron-nano-8b-v1","company":"nvidia","family":"Llama","version":"Llama 3.1","score":16.1}]},{"id":"multiimg-qa-avg","name":"Multi-Image QA Average","topic":"Multi-image QA (aggregate)","description":"Aggregate score over multi-image visual question answering tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":81.9,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.9},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.4},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":72.1},{"place":4,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.3},{"place":5,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":68.2},{"place":6,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":67.4},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.5},{"place":8,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":57.8},{"place":9,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.6},{"place":10,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":56.4},{"place":11,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.3},{"place":12,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":54.9},{"place":13,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":53.5},{"place":14,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":53.5},{"place":15,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":52.1},{"place":16,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":52},{"place":17,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":47.3},{"place":18,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":40.6},{"place":19,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":35.7}]},{"id":"multilingual-mmbench","name":"Multilingual MMBench","topic":"Multilingual vision benchmark","description":"Multilingual MMBench average score across languages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5-VL-3B","top_percent":79.5,"top_model_id":"lfm2.5-vl-3b","top_generation":"LFM2.5-VL","top_model_base":"LFM2.5-VL 3B","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":79.5},{"place":2,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77},{"place":3,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.6},{"place":4,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":76.3},{"place":5,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.2},{"place":6,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":70.9},{"place":7,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.9},{"place":8,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":65.9},{"place":9,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62.8},{"place":10,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":60.57},{"place":11,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":58.32},{"place":12,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":50.89}]},{"id":"multilingual-mmlu","name":"Multilingual MMLU","topic":"Multi-domain knowledge (multilingual)","description":"Multilingual variant of MMLU across many languages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-4.1","top_percent":87.3,"top_model_id":"gpt-4.1","top_generation":"GPT-4.1","top_model_base":"GPT-4.1","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":34,"total_models":3854,"placements":[{"place":1,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":87.3},{"place":2,"model":"cogito-671b-v2.1","company":"deepcogito","family":"Cogito","version":"Cogito 671B v2.1","score":86.24},{"place":3,"model":"llama-4-behemoth","company":"meta","family":"Llama","version":"Llama 4","score":85.8},{"place":4,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":85.1},{"place":5,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":83.2},{"place":6,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":80.1},{"place":7,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":79.97},{"place":8,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":79.3},{"place":9,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":78.37},{"place":10,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":78},{"place":11,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":78},{"place":12,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":77.84},{"place":13,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77.16},{"place":14,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":76.49},{"place":15,"model":"qwen3-14b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":75.4},{"place":16,"model":"ministral-3-14b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":74.2},{"place":17,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":73.44},{"place":18,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.12},{"place":19,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":71},{"place":20,"model":"ministral-3-8b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":70.6},{"place":21,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":70},{"place":22,"model":"gemma-3-12b-base","company":"google","family":"Gemma","version":"Gemma 3","score":69},{"place":23,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":68.4},{"place":24,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":68},{"place":25,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":67.7},{"place":26,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.98},{"place":27,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":65.5},{"place":28,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":65.2},{"place":29,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":65},{"place":30,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":60.47},{"place":31,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":60},{"place":32,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":59.65},{"place":33,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":55.18},{"place":34,"model":"gemma-3-4b-base","company":"google","family":"Gemma","version":"Gemma 3","score":51.6},{"place":35,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":50},{"place":36,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":46.72}]},{"id":"multiloko","name":"MultiLoKo","topic":"Multilingual knowledge","description":"Multilingual local-knowledge QA benchmark covering 31 languages with locally sourced questions.","url":"https://github.com/facebookresearch/multiloko","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Pro Base","top_percent":51.1,"top_model_id":"deepseek-v4-pro-base","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Pro Base","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.1},{"place":2,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.9},{"place":3,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":45.5},{"place":4,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":42.6},{"place":5,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":42.2},{"place":6,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":38.7}]},{"id":"multimodal-troubleshooting-virology","name":"Multimodal Troubleshooting Virology","topic":"Biosecurity","description":"Virology troubleshooting in laboratory scenarios, sometimes with images; models must select every correct answer and no incorrect ones (pass@1).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":63.11,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":63.11},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":55.5},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":55.34},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":52.54},{"place":5,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":51.68},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":50.6},{"place":7,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":49.1},{"place":8,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":48.13}]},{"id":"multipl-e","name":"MultiPL-E","topic":"Code generation (multilingual)","description":"Multilingual code generation and execution benchmark across many programming languages.","url":"https://github.com/nuprl/MultiPL-E","leaderboard":"","github":"","paper":"","metric":"percent","stars":"269","top_model":"Claude Opus 4","top_percent":89.6,"top_model_id":"claude-opus-4","top_generation":"Claude 4","top_model_base":"Claude Opus 4","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":130,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":89.6},{"place":2,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":88.6},{"place":3,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":87.9},{"place":4,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":87.8},{"place":5,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":86.7},{"place":6,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85.7},{"place":7,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.6},{"place":8,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.5},{"place":9,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":83.8},{"place":10,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.8},{"place":11,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":83.1},{"place":12,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":82.7},{"place":13,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":81.5},{"place":14,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":81.4},{"place":15,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":81.4},{"place":16,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.3},{"place":17,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":81},{"place":18,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.6},{"place":19,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":80},{"place":20,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79.9},{"place":21,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79.3},{"place":22,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":78.2},{"place":23,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":77.91},{"place":24,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":77.68},{"place":25,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":77},{"place":26,"model":"qwen2.5-plus-1127","company":"qwen","family":"Qwen","version":"Qwen2.5","score":77},{"place":27,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":76.9},{"place":28,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":76.9},{"place":29,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":76.66},{"place":30,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.4},{"place":31,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.1},{"place":32,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":75.1},{"place":33,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":75},{"place":34,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":74.87},{"place":35,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.7},{"place":36,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73.54},{"place":37,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":73.5},{"place":38,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":73.5},{"place":39,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":73.34},{"place":40,"model":"qwen-turbo-0919","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73},{"place":41,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.8},{"place":42,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":71.5},{"place":43,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.48},{"place":44,"model":"stable-diffcoder-8b-base","company":"bytedance","family":"Seed","version":"Stable-DiffCoder","score":71.2},{"place":45,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":70.89},{"place":46,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":70.79},{"place":47,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.67},{"place":48,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.4},{"place":49,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":69.2},{"place":50,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":68.2},{"place":51,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":68.07},{"place":52,"model":"seed-coder-8b-base","company":"bytedance","family":"Seed","version":"Seed Coder","score":67.6},{"place":53,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":67.46},{"place":54,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":67.4},{"place":55,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":67.17},{"place":56,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":67.1},{"place":57,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.1},{"place":58,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":67.09},{"place":59,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":66.4},{"place":60,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":65.76},{"place":61,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":65.26},{"place":62,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":64.6},{"place":63,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":64.38},{"place":64,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":64.34},{"place":65,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":64.16},{"place":66,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":64.16},{"place":67,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":63.4},{"place":68,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":63.21},{"place":69,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":62.43},{"place":70,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":62.31},{"place":71,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":61.7},{"place":72,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":61.1},{"place":73,"model":"opencoder-8b-base","company":"map","family":"OpenCoder","version":"OpenCoder","score":61},{"place":74,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.5},{"place":75,"model":"hunyuan-7b-pretrain","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":60.41},{"place":76,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":60.26},{"place":77,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.2},{"place":78,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":59.6},{"place":79,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.4},{"place":80,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":59.1},{"place":81,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":58.8},{"place":82,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":57.37},{"place":83,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":57.28},{"place":84,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":55.4},{"place":85,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":53.57},{"place":86,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":53.5},{"place":87,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":53.4},{"place":88,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.89},{"place":89,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":52.7},{"place":90,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":52.54},{"place":91,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51},{"place":92,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":50.7},{"place":93,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":50.7},{"place":94,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.4},{"place":95,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.3},{"place":96,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":49.8},{"place":97,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":49.21},{"place":98,"model":"minicpm3-4b","company":"openbmb","family":"MiniCPM","version":"MiniCPM3","score":49.1},{"place":99,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":48.91},{"place":100,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":48.5},{"place":101,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":48.1},{"place":102,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":48},{"place":103,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":47.26},{"place":104,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":47.2},{"place":105,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":46.7},{"place":106,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":46.3},{"place":107,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":46.3},{"place":108,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":45.77},{"place":109,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.47},{"place":110,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":44.7},{"place":111,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":44.4},{"place":112,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":41.8},{"place":113,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":41.2},{"place":114,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":41},{"place":115,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":39.5},{"place":116,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":39},{"place":117,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":38.5},{"place":118,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":38.5},{"place":119,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":36.1},{"place":120,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":34.9},{"place":121,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":33.1},{"place":122,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":30.5},{"place":123,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":29.7},{"place":124,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":29.4},{"place":125,"model":"qwen2.5-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28.5},{"place":126,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":28.1},{"place":127,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":27.9},{"place":128,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":27.2},{"place":129,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":22.6},{"place":130,"model":"qwen2-0.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":20.8},{"place":131,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":18.9},{"place":132,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":17.6},{"place":133,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":16.3}]},{"id":"multipl-e-humaneval","name":"MultiPL-E HumanEval","topic":"Code generation (multilingual)","description":"MultiPL-E variant of HumanEval tasks.","url":"https://github.com/nuprl/MultiPL-E","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 3.1 405B","top_percent":75.2,"top_model_id":"llama-3.1-405b","top_generation":"Llama 3.1","top_model_base":"Llama 3.1 405B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":75.2},{"place":2,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":67.7},{"place":3,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":65.5},{"place":4,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":63},{"place":5,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":60.5},{"place":6,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":59.5},{"place":7,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":52.3},{"place":8,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":50.8},{"place":9,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":45.9},{"place":10,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":45.9},{"place":11,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":45.7},{"place":12,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":45.7},{"place":13,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":40.3},{"place":14,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":34.5},{"place":15,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":29.4},{"place":16,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":28.7},{"place":17,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":27.9},{"place":18,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":22.3},{"place":19,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":15.6},{"place":20,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":15.5},{"place":21,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":14.5},{"place":22,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":4.2}]},{"id":"multipl-e-mbpp","name":"MultiPL-E MBPP","topic":"Code generation (multilingual)","description":"MultiPL-E variant of MBPP tasks.","url":"https://github.com/nuprl/MultiPL-E","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 3.1 405B","top_percent":65.7,"top_model_id":"llama-3.1-405b","top_generation":"Llama 3.1","top_model_base":"Llama 3.1 405B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":65.7},{"place":2,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":62},{"place":3,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":58.8},{"place":4,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":58},{"place":5,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":56.7},{"place":6,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":52.5},{"place":7,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":52.5},{"place":8,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":52.4},{"place":9,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":50.6},{"place":10,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":50.6},{"place":11,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":48.4},{"place":12,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":47.9},{"place":13,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":45.4},{"place":14,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":42.5},{"place":15,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":39.5},{"place":16,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":38.2},{"place":17,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":38.2},{"place":18,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":32.3},{"place":19,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":29.2},{"place":20,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":28.3},{"place":21,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":27.6},{"place":22,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":12.2}]},{"id":"musr","name":"MuSR","topic":"Reasoning","description":"Multistep Soft Reasoning.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2310.16049","metric":"percent","stars":"","top_model":"Clef-Flash","top_percent":86,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":94,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":86},{"place":2,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":83.8},{"place":3,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":83.5},{"place":4,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":82.72},{"place":5,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":82.72},{"place":6,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":80.1},{"place":7,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":79.84},{"place":8,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":79.63},{"place":9,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":79.15},{"place":10,"model":"qwen3.8-27b-ud-q4-k-xl","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.01},{"place":11,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":72.6},{"place":12,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":71.89},{"place":13,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":71.48},{"place":14,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":71.36},{"place":15,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":70.7},{"place":16,"model":"ternary-bonsai-2-27b","company":"prismml","family":"Bonsai","version":"Bonsai 2","score":70.63},{"place":17,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":70.43},{"place":18,"model":"hermes-4.3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":70.4},{"place":19,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.02},{"place":20,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":69.9},{"place":21,"model":"hermes-4.3-36b-pyche","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":69.7},{"place":22,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":69.3},{"place":23,"model":"underdog-saluki-27b-1.0","company":"conwayresearch","family":"Underdog","version":"Underdog 1.0","score":67.5},{"place":24,"model":"qwen3.8-27b-iq2-xxs","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.99},{"place":25,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.8},{"place":26,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":66.1},{"place":27,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":66.1},{"place":28,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":65.9},{"place":29,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":65.7},{"place":30,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":65.3},{"place":31,"model":"hermes-4.3-36b","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":64.7},{"place":32,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":64.47},{"place":33,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.4},{"place":34,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":63.49},{"place":35,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":62.6},{"place":36,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":62.4},{"place":37,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":61.2},{"place":38,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61},{"place":39,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":60.8},{"place":40,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.5},{"place":41,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":60.2},{"place":42,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":60.2},{"place":43,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":59.8},{"place":44,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.7},{"place":45,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":59.6},{"place":46,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":58.8},{"place":47,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.5},{"place":48,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":58.3},{"place":49,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":58},{"place":50,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":57.9},{"place":51,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":57.9},{"place":52,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":57.7},{"place":53,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":57.4},{"place":54,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":56.8},{"place":55,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":56.8},{"place":56,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.6},{"place":57,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":56.6},{"place":58,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":56.4},{"place":59,"model":"magistral-small-2509","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":56.3},{"place":60,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":56.1},{"place":61,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":54.4},{"place":62,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":54.1},{"place":63,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":53.7},{"place":64,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":52},{"place":65,"model":"midm-2.0-base-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":51.9},{"place":66,"model":"midm-2.0-mini-instruct","company":"kt","family":"Mi:dm","version":"Mi:dm 2.0","score":51.7},{"place":67,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":51.3},{"place":68,"model":"exaone-3.5-7.8b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":51.2},{"place":69,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":51.1},{"place":70,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":50.3},{"place":71,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":50},{"place":72,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":49.9},{"place":73,"model":"exaone-3.5-2.4b-instruct","company":"lg","family":"EXAONE","version":"EXAONE 3.5","score":49.7},{"place":74,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":47.22},{"place":75,"model":"phi-3.5-moe-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5 MoE","score":46.79},{"place":76,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.6},{"place":77,"model":"solar-pro-preview","company":"upstage","family":"Solar","version":"Solar Pro","score":45.85},{"place":78,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":45.67},{"place":79,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":45.2},{"place":80,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":44.8},{"place":81,"model":"deepseek-r1-distill-qwen-1.5b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":43.8},{"place":82,"model":"command-r7b","company":"cohere","family":"Command","version":"Command","score":43.3},{"place":83,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":43.2},{"place":84,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":42.28},{"place":85,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":41.14},{"place":86,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":39.95},{"place":87,"model":"afm-4.5b","company":"arcee","family":"AFM","version":"AFM","score":38.76},{"place":88,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":38},{"place":89,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":36.77},{"place":90,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":29.68},{"place":91,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.65},{"place":92,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":9.71},{"place":93,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":7.73},{"place":94,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":5.27},{"place":95,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":4.6},{"place":96,"model":"falcon-e-1b-base","company":"tii","family":"Falcon","version":"Falcon E","score":3.65},{"place":97,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.38},{"place":98,"model":"llama-spark-8b","company":"arcee","family":"Llama Spark","version":"Llama Spark 8B","score":2.62},{"place":99,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":2.08}]},{"id":"mvbench","name":"MVBench","topic":"Video QA","description":"Multi-view or multi-video QA benchmark (MVBench).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.7 Flash","top_percent":82.2,"top_model_id":"gemini-3.7-flash","top_generation":"Gemini 3.7","top_model_base":"Gemini 3.7 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":128,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":82.2},{"place":2,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":81.3},{"place":3,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":79},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":78.1},{"place":5,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":77.8},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.6},{"place":7,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":77.5},{"place":8,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":77.1},{"place":9,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.6},{"place":10,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":76.4},{"place":11,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":75.9},{"place":12,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75.5},{"place":13,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.2},{"place":14,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":75.2},{"place":15,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":75.2},{"place":16,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":75.2},{"place":17,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":75.1},{"place":18,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":75},{"place":19,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":74.9},{"place":20,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.8},{"place":21,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":74.8},{"place":22,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":74.8},{"place":23,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":74.7},{"place":24,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.6},{"place":25,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.6},{"place":26,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.4},{"place":27,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":74.4},{"place":28,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.2},{"place":29,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.1},{"place":30,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":74.1},{"place":31,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":74},{"place":32,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":74},{"place":33,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":73.7},{"place":34,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":73.6},{"place":35,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":73.6},{"place":36,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":73.5},{"place":37,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":73},{"place":38,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.8},{"place":39,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.3},{"place":40,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":72.1},{"place":41,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72},{"place":42,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":72},{"place":43,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":72},{"place":44,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":71.7},{"place":45,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":71.6},{"place":46,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":71.6},{"place":47,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":71.5},{"place":48,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.2},{"place":49,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":71.2},{"place":50,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":71.2},{"place":51,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":71.2},{"place":52,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":71},{"place":53,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":70.9},{"place":54,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":70.8},{"place":55,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":70.8},{"place":56,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.6},{"place":57,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":70.4},{"place":58,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.4},{"place":59,"model":"oryx-1.5-32b","company":"tsinghua","family":"Oryx","version":"Oryx-1.5","score":70.1},{"place":60,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":69.7},{"place":61,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":69.6},{"place":62,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":69.5},{"place":63,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.4},{"place":64,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.3},{"place":65,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":69.1},{"place":66,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.9},{"place":67,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":68.8},{"place":68,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.7},{"place":69,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":68.4},{"place":70,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":68.4},{"place":71,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":67.7},{"place":72,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.5},{"place":73,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":67.3},{"place":74,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.2},{"place":75,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":67.1},{"place":76,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":67.1},{"place":77,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":67},{"place":78,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":67},{"place":79,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":67},{"place":80,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":67},{"place":81,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":66.73},{"place":82,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.7},{"place":83,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":66.5},{"place":84,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":65.9},{"place":85,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":65.8},{"place":86,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":65.5},{"place":87,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":65.1},{"place":88,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":65},{"place":89,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.9},{"place":90,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.5},{"place":91,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":64.31},{"place":92,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":64.3},{"place":93,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":64},{"place":94,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":63.2},{"place":95,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":63.2},{"place":96,"model":"videochat2-hd-mistral","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":62.3},{"place":97,"model":"cogvlm2-video-llama3-chat","company":"zai","family":"CogVLM2","version":"CogVLM2","score":62.3},{"place":98,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.1},{"place":99,"model":"videollama2-72b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":62},{"place":100,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.7},{"place":101,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":61.18},{"place":102,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":60.9},{"place":103,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":60.5},{"place":104,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":60.2},{"place":105,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":59.7},{"place":106,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":59.4},{"place":107,"model":"videogpt-plus","company":"mbzuai","family":"VideoGPT","version":"VideoGPT+","score":58.7},{"place":108,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":58.6},{"place":109,"model":"pllava-34b","company":"bytedance","family":"PLLaVA","version":"PLLaVA","score":58.1},{"place":110,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":57.9},{"place":111,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":57.5},{"place":112,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":57.1},{"place":113,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":56.9},{"place":114,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":56.7},{"place":115,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.8},{"place":116,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.1},{"place":117,"model":"st-llm-7b","company":"tencent","family":"ST-LLM","version":"ST-LLM","score":54.9},{"place":118,"model":"videollama2-7b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":54.6},{"place":119,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":53.4},{"place":120,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":52.9},{"place":121,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":52.6},{"place":122,"model":"sharegpt4video-8b","company":"shanghai-ai-lab","family":"ShareGPT4Video","version":"ShareGPT4Video","score":51.2},{"place":123,"model":"videochat2-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":51.1},{"place":124,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":50.6},{"place":125,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":49.4},{"place":126,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":49.2},{"place":127,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":47.8},{"place":128,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":46.8},{"place":129,"model":"llava-next-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":46.5},{"place":130,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":46.3},{"place":131,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":46.27},{"place":132,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":44.9},{"place":133,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":43.7},{"place":134,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":43.5},{"place":135,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":43.5},{"place":136,"model":"video-llava-7b","company":"pku","family":"Video-LLaVA","version":"Video-LLaVA","score":41},{"place":137,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":39.73},{"place":138,"model":"anygpt","company":"fudan","family":"AnyGPT","version":"AnyGPT","score":33.2},{"place":139,"model":"smolvlm2-0.256b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":32.7}]},{"id":"nanogpt","name":"NanoGPT","topic":"AI research automation","description":"OpenAI internal eval (GPT-5.6 announcement): improving a NanoGPT training recipe (speed-up score).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Terra","top_percent":14.5,"top_model_id":"gpt-5.6-terra","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":14.5},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":9.69},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":2.65},{"place":4,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":1.66}]},{"id":"nanonets-kie","name":"Nanonets KIE","topic":"Key information extraction","description":"Nanonets key information extraction benchmark (F1).","url":"https://github.com/NanoNets/docext","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qianfan-OCR","top_percent":86.5,"top_model_id":"qianfan-ocr","top_generation":"Qianfan-OCR","top_model_base":"Qianfan-OCR","top_model_family":"Qianfan","top_company":"baidu","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":86.5},{"place":2,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.8},{"place":3,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.3},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.1}]},{"id":"natural2code","name":"Natural2Code","topic":"Code generation","description":"Natural language to code benchmark for instruction-following synthesis.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.0 Flash","top_percent":92.9,"top_model_id":"gemini-2.0-flash","top_generation":"Gemini 2.0","top_model_base":"Gemini 2.0 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":92.9},{"place":2,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":85.4},{"place":3,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":84.5},{"place":4,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":80.7},{"place":5,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":79.8},{"place":6,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":75.5},{"place":7,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":70.3},{"place":8,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":56}]},{"id":"naturalcodebench","name":"NaturalCodeBench","topic":"Code generation","description":"NaturalCodeBench (NCB): real-world coding prompts in Python and Java, English and Chinese.","url":"https://github.com/THUDM/NaturalCodeBench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2405.04520","metric":"percent","stars":"","top_model":"GPT-4 Turbo (2024-04-09)","top_percent":53.8,"top_model_id":"gpt-4-turbo-2024-04-09","top_generation":"GPT-4","top_model_base":"GPT-4 Turbo","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":53.8},{"place":2,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":52.8},{"place":3,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":51.5},{"place":4,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":48.3},{"place":5,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":47.1},{"place":6,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":46},{"place":7,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":42.3},{"place":8,"model":"glm-4-air-0605","company":"zai","family":"GLM","version":"GLM 4","score":40.8},{"place":9,"model":"codegeex4-all-9b","company":"zai","family":"Codegeex4","version":"Codegeex4","score":40.4},{"place":10,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":39.3},{"place":11,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":37},{"place":12,"model":"claude-2","company":"anthropic","family":"claude-2","version":"claude-2 (Mar 2024)","score":34.4},{"place":13,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":32.2},{"place":14,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":24.7},{"place":15,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":11.3}]},{"id":"naturalquestions","name":"NaturalQuestions","topic":"Open-domain QA","description":"Google NQ; real user questions with long/short answers.","url":"https://ai.google.com/research/NaturalQuestions","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Mixtral-8x22B-Instruct-v0.1","top_percent":54.9,"top_model_id":"mixtral-8x22b-instruct-v0.1","top_generation":"Mixtral v0.1","top_model_base":"Mixtral 8x22B v0.1","top_model_family":"Mixtral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":124,"total_models":3854,"placements":[{"place":1,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":54.9},{"place":2,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":53.4},{"place":3,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":52.8},{"place":4,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":51.9},{"place":5,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":47.5},{"place":6,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":47},{"place":7,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":46.9},{"place":8,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":44.6},{"place":9,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":44.6},{"place":10,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":42.6},{"place":11,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":42.2},{"place":12,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":41.5},{"place":13,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":40.4},{"place":14,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":40.2},{"place":15,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":40.1},{"place":16,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":40},{"place":17,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":39.6},{"place":18,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":39.6},{"place":19,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":38.7},{"place":20,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":38.7},{"place":21,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":38.6},{"place":22,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":37.4},{"place":23,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":37.1},{"place":24,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":37},{"place":25,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":36.7},{"place":26,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":36.6},{"place":27,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":36.5},{"place":28,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":36.1},{"place":29,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":36.1},{"place":30,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":36.1},{"place":31,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":36.1},{"place":32,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":35.6},{"place":33,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":35.5},{"place":34,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":35.5},{"place":35,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":35.1},{"place":36,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":35},{"place":37,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":34.8},{"place":38,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":34.5},{"place":39,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":34.2},{"place":40,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":34.16},{"place":41,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":33.8},{"place":42,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":33.41},{"place":43,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":33.4},{"place":44,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":33.2},{"place":45,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":33.1},{"place":46,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":33},{"place":47,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":32.7},{"place":48,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":32.6},{"place":49,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":32.5},{"place":50,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":31.4},{"place":51,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":31.2},{"place":52,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":31.1},{"place":53,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":31},{"place":54,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":30.9},{"place":55,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":30.89},{"place":56,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":30.8},{"place":57,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":30.6},{"place":58,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":30.3},{"place":59,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":29.6},{"place":60,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":29.5},{"place":61,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":29.4},{"place":62,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":29},{"place":63,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":28.8},{"place":64,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":28.8},{"place":65,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":28.8},{"place":66,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":28.4},{"place":67,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":28.1},{"place":68,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":28.1},{"place":69,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":28},{"place":70,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":27.8},{"place":71,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":27.5},{"place":72,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":26},{"place":73,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":25.9},{"place":74,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":25.5},{"place":75,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":25.5},{"place":76,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":25.4},{"place":77,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":25.2},{"place":78,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":25.2},{"place":79,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":25.15},{"place":80,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":25.1},{"place":81,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":24.9},{"place":82,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":24.85},{"place":83,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":24.8},{"place":84,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":24.7},{"place":85,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":24.5},{"place":86,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":24.1},{"place":87,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":24.1},{"place":88,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":24},{"place":89,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":23.9},{"place":90,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":23.6},{"place":91,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":23.2},{"place":92,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":23},{"place":93,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":23},{"place":94,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":22.9},{"place":95,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":22.7},{"place":96,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":22.7},{"place":97,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":22.5},{"place":98,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":22.2},{"place":99,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":22.1},{"place":100,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":21.3},{"place":101,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":21.1},{"place":102,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":20.2},{"place":103,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":20.17},{"place":104,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":19.8},{"place":105,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":19.6},{"place":106,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":19.1},{"place":107,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":18.6},{"place":108,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":18.1},{"place":109,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":17.8},{"place":110,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":17.7},{"place":111,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":17.5},{"place":112,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":17.4},{"place":113,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":17.2},{"place":114,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":17.2},{"place":115,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":17.2},{"place":116,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":16.8},{"place":117,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":16.7},{"place":118,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":16.32},{"place":119,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":16.3},{"place":120,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":15.76},{"place":121,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":15.7},{"place":122,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":15.3},{"place":123,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":14.2},{"place":124,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":14},{"place":125,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":13.2},{"place":126,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":12.8},{"place":127,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":12.7},{"place":128,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":12.5},{"place":129,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":12.4},{"place":130,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":12.4},{"place":131,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":11.8},{"place":132,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":11.6},{"place":133,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":11},{"place":134,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":10.9},{"place":135,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":10.14},{"place":136,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":10.1},{"place":137,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":9.97},{"place":138,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":9.7},{"place":139,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":9.48},{"place":140,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":9.4},{"place":141,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":9.31},{"place":142,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":8.9},{"place":143,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":8.9},{"place":144,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":8.9},{"place":145,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.8},{"place":146,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":8.25},{"place":147,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":8.1},{"place":148,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":6.4},{"place":149,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":5.48},{"place":150,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":5.07},{"place":151,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":3.8},{"place":152,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":3.3},{"place":153,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":3.2},{"place":154,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":3.1},{"place":155,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":3.02},{"place":156,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":3},{"place":157,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":2.8},{"place":158,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":2.41},{"place":159,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":1.83},{"place":160,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1.5},{"place":161,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":1.14},{"place":162,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":1.02},{"place":163,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":0.86},{"place":164,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":0.66},{"place":165,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":0.53},{"place":166,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":0.3}]},{"id":"navsim","name":"NAVSIM (PDMS)","topic":"Driving planning","description":"NAVSIM v1 non-reactive simulation benchmark for end-to-end driving planners; score = PDM Score (PDMS, 0-100).","url":"https://github.com/autonomousvision/navsim","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Qwen-Drive-1.0-4B RL","top_percent":90.7,"top_model_id":"qwen-drive-1.0-4b-rl","top_generation":"Qwen-Drive-1.0","top_model_base":"Qwen-Drive 1.0 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen-drive-1.0-4b-rl","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":90.7},{"place":2,"model":"spanvla","company":"spanvla","family":"SpanVLA","version":"SpanVLA","score":90.3},{"place":3,"model":"simwam-il","company":"hust","family":"SimWAM","version":"SimWAM","score":90.3},{"place":4,"model":"autovla","company":"ucla","family":"AutoVLA","version":"AutoVLA","score":89.6},{"place":5,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":88.2}]},{"id":"new-yorker-caption-matching","name":"New Yorker caption matching","topic":"Humor understanding","description":"Pick the caption written for a described New Yorker cartoon from five; accuracy (Jev Decision Index suite, posed as typed decisions).","url":"https://huggingface.co/datasets/jmhessel/newyorker_caption_contest","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"AutoTrust GEV-26B-Decide","top_percent":82,"top_model_id":"autotrust-gev-26b-decide","top_generation":"GEV-26B-Decide","top_model_base":"GEV-26B-Decide","top_model_family":"GEV","top_company":"autotrust","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":82},{"place":2,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":82},{"place":3,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":80.3},{"place":4,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":79.5},{"place":5,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":79},{"place":6,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":76.1},{"place":7,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":74.1},{"place":8,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":73.1},{"place":9,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":72.5},{"place":10,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":71.6},{"place":11,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":70.6},{"place":12,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":70.1},{"place":13,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":69.5},{"place":14,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":68.6},{"place":15,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":66.1},{"place":16,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":65.1},{"place":17,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":64.2},{"place":18,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":64},{"place":19,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":63.6},{"place":20,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":61.6},{"place":21,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61.6},{"place":22,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":60.4},{"place":23,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59.3},{"place":24,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":58.5},{"place":25,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":58.1},{"place":26,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56.6},{"place":27,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":55.7},{"place":28,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":55.5},{"place":29,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":46.6},{"place":30,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":45.5},{"place":31,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":45.5},{"place":32,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":40.3},{"place":33,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":40},{"place":34,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":36},{"place":35,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":32.2},{"place":36,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":30.7},{"place":37,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":27.1},{"place":38,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":27.1}]},{"id":"nextbase","name":"NextBase","topic":"Genomics","description":"Next-base DNA sequence prediction (per-base accuracy).","url":"https://huggingface.co/HuggingFaceBio/Carbon-X","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Carbon-X","top_percent":39.4,"top_model_id":"carbon-x","top_generation":"Carbon","top_model_base":"Carbon-X","top_model_family":"Carbon","top_company":"huggingface","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"carbon-x","company":"huggingface","family":"Carbon","version":"Carbon","score":39.4},{"place":2,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":32.9},{"place":3,"model":"gemini-4-argon-low","company":"google","family":"Gemini","version":"Gemini 4","score":31.2},{"place":4,"model":"kimi-k3-low","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":30.6},{"place":5,"model":"deepseek-v4.1-flash-low","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":27.2},{"place":6,"model":"glm-5.3-low","company":"zai","family":"GLM","version":"GLM 5.3","score":9.7},{"place":7,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1.1}]},{"id":"nextqa","name":"NExT-QA","topic":"Video understanding","description":"Video question answering benchmark on causal and temporal action reasoning (multiple-choice).","url":"https://github.com/doc-doc/NExT-QA","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":86.3,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86.3},{"place":2,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":86.3},{"place":3,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":86.2},{"place":4,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":85.5},{"place":5,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":85.5},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.3},{"place":7,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":85},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":84.3},{"place":9,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":84.3},{"place":10,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":84.1},{"place":11,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.4},{"place":12,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":83.4},{"place":13,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":83.2},{"place":14,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":83.2},{"place":15,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.8},{"place":16,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":81.7},{"place":17,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.4},{"place":18,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":81.3},{"place":19,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":80.3},{"place":20,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.2},{"place":21,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":78.8},{"place":22,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":75.8}]},{"id":"nexus","name":"Nexus (0-shot)","topic":"Tool use","description":"Nexus tool-use benchmark, zero-shot setting.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 3.1 405B","top_percent":58.7,"top_model_id":"llama-3.1-405b","top_generation":"Llama 3.1","top_model_base":"Llama 3.1 405B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"llama-3.1-405b","company":"meta","family":"Llama","version":"Llama 3.1","score":58.7},{"place":2,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":56.7},{"place":3,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":50.45},{"place":4,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49.93},{"place":5,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":47.8},{"place":6,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":47.65},{"place":7,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":44.83},{"place":8,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":38.5},{"place":9,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.71},{"place":10,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":36.25},{"place":11,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":35.18},{"place":12,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":34.38},{"place":13,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":33.69},{"place":14,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":31.59},{"place":15,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":18.1}]},{"id":"nih","name":"Needle In A Haystack","topic":"Long-context retrieval","description":"Needle In A Haystack test for locating hidden facts in long contexts.","url":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","leaderboard":"","github":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","paper":"","metric":"percent","stars":"","top_model":"MobileLLM P1 Base","top_percent":100,"top_model_id":"mobilellm-p1-base","top_generation":"MobileLLM P1","top_model_base":"MobileLLM P1","top_model_family":"MobileLLM","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":100},{"place":2,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":98.67},{"place":3,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":96.44}]},{"id":"nl2repo","name":"NL2Repo","topic":"Software engineering","description":"Long-horizon repository generation: agents build a complete Python repository from a natural-language requirements document; scored by the repo's test suite.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":79.9,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":78,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":79.9},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":75.3},{"place":3,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":71.9},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.7},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.4},{"place":6,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":68.2},{"place":7,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":65.4},{"place":8,"model":"qwen3.8-max-0902","company":"qwen","family":"Qwen","version":"Qwen3.8","score":64.9},{"place":9,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":64},{"place":10,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":63.2},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":63.1},{"place":12,"model":"iquest-q1","company":"iquest","family":"IQuest","version":"IQuest Q1","score":63},{"place":13,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.5},{"place":14,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.1},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":60.7},{"place":16,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":59.5},{"place":17,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":58.9},{"place":18,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":58.2},{"place":19,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":58},{"place":20,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":58},{"place":21,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.7},{"place":22,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":56.8},{"place":23,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":56.3},{"place":24,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":56.3},{"place":25,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":55.9},{"place":26,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":54.8},{"place":27,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.2},{"place":28,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":53},{"place":29,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":52.9},{"place":30,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":51.4},{"place":31,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":51.2},{"place":32,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":50.7},{"place":33,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":50},{"place":34,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":49.8},{"place":35,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":49.8},{"place":36,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.5},{"place":37,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":49.4},{"place":38,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":48.9},{"place":39,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":48.9},{"place":40,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":48.3},{"place":41,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":48.2},{"place":42,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":48.1},{"place":43,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":47.6},{"place":44,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":47.2},{"place":45,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":47},{"place":46,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":46.2},{"place":47,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":45.6},{"place":48,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":45.2},{"place":49,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":45.1},{"place":50,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":43.7},{"place":51,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.2},{"place":52,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":42.9},{"place":53,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":42.8},{"place":54,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":42.7},{"place":55,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":42.3},{"place":56,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":42.1},{"place":57,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":41.5},{"place":58,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":41.5},{"place":59,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":41.3},{"place":60,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":41.1},{"place":61,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":41},{"place":62,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":39.8},{"place":63,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":39.4},{"place":64,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":39.4},{"place":65,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.5},{"place":66,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37.9},{"place":67,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":37.3},{"place":68,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.8},{"place":69,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":36.2},{"place":70,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":36.2},{"place":71,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":35.9},{"place":72,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":35.6},{"place":73,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35.5},{"place":74,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35.5},{"place":75,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":35.3},{"place":76,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":35},{"place":77,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":34.6},{"place":78,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34.4},{"place":79,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.8},{"place":80,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":33.4},{"place":81,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":32.4},{"place":82,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.2},{"place":83,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":32.2},{"place":84,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":32},{"place":85,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":32},{"place":86,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":30.2},{"place":87,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":30.2},{"place":88,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":29.4},{"place":89,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":28.7},{"place":90,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":28.3},{"place":91,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":27.9},{"place":92,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":27.6},{"place":93,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":27.4},{"place":94,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.3},{"place":95,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":27.2},{"place":96,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":24.6},{"place":97,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":21.6},{"place":98,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":21},{"place":99,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.5},{"place":100,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":16.2},{"place":101,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15.5},{"place":102,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":11.6},{"place":103,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":10.3}]},{"id":"nli4ct","name":"NLI4CT","topic":"Clinical NLI","description":"NLI over clinical trial reports (SemEval NLI4CT); macro-F1 (Jev Decision Index suite, posed as typed decisions).","url":"https://sites.google.com/view/nli4ct/","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"vLLM-SR d3","top_percent":86,"top_model_id":"vllm-sr-d3","top_generation":"d3","top_model_base":"d3","top_model_family":"vLLM-SR d3","top_company":"vllm-sr","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":86},{"place":2,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":85.7},{"place":3,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":85.1},{"place":4,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":85.1},{"place":5,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":84.4},{"place":6,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":84.3},{"place":7,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":84.1},{"place":8,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":83.6},{"place":9,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":82.9},{"place":10,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":82.6},{"place":11,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":82.4},{"place":12,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":82.3},{"place":13,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":81.7},{"place":14,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":80.8},{"place":15,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":79.7},{"place":16,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":79.6},{"place":17,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":78.6},{"place":18,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":78.4},{"place":19,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":77.8},{"place":20,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":77.3},{"place":21,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":77.3},{"place":22,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":76.8},{"place":23,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":76.3},{"place":24,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":74.9},{"place":25,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":74.1},{"place":26,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":71.6},{"place":27,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":68.5},{"place":28,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":66.3},{"place":29,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":66.1},{"place":30,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":65.8},{"place":31,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":63.6},{"place":32,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":61.3},{"place":33,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59.5},{"place":34,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":57.6},{"place":35,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":56.7},{"place":36,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":53.2},{"place":37,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":48},{"place":38,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":47.7}]},{"id":"nocaps","name":"NoCaps","topic":"Image captioning","description":"Novel object captioning benchmark (CIDEr on val).","url":"https://nocaps.org/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1812.08658","metric":"cider","stars":"","top_model":"InstructBLIP (Vicuna-13B)","top_percent":121.9,"top_model_id":"instructblip-vicuna-13b","top_generation":"InstructBLIP","top_model_base":"InstructBLIP 13B","top_model_family":"BLIP","top_company":"salesforce","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"instructblip-vicuna-13b","company":"salesforce","family":"BLIP","version":"InstructBLIP","score":121.9},{"place":2,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":121.4},{"place":3,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":120.2},{"place":4,"model":"blip-2-vicuna-13b","company":"salesforce","family":"BLIP","version":"BLIP-2","score":103.9}]},{"id":"nolima-128k","name":"NoLiMa 128K","topic":"Long-context eval","description":"NoLiMa (No Literal Match) long-context benchmark at 128k context window.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniCPM-SALA","top_percent":23.86,"top_model_id":"minicpm-sala","top_generation":"MiniCPM SALA","top_model_base":"MiniCPM-SALA","top_model_family":"MiniCPM","top_company":"openbmb","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":23.86},{"place":2,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.25},{"place":3,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":5.8},{"place":4,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":4.73},{"place":5,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":3.48}]},{"id":"nolima-32k","name":"NoLiMa 32K","topic":"Long-context eval","description":"NoLiMa (No Literal Match) long-context benchmark at 32k context window.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniCPM-SALA","top_percent":54.54,"top_model_id":"minicpm-sala","top_generation":"MiniCPM SALA","top_model_base":"MiniCPM-SALA","top_model_family":"MiniCPM","top_company":"openbmb","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":54.54},{"place":2,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":43.4},{"place":3,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":19.69},{"place":4,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":14.89},{"place":5,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":3.78}]},{"id":"nolima-64k","name":"NoLiMa 64K","topic":"Long-context eval","description":"NoLiMa (No Literal Match) long-context benchmark at 64k context window.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniCPM-SALA","top_percent":42.95,"top_model_id":"minicpm-sala","top_generation":"MiniCPM SALA","top_model_base":"MiniCPM-SALA","top_model_family":"MiniCPM","top_company":"openbmb","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":42.95},{"place":2,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.35},{"place":3,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":11.82},{"place":4,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":9.87},{"place":5,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":2.48}]},{"id":"nova-63","name":"NOVA-63","topic":"Multilingual evaluation","description":"Multilingual evaluation benchmark covering 63 languages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-397B-A17B","top_percent":59.1,"top_model_id":"qwen3.5-397b-a17b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 397B A17B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":29,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.1},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.1},{"place":3,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":59},{"place":4,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":58.8},{"place":5,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.6},{"place":6,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.1},{"place":7,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57.9},{"place":8,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.1},{"place":9,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.7},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.7},{"place":11,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":56.7},{"place":12,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":56},{"place":13,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.9},{"place":14,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.4},{"place":15,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":55.1},{"place":16,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.6},{"place":17,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":54.6},{"place":18,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.3},{"place":19,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.2},{"place":20,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":53.3},{"place":21,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.8},{"place":22,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":52.5},{"place":23,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":51.9},{"place":24,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":51.1},{"place":25,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":48.7},{"place":26,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.1},{"place":27,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.4},{"place":28,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.4},{"place":29,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":40.3}]},{"id":"nuscenes","name":"NuScenes","topic":"3D scene understanding","description":"3D scene understanding and perception benchmark for autonomous driving.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-397B-A17B","top_percent":16,"top_model_id":"qwen3.5-397b-a17b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 397B A17B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":16},{"place":2,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15.4},{"place":3,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15.2},{"place":4,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.6},{"place":5,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":13.9},{"place":6,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":11.8},{"place":7,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":10.3},{"place":8,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.9},{"place":9,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.9},{"place":10,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5.7},{"place":11,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4.9},{"place":12,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4}]},{"id":"objectron","name":"Objectron","topic":"Object detection","description":"Objectron benchmark for 3D object detection in video captures.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-VL-235B-A22B Thinking","top_percent":71.2,"top_model_id":"qwen3-vl-235b-a22b-thinking","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.2},{"place":2,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":8.1},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":5.5}]},{"id":"obqa","name":"OBQA","topic":"Open book QA","description":"OpenBookQA science question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen2.5-Omni-3B","top_percent":76.26,"top_model_id":"qwen2.5-omni-3b","top_generation":"Qwen2.5 Omni","top_model_base":"Qwen2.5-Omni-3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":76.26},{"place":2,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":44.4},{"place":3,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":44.4},{"place":4,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":26.59},{"place":5,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":25.93}]},{"id":"ocnli","name":"OCNLI","topic":"Natural language inference (Chinese)","description":"Original Chinese Natural Language Inference benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Aquila2-34B","top_percent":79.92,"top_model_id":"aquila2-34b","top_generation":"Aquila2","top_model_base":"Aquila2 34B","top_model_family":"Aquila","top_company":"baai","top_open_source":1,"lower_is_better":false,"bench_models":37,"total_models":3854,"placements":[{"place":1,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":79.92},{"place":2,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":72.75},{"place":3,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":72.17},{"place":4,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":71.63},{"place":5,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.59},{"place":6,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":68.3},{"place":7,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":65.36},{"place":8,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":64.51},{"place":9,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":62.9},{"place":10,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":62.27},{"place":11,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":61.59},{"place":12,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":61.49},{"place":13,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":61.02},{"place":14,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":60.17},{"place":15,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":58.2},{"place":16,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":57.9},{"place":17,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":57.6},{"place":18,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":57},{"place":19,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":55},{"place":20,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":51},{"place":21,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":48.3},{"place":22,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":47.4},{"place":23,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":46.5},{"place":24,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":44.9},{"place":25,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":43.3},{"place":26,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":42.5},{"place":27,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":40.17},{"place":28,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":39},{"place":29,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":38.07},{"place":30,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":37.5},{"place":31,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":37.1},{"place":32,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":36.9},{"place":33,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":36.23},{"place":34,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":34.1},{"place":35,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":33.6},{"place":36,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":33.1},{"place":37,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":32.1},{"place":38,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":32.1},{"place":39,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":30.7},{"place":40,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":30.6},{"place":41,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":30.3},{"place":42,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":30.03},{"place":43,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":30},{"place":44,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":30},{"place":45,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":30},{"place":46,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":30},{"place":47,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":30},{"place":48,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":30}]},{"id":"ocrbench","name":"OCRBench V2","topic":"OCR (vision text extraction)","description":"OCRBench v2 evaluating text extraction from images and documents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-397B-A17B","top_percent":93.1,"top_model_id":"qwen3.5-397b-a17b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 397B A17B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":239,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.1},{"place":2,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":92.3},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":92.3},{"place":4,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.1},{"place":5,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":91.3},{"place":6,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":91.3},{"place":7,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":91.2},{"place":8,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91},{"place":9,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":90.7},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.4},{"place":11,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.3},{"place":12,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.3},{"place":13,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90},{"place":14,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90},{"place":15,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":89.7},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.6},{"place":17,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.5},{"place":18,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.4},{"place":19,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.4},{"place":20,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":89.3},{"place":21,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.3},{"place":22,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.2},{"place":23,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":89.1},{"place":24,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":89.1},{"place":25,"model":"step3-vl-10b-pacore","company":"stepfun","family":"Step","version":"Step3-VL","score":89},{"place":26,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":89},{"place":27,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":88.9},{"place":28,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":88.8},{"place":29,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.5},{"place":30,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.5},{"place":31,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.1},{"place":32,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":88.1},{"place":33,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":88},{"place":34,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":88},{"place":35,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":88},{"place":36,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":87.9},{"place":37,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":87.7},{"place":38,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":87.7},{"place":39,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":87.6},{"place":40,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":87.6},{"place":41,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.5},{"place":42,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.5},{"place":43,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.3},{"place":44,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87.1},{"place":45,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":87},{"place":46,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":86.9},{"place":47,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.9},{"place":48,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.8},{"place":49,"model":"step3-vl-10b-sere","company":"stepfun","family":"Step","version":"Step3-VL","score":86.75},{"place":50,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":86.75},{"place":51,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":86.7},{"place":52,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":86.7},{"place":53,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":86.6},{"place":54,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.6},{"place":55,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":86.6},{"place":56,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":86.6},{"place":57,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":86.5},{"place":58,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":86.5},{"place":59,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":86.5},{"place":60,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":86.5},{"place":61,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":86.5},{"place":62,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.4},{"place":63,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":86.4},{"place":64,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":86.3},{"place":65,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":86.3},{"place":66,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":86.3},{"place":67,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.3},{"place":68,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.2},{"place":69,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":86.2},{"place":70,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":86.2},{"place":71,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":86.1},{"place":72,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.1},{"place":73,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":86.1},{"place":74,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":86.1},{"place":75,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":86},{"place":76,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":86},{"place":77,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86},{"place":78,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":85.97},{"place":79,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.9},{"place":80,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.9},{"place":81,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.8},{"place":82,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.8},{"place":83,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":85.7},{"place":84,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":85.7},{"place":85,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":85.5},{"place":86,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":85.4},{"place":87,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":85.4},{"place":88,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.4},{"place":89,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":85.4},{"place":90,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.4},{"place":91,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.3},{"place":92,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.3},{"place":93,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":85.3},{"place":94,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":85.2},{"place":95,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":85.2},{"place":96,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":85.2},{"place":97,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":85.2},{"place":98,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":85.2},{"place":99,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":85.2},{"place":100,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85},{"place":101,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85},{"place":102,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":84.9},{"place":103,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.8},{"place":104,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":84.7},{"place":105,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":84.6},{"place":106,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.5},{"place":107,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":84.5},{"place":108,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":84.3},{"place":109,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":84.2},{"place":110,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":84.2},{"place":111,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":84.2},{"place":112,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":84.2},{"place":113,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":84},{"place":114,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.9},{"place":115,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83.9},{"place":116,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":83.9},{"place":117,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":83.9},{"place":118,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":83.8},{"place":119,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":83.8},{"place":120,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":83.7},{"place":121,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":83.7},{"place":122,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":83.7},{"place":123,"model":"internvl2-pro","company":"opengvlab","family":"Intern","version":"InternVL 2","score":83.7},{"place":124,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":83.6},{"place":125,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":83.5},{"place":126,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":83.4},{"place":127,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":83.3},{"place":128,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":83.3},{"place":129,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":83.2},{"place":130,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.1},{"place":131,"model":"ovis1.6-gemma2-9b","company":"alibaba","family":"Ovis","version":"Ovis1.6-Gemma2","score":83},{"place":132,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.85},{"place":133,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":82.8},{"place":134,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.8},{"place":135,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":82.5},{"place":136,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":82.5},{"place":137,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":82.3},{"place":138,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":82.2},{"place":139,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":82.2},{"place":140,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":82.2},{"place":141,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.1},{"place":142,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82},{"place":143,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.9},{"place":144,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":81.8},{"place":145,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":81.7},{"place":146,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.6},{"place":147,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":81.6},{"place":148,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.3},{"place":149,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":81.3},{"place":150,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":81.3},{"place":151,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":81.1},{"place":152,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":81},{"place":153,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":80.9},{"place":154,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":80.9},{"place":155,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":80.9},{"place":156,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.8},{"place":157,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":80.7},{"place":158,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":80.7},{"place":159,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":80.7},{"place":160,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":80.7},{"place":161,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":80.6},{"place":162,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":80.4},{"place":163,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":80.2},{"place":164,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":79.9},{"place":165,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":79.8},{"place":166,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":79.8},{"place":167,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":79.7},{"place":168,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":79.7},{"place":169,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":79.4},{"place":170,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":79.4},{"place":171,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":79.3},{"place":172,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.2},{"place":173,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":79.2},{"place":174,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.1},{"place":175,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":78.8},{"place":176,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":78.8},{"place":177,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":78.8},{"place":178,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":78.8},{"place":179,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":78.7},{"place":180,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":78.6},{"place":181,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":78.5},{"place":182,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":78.5},{"place":183,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":78.5},{"place":184,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":78.4},{"place":185,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":78},{"place":186,"model":"cogvlm2-llama3-chinese-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":78},{"place":187,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":77.8},{"place":188,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.6},{"place":189,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":77.6},{"place":190,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":77.2},{"place":191,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.9},{"place":192,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.8},{"place":193,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.6},{"place":194,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":76},{"place":195,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":75.9},{"place":196,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":75.7},{"place":197,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":75.6},{"place":198,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":75.4},{"place":199,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":75.4},{"place":200,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":75.3},{"place":201,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":75.3},{"place":202,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.1},{"place":203,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":74.6},{"place":204,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.5},{"place":205,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.5},{"place":206,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":74.1},{"place":207,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":74.1},{"place":208,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":73.9},{"place":209,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":73.6},{"place":210,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":73.6},{"place":211,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":73.5},{"place":212,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.5},{"place":213,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":73.3},{"place":214,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":73.3},{"place":215,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":73.1},{"place":216,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":72.9},{"place":217,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":72.7},{"place":218,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":72.6},{"place":219,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":72.5},{"place":220,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":72.5},{"place":221,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":72.4},{"place":222,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":72.3},{"place":223,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":72},{"place":224,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.9},{"place":225,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":70.4},{"place":226,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":70.2},{"place":227,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":70.1},{"place":228,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":70.1},{"place":229,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":70},{"place":230,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":70},{"place":231,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":69.4},{"place":232,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":69.4},{"place":233,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":69.4},{"place":234,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":69},{"place":235,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":68.7},{"place":236,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":68.5},{"place":237,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.4},{"place":238,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":68.4},{"place":239,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":68},{"place":240,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":68},{"place":241,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":68},{"place":242,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":67.8},{"place":243,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":67.5},{"place":244,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.3},{"place":245,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.8},{"place":246,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":65.9},{"place":247,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":65.9},{"place":248,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":65.9},{"place":249,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":65.8},{"place":250,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":65.8},{"place":251,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":65.7},{"place":252,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":65.6},{"place":253,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":65.6},{"place":254,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":65.6},{"place":255,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":64.6},{"place":256,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":64.5},{"place":257,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":64.5},{"place":258,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":64.2},{"place":259,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":63.9},{"place":260,"model":"phi-3-vision-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":63.9},{"place":261,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":63.7},{"place":262,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":63.5},{"place":263,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":63.2},{"place":264,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":63.2},{"place":265,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":62.6},{"place":266,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":62.5},{"place":267,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":62},{"place":268,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":60.6},{"place":269,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":60.5},{"place":270,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":60.5},{"place":271,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":60},{"place":272,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":60},{"place":273,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":59.9},{"place":274,"model":"docowl-1.5-chat","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Chat","score":59.9},{"place":275,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":59.1},{"place":276,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":59.1},{"place":277,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":59},{"place":278,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":59},{"place":279,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":59},{"place":280,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":57.4},{"place":281,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":56.9},{"place":282,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":56.5},{"place":283,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":56.1},{"place":284,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":55.9},{"place":285,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":55.8},{"place":286,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":55.8},{"place":287,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":55},{"place":288,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":53.2},{"place":289,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":51.8},{"place":290,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":51.6},{"place":291,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":51.6},{"place":292,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":48.8},{"place":293,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":48.7},{"place":294,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":47.2},{"place":295,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":46},{"place":296,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":45.6},{"place":297,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":43.5},{"place":298,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":41.44},{"place":299,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":41.3},{"place":300,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":40.9},{"place":301,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":36.6},{"place":302,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":35.11},{"place":303,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":33.7},{"place":304,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":33.53},{"place":305,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":33.1},{"place":306,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":29},{"place":307,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":29},{"place":308,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":26.61},{"place":309,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":7.6},{"place":310,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":3.2}]},{"id":"ocrbench-elo","name":"OCRBench-ELO","topic":"OCR (ELO ranking)","description":"OCR benchmark using ELO rating system to rank model performance on text extraction tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"elo","stars":"","top_model":"Gemini 3 Pro","top_percent":909,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":909},{"place":2,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":880},{"place":3,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":878},{"place":4,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":873},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":866},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":863},{"place":7,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":858},{"place":8,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":834},{"place":9,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":831},{"place":10,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":824},{"place":11,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":822},{"place":12,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":810},{"place":13,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":804},{"place":14,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":725},{"place":15,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":684},{"place":16,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":657},{"place":17,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":609},{"place":18,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":459}]},{"id":"ocrbench-kie","name":"OCRBench (KIE)","topic":"Key information extraction","description":"Key information extraction subset of OCRBench (v1).","url":"https://github.com/Yuliang-Liu/MultimodalOCR","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":96,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":96},{"place":2,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":95},{"place":3,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94},{"place":4,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":90.5},{"place":5,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89},{"place":6,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":81},{"place":7,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":79},{"place":8,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.5},{"place":9,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":76.5}]},{"id":"ocrbenchv2-cn","name":"OCRBenchV2 (CN)","topic":"OCR (Chinese)","description":"OCRBenchV2 Chinese subset assessing OCR performance on Chinese-language documents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":68.3,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":61,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":68.3},{"place":2,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":68.3},{"place":3,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.3},{"place":4,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":67.1},{"place":5,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":67.1},{"place":6,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":66},{"place":7,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.8},{"place":8,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":63.7},{"place":9,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.6},{"place":10,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.5},{"place":11,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.2},{"place":12,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":61.6},{"place":13,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":61.3},{"place":14,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.2},{"place":15,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61},{"place":16,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":60.77},{"place":17,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":60.6},{"place":18,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":60.5},{"place":19,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.4},{"place":20,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":59.6},{"place":21,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":59.5},{"place":22,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":59.3},{"place":23,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.2},{"place":24,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":59.15},{"place":25,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.13},{"place":26,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":58.97},{"place":27,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":58.32},{"place":28,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":58.2},{"place":29,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":58.1},{"place":30,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.8},{"place":31,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":57.7},{"place":32,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":57.7},{"place":33,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.6},{"place":34,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.6},{"place":35,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":57.4},{"place":36,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":57.3},{"place":37,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":56.8},{"place":38,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":55.84},{"place":39,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":55.84},{"place":40,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":55.48},{"place":41,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.4},{"place":42,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":55.3},{"place":43,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":54.9},{"place":44,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.6},{"place":45,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53},{"place":46,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":52.5},{"place":47,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":52.4},{"place":48,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.5},{"place":49,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":48.4},{"place":50,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":48.2},{"place":51,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":48.1},{"place":52,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":47.3},{"place":53,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":45.1},{"place":54,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.9},{"place":55,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.8},{"place":56,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":43.7},{"place":57,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":43.2},{"place":58,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.9},{"place":59,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":39.5},{"place":60,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":38.31},{"place":61,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":37.7},{"place":62,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":36.2},{"place":63,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.1},{"place":64,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":34.2},{"place":65,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":31.3},{"place":66,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":30.4},{"place":67,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":27.3},{"place":68,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":24.6},{"place":69,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":23.5},{"place":70,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":23.2},{"place":71,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21.7}]},{"id":"ocrbenchv2-en","name":"OCRBenchV2 (EN)","topic":"OCR (English)","description":"OCRBenchV2 English subset evaluating OCR accuracy on English documents and layouts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":74.2,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":78,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":74.2},{"place":2,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":74.2},{"place":3,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":72.6},{"place":4,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":70.7},{"place":5,"model":"interfaze","company":"interfaze","family":"Interfaze","version":"Interfaze 1","score":70.7},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":69},{"place":7,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.3},{"place":8,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":68.12},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68},{"place":10,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67.9},{"place":11,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.43},{"place":12,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.4},{"place":13,"model":"nemotron-3-nano-omni-30b-a3b-reasoning","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.04},{"place":14,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.02},{"place":15,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67},{"place":16,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.8},{"place":17,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":66.28},{"place":18,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":66.18},{"place":19,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":66.07},{"place":20,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":65.9},{"place":21,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.4},{"place":22,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":65.3},{"place":23,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":65.1},{"place":24,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.6},{"place":25,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":64.2},{"place":26,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.7},{"place":27,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":63.5},{"place":28,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.2},{"place":29,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":62},{"place":30,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.9},{"place":31,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":61.8},{"place":32,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":61.6},{"place":33,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":61.5},{"place":34,"model":"interfaze-1.1-lite","company":"interfaze","family":"Interfaze","version":"Interfaze 1.1","score":60.9},{"place":35,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.68},{"place":36,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":60.1},{"place":37,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":59.1},{"place":38,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.8},{"place":39,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.7},{"place":40,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":58.5},{"place":41,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.8},{"place":42,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":56.4},{"place":43,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.3},{"place":44,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":56},{"place":45,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":55.8},{"place":46,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":54.8},{"place":47,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":54.7},{"place":48,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":54.7},{"place":49,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.3},{"place":50,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":54.3},{"place":51,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":54.2},{"place":52,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.1},{"place":53,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":53.9},{"place":54,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":53},{"place":55,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":52.7},{"place":56,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":52.6},{"place":57,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":51.5},{"place":58,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":50.7},{"place":59,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":49.2},{"place":60,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":49.1},{"place":61,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.8},{"place":62,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":48.7},{"place":63,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":48.4},{"place":64,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":48.2},{"place":65,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.1},{"place":66,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.1},{"place":67,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48},{"place":68,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.7},{"place":69,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":47.5},{"place":70,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":47},{"place":71,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.4},{"place":72,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":45.5},{"place":73,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.7},{"place":74,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":44.6},{"place":75,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.5},{"place":76,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.4},{"place":77,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.3},{"place":78,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":43.9},{"place":79,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.5},{"place":80,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.9},{"place":81,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":41.8},{"place":82,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.7},{"place":83,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":41.5},{"place":84,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.5},{"place":85,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":41.4},{"place":86,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":41.4},{"place":87,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":40.6},{"place":88,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":40.1},{"place":89,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.8},{"place":90,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":37.9},{"place":91,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":36.7},{"place":92,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":36},{"place":93,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":33.9},{"place":94,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":32.9},{"place":95,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":30.4},{"place":96,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":23.8},{"place":97,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":15.98}]},{"id":"ocrbenchv2-kie","name":"OCRBenchV2 KIE","topic":"Key information extraction","description":"Key information extraction subset of OCRBench v2 as reported without a language split (OvisOCR3 release).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OvisOCR3","top_percent":83.01,"top_model_id":"ovisocr3","top_generation":"OvisOCR3","top_model_base":"OvisOCR3","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":83.01},{"place":2,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":74.66},{"place":3,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":74.22},{"place":4,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.9},{"place":5,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":68.63}]},{"id":"ocrbenchv2-kie-en","name":"OCRBenchV2 KIE (EN)","topic":"Key information extraction","description":"English key information extraction subset of OCRBench v2.","url":"https://github.com/Yuliang-Liu/MultimodalOCR","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":87.8,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.8},{"place":2,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.6},{"place":3,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":82.8},{"place":4,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.1}]},{"id":"ocrbenchv2-kie-zh","name":"OCRBenchV2 KIE (ZH)","topic":"Key information extraction (Chinese)","description":"Chinese key information extraction subset of OCRBench v2.","url":"https://github.com/Yuliang-Liu/MultimodalOCR","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qianfan-OCR","top_percent":82.3,"top_model_id":"qianfan-ocr","top_generation":"Qianfan-OCR","top_model_base":"Qianfan-OCR","top_model_family":"Qianfan","top_company":"baidu","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":82.3},{"place":2,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.3},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":63.4},{"place":4,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.9}]},{"id":"ocrreasoning","name":"OCRReasoning","topic":"OCR reasoning","description":"OCR reasoning benchmark combining text extraction with multi-step reasoning over documents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":70.81,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.81},{"place":2,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67.1},{"place":3,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":66.23},{"place":4,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":66.14},{"place":5,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":65.2},{"place":6,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":65.08},{"place":7,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":64.6},{"place":8,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.3},{"place":9,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":63.42},{"place":10,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":62.49},{"place":11,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":59.78},{"place":12,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":59.03},{"place":13,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":54.7},{"place":14,"model":"nemotron-3-nano-omni-30b-a3b-reasoning","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":54.14},{"place":15,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":38.02},{"place":16,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":33.9},{"place":17,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":22.85}]},{"id":"ocrvqa","name":"OCR-VQA","topic":"Text-based VQA","description":"Visual question answering by reading text in book cover images.","url":"https://ocr-vqa.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen-VL","top_percent":75.7,"top_model_id":"qwen-vl","top_generation":"Qwen-VL","top_model_base":"Qwen-VL","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":75.7},{"place":2,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":75},{"place":3,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":73.8},{"place":4,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":70.5},{"place":5,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":67.8},{"place":6,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":66.8},{"place":7,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.7},{"place":8,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.3}]},{"id":"octocodingbench","name":"OctoCodingBench","topic":"Code generation","description":"Coding benchmark across multi-language programming tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":36.2,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":36.2},{"place":2,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":26.1},{"place":3,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":26},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":22.9},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":22.8},{"place":6,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":13.3}]},{"id":"ocw-courses","name":"OCW Courses","topic":"STEM math reasoning","description":"MIT OpenCourseWare undergraduate STEM problems (from Minerva).","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2206.14858","metric":"percent","stars":"","top_model":"Minerva 540B","top_percent":17.6,"top_model_id":"minerva-540b","top_generation":"Minerva","top_model_base":"Minerva 540B","top_model_family":"Minerva","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"minerva-540b","company":"google","family":"Minerva","version":"Minerva","score":17.6},{"place":2,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":15.4},{"place":3,"model":"minerva-62b","company":"google","family":"Minerva","version":"Minerva","score":12},{"place":4,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":10.3},{"place":5,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":9.2},{"place":6,"model":"minerva-8b","company":"google","family":"Minerva","version":"Minerva","score":7.7},{"place":7,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":6.3}]},{"id":"odinw-13","name":"ODinW-13","topic":"Object detection (in the wild)","description":"Object Detection in the Wild benchmark covering 13 real-world domains.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.6-Plus","top_percent":51.8,"top_model_id":"qwen3.6-plus","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":33,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":51.8},{"place":2,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":51.5},{"place":3,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":51.1},{"place":4,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":50.8},{"place":5,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":49.5},{"place":6,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.2},{"place":7,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.5},{"place":8,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47},{"place":9,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":46.8},{"place":10,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.6},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":46.3},{"place":12,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":45.87},{"place":13,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.7},{"place":14,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":44.6},{"place":15,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.5},{"place":16,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":43.6},{"place":17,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.4},{"place":18,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.2},{"place":19,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":43.2},{"place":20,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.2},{"place":21,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":43.1},{"place":22,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.6},{"place":23,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":41.3},{"place":24,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.1},{"place":25,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.78},{"place":26,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":40.19},{"place":27,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":39.4},{"place":28,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36},{"place":29,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.9},{"place":30,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":35.87},{"place":31,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.7},{"place":32,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.6},{"place":33,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":4.8}]},{"id":"odvbench","name":"ODVBench","topic":"Streaming video understanding","description":"Online/streaming video understanding benchmark (accuracy).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"JoyAI-VL-Interaction","top_percent":68.6,"top_model_id":"joyai-vl-interaction","top_generation":"JoyAI-VL","top_model_base":"JoyAI-VL-Interaction","top_model_family":"JoyAI-VL","top_company":"jd","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":68.6},{"place":2,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.1},{"place":3,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":53.84},{"place":4,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":47.68}]},{"id":"odyssey-math","name":"Odyssey Math","topic":"Math reasoning","description":"Odyssey multi-step math benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek-Coder V2 Instruct","top_percent":53.7,"top_model_id":"deepseek-coder-v2-instruct","top_generation":"DeepSeek Coder V2","top_model_base":"DeepSeek-Coder V2","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":53.7},{"place":2,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":53.2},{"place":3,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":49.1},{"place":4,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":46.8},{"place":5,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":45},{"place":6,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":44.4},{"place":7,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":40.6},{"place":8,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":37.2},{"place":9,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":27.9},{"place":10,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":27.6},{"place":11,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":24.8},{"place":12,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":24},{"place":13,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":18.9},{"place":14,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":18.6}]},{"id":"officeqa","name":"OfficeQA","topic":"Enterprise document QA","description":"Grounded question answering over office and enterprise documents, as reported by OpenAI for GPT-5.4.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":86.3,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":86.3},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.5},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":68.1},{"place":4,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":65.1},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":63.1}]},{"id":"officeqa-pro","name":"OfficeQA Pro","topic":"Enterprise document QA","description":"Harder OfficeQA variant. Models must use files, tools and context together instead of answering from memory.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":80.6,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":34,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":80.6},{"place":2,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":76.5},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":74.4},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":72.5},{"place":5,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":70.9},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":69.9},{"place":7,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":69.2},{"place":8,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":67.2},{"place":9,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":67.1},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":66.4},{"place":11,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":66.2},{"place":12,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":66.2},{"place":13,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":66.2},{"place":14,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":66.2},{"place":15,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.2},{"place":16,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":65.8},{"place":17,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":65.4},{"place":18,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.4},{"place":19,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":65.4},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":65.4},{"place":21,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":63.9},{"place":22,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":63.3},{"place":23,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":63.2},{"place":24,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":62.9},{"place":25,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":62.8},{"place":26,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":62.4},{"place":27,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":60.9},{"place":28,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":59.4},{"place":29,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.9},{"place":30,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57.9},{"place":31,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":57.1},{"place":32,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":54.1},{"place":33,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":54.1},{"place":34,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":53.2},{"place":35,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":52.6},{"place":36,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.2},{"place":37,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":51.1},{"place":38,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":48.9},{"place":39,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":48.1},{"place":40,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":48.1},{"place":41,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":46.6},{"place":42,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":45.1},{"place":43,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":43.6},{"place":44,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":43.6},{"place":45,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":42.9},{"place":46,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":41.4},{"place":47,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.1},{"place":48,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":23.3},{"place":49,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":21.1},{"place":50,"model":"mimo-v2.6-distill-qwen-9b","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":19.5},{"place":51,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":18.1},{"place":52,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15.8},{"place":53,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15.3},{"place":54,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9},{"place":55,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.3},{"place":56,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.1}]},{"id":"officeqa-pro-v2","name":"OfficeQA Pro v2","topic":"Enterprise document QA","description":"OfficeQA Pro v2: grounded QA over office/enterprise documents requiring files, tools and context.","url":"https://www.kimi.ai/blog/kimi-k3-1-pro","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3.1 Pro","top_percent":64.4,"top_model_id":"kimi-k3.1-pro","top_generation":"Kimi K3.1","top_model_base":"Kimi K3.1 Pro","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":64.4},{"place":2,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":62.2},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":54.5},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":54.4},{"place":5,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":40.4},{"place":6,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":31.1}]},{"id":"oibench-en","name":"OIBench EN","topic":"Code generation","description":"English subset of OIBench for code generation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":58.2,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":58.2},{"place":2,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50},{"place":3,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":47.7},{"place":4,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":43.3},{"place":5,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":39},{"place":6,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":36.8},{"place":7,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":30.8}]},{"id":"ojbench","name":"OJBench","topic":"Code generation (online judge)","description":"Programming problems evaluated via online judge-style execution.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Keye-VL-2.0-30B-A3B","top_percent":71.5,"top_model_id":"keye-vl-2.0-30b-a3b","top_generation":"Keye-VL 2.0","top_model_base":"Keye-VL 2.0 30B A3B","top_model_family":"Keye-VL","top_company":"kuaishou","top_open_source":1,"lower_is_better":false,"bench_models":71,"total_models":3854,"placements":[{"place":1,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":71.5},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.7},{"place":3,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.2},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68.5},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":61.2},{"place":6,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":60.6},{"place":7,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":60.3},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":58.8},{"place":9,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":58.7},{"place":10,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":57.4},{"place":11,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":56.2},{"place":12,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":55},{"place":13,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":54.7},{"place":14,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":54.7},{"place":15,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.6},{"place":16,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":48.7},{"place":17,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":48.4},{"place":18,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":46.7},{"place":19,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":44.6},{"place":20,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":42.3},{"place":21,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":42.2},{"place":22,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":41.8},{"place":23,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":41.8},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":41.6},{"place":25,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":41.5},{"place":26,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":41.5},{"place":27,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":41.2},{"place":28,"model":"longcat-flash-thinking","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":40.7},{"place":29,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":40.4},{"place":30,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.1},{"place":31,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.5},{"place":32,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":38.9},{"place":33,"model":"vibethinker-3b","company":"weibo","family":"VibeThinker","version":"VibeThinker","score":38.6},{"place":34,"model":"o3","company":"openai","family":"o3","version":"o3","score":38.4},{"place":35,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":38.2},{"place":36,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":36.3},{"place":37,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36},{"place":38,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":35.6},{"place":39,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":34.1},{"place":40,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":33.6},{"place":41,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":33.6},{"place":42,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":32.7},{"place":43,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":32.5},{"place":44,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":32.5},{"place":45,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":32.1},{"place":46,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":30.4},{"place":47,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":29.7},{"place":48,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":29.4},{"place":49,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.2},{"place":50,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":27.1},{"place":51,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":25.9},{"place":52,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":25.5},{"place":53,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":25.4},{"place":54,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":25.1},{"place":55,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.8},{"place":56,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":24.1},{"place":57,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.1},{"place":58,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":24},{"place":59,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":23.5},{"place":60,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":23.5},{"place":61,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":23.5},{"place":62,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":21.8},{"place":63,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":21.6},{"place":64,"model":"mimo-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":20.2},{"place":65,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":20},{"place":66,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":19.6},{"place":67,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":19.5},{"place":68,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":19.5},{"place":69,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":19},{"place":70,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":19},{"place":71,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":17.9},{"place":72,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":15.6},{"place":73,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":15.3},{"place":74,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":15.1},{"place":75,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":14.4},{"place":76,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":14.2},{"place":77,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":12.1},{"place":78,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":11.6},{"place":79,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.3},{"place":80,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":11.2},{"place":81,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":8.2},{"place":82,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":7.33},{"place":83,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":5.2},{"place":84,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.6},{"place":85,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":1.94},{"place":86,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":0.86},{"place":87,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.43}]},{"id":"okvqa","name":"OK-VQA","topic":"Knowledge-based VQA","description":"Visual question answering requiring outside knowledge.","url":"https://okvqa.allenai.org/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1906.00067","metric":"percent","stars":"","top_model":"Emu2-Chat","top_percent":64.8,"top_model_id":"emu2-chat","top_generation":"Emu2-Chat","top_model_base":"Emu2-Chat","top_model_family":"Emu","top_company":"baai","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":64.8},{"place":2,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":64.8},{"place":3,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":62.6},{"place":4,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":61.2},{"place":5,"model":"fuyu-8b","company":"adept","family":"Fuyu","version":"Fuyu","score":60.6},{"place":6,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":58.6},{"place":7,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":57.7},{"place":8,"model":"ureader","company":"alibaba","family":"mPLUG","version":"UReader","score":57.6},{"place":9,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":56.6},{"place":10,"model":"unified-io-2-xxl","company":"allenai","family":"Unified-IO","version":"Unified-IO 2","score":55.5},{"place":11,"model":"flamingo-80b","company":"google","family":"Flamingo","version":"Flamingo","score":50.6},{"place":12,"model":"shikra-13b","company":"sensetime","family":"Shikra","version":"Shikra","score":47.16},{"place":13,"model":"blip-2-vicuna-13b","company":"salesforce","family":"BLIP","version":"BLIP-2","score":45.9},{"place":14,"model":"flamingo-9b","company":"google","family":"Flamingo","version":"Flamingo","score":44.7},{"place":15,"model":"dreamllm-7b","company":"megvii","family":"DreamLLM","version":"DreamLLM","score":44.3},{"place":16,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":38.3},{"place":17,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":36.9}]},{"id":"olmocr-bench","name":"olmOCR-Bench","topic":"Document OCR","description":"olmOCR benchmark assessing OCR fidelity and structured extraction on complex document pages.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Infinity-Parser2-Pro","top_percent":87.6,"top_model_id":"infinity-parser2-pro","top_generation":"Infinity-Parser2","top_model_base":"Infinity-Parser2 Pro","top_model_family":"Infinity-Parser","top_company":"infly","top_open_source":1,"lower_is_better":false,"bench_models":61,"total_models":3854,"placements":[{"place":1,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":87.6},{"place":2,"model":"lightonocr-3-4b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":86.3},{"place":3,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":86},{"place":4,"model":"chandra-ocr-2","company":"chandra","family":"Chandra OCR","version":"Chandra OCR 2","score":85.9},{"place":5,"model":"chandra-ocr-2","company":"chandra","family":"Chandra OCR","version":"Chandra OCR 2","score":85.8},{"place":6,"model":"interfaze","company":"interfaze","family":"Interfaze","version":"Interfaze 1","score":85.7},{"place":7,"model":"lightonocr-3-0.8b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":85.5},{"place":8,"model":"mistral-ocr-4","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":85.2},{"place":9,"model":"lightonocr-3-1b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":84.5},{"place":10,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":83.9},{"place":11,"model":"interfaze-1.1-lite","company":"interfaze","family":"Interfaze","version":"Interfaze 1.1","score":83.8},{"place":12,"model":"jina-ocr-v1","company":"jina","family":"jina-ocr","version":"jina-ocr-v1","score":83.4},{"place":13,"model":"surya-ocr-2","company":"datalab","family":"Surya OCR","version":"Surya OCR 2","score":83.3},{"place":14,"model":"lightonocr-2-1b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-2","score":83.2},{"place":15,"model":"chandra-ocr-0.1.0","company":"chandra","family":"Chandra OCR","version":"Chandra OCR","score":83.1},{"place":16,"model":"chandra-ocr-2","company":"chandra","family":"Chandra OCR","version":"Chandra OCR 2","score":83},{"place":17,"model":"infinity-parser-7b","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser","score":82.5},{"place":18,"model":"olmocr-2-7b-1025","company":"allenai","family":"OLMOCR","version":"OLMOCR 2","score":82.4},{"place":19,"model":"lightonocr-2-1b-ocr-soup","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-2","score":82.4},{"place":20,"model":"mineru2.5-pro","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":82},{"place":21,"model":"chandra-ocr-0.1.0","company":"chandra","family":"Chandra OCR","version":"Chandra OCR","score":82},{"place":22,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":81.9},{"place":23,"model":"mistral-ocr-4.1","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":81.9},{"place":24,"model":"lightonocr-2-1b-base","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-2","score":81.8},{"place":25,"model":"chandra-ocr-0.1.0","company":"chandra","family":"Chandra OCR","version":"Chandra OCR","score":81.7},{"place":26,"model":"mistral-ocr-3","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":81.7},{"place":27,"model":"lightonocr-2-1b-bbox-base","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-2","score":80.8},{"place":28,"model":"lightonocr-2-1b-bbox-soup","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-2","score":80.8},{"place":29,"model":"olmocr-2-7b-1025","company":"allenai","family":"OLMOCR","version":"OLMOCR 2","score":80.4},{"place":30,"model":"falcon-ocr","company":"tii","family":"Falcon-OCR","version":"Falcon-OCR","score":80.3},{"place":31,"model":"lightonocr-2-1b-bbox","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-2","score":80.2},{"place":32,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80.2},{"place":33,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":80.1},{"place":34,"model":"paddleocr-vl","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR","score":80},{"place":35,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":79.3},{"place":36,"model":"paddleocr-vl","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR","score":79.2},{"place":37,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":79.1},{"place":38,"model":"mistral-ocr-3","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":79.1},{"place":39,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":79},{"place":40,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":78.8},{"place":41,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":78.5},{"place":42,"model":"paddleocr-vl","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR","score":77.5},{"place":43,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":77.5},{"place":44,"model":"olmocr","company":"allenai","family":"OLMOCR","version":"OLMOCR","score":77.4},{"place":45,"model":"lightonocr-2-1b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-2","score":77.3},{"place":46,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":77},{"place":47,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":76.9},{"place":48,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":76.3},{"place":49,"model":"marker","company":"datalab","family":"Marker","version":"Marker","score":76.1},{"place":50,"model":"olmocr","company":"allenai","family":"OLMOCR","version":"OLMOCR","score":76.1},{"place":51,"model":"lightonocr-1b-1025","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-1","score":76.1},{"place":52,"model":"monkeyocr-pro-3b","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCR Pro","score":75.8},{"place":53,"model":"deepseek-ocr-base","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":75.7},{"place":54,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":75.7},{"place":55,"model":"olmocr","company":"allenai","family":"OLMOCR","version":"OLMOCR","score":75.5},{"place":56,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":75.3},{"place":57,"model":"mineru-2.5.4","company":"opendatalab","family":"MinerU","version":"MinerU","score":75.2},{"place":58,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":75.2},{"place":59,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.9},{"place":60,"model":"monkeyocr-pro-3b","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCR Pro","score":73.6},{"place":61,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":73.1},{"place":62,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":72.2},{"place":63,"model":"mistral-ocr-api","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":72},{"place":64,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":72},{"place":65,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":71},{"place":66,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":70.4},{"place":67,"model":"marker-v1.7.5","company":"datalab","family":"Marker","version":"Marker","score":70.1},{"place":68,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":69.9},{"place":69,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":69.8},{"place":70,"model":"nanonets-ocr2-3b","company":"nanonets","family":"Nanonets OCR","version":"Nanonets OCR2","score":69.5},{"place":71,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":68.9},{"place":72,"model":"monkeyocr-pro-1.2b","company":"monkeyocr","family":"MonkeyOCR","version":"MonkeyOCR","score":68.9},{"place":73,"model":"sarashina2.2-ocr","company":"sbintuitions","family":"Sarashina2.2","version":"Sarashina2.2","score":68.3},{"place":74,"model":"olmocr","company":"allenai","family":"OLMOCR","version":"OLMOCR","score":68.2},{"place":75,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":65.5},{"place":76,"model":"nanonets-ocr-s","company":"nanonets","family":"Nanonets OCR","version":"Nanonets OCR","score":64.5},{"place":77,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":64.3},{"place":78,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":63.8},{"place":79,"model":"mineru-1.3.10","company":"opendatalab","family":"MinerU","version":"MinerU","score":61.5},{"place":80,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":59.2},{"place":81,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.8},{"place":82,"model":"got-ocr","company":"stepfun","family":"GOT-OCR","version":"GOT-OCR","score":48.3},{"place":83,"model":"got-ocr2.0","company":"stepfun","family":"GOT-OCR","version":"GOT-OCR","score":48.3},{"place":84,"model":"qwen2-vl","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":31.5},{"place":85,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":31.5}]},{"id":"olympiadbench","name":"OlympiadBench","topic":"Math (olympiad)","description":"Advanced mathematics olympiad-style problem benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-30B-A3B-Instruct-2507","top_percent":77.59,"top_model_id":"qwen3-30b-a3b-instruct-2507","top_generation":"Qwen3","top_model_base":"Qwen3 30B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":80,"total_models":3854,"placements":[{"place":1,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.59},{"place":2,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":76.59},{"place":3,"model":"hunyuan-7b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":76.5},{"place":4,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":76.19},{"place":5,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":75.85},{"place":6,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":74.07},{"place":7,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":72.3},{"place":8,"model":"questa-nemotron-1.5b","company":"amazon","family":"Nemotron","version":"QuestA Nemotron","score":70.36},{"place":9,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":70.05},{"place":10,"model":"nemotron-research-goosereason-4b-instruct","company":"nvidia","family":"Nemotron Research","version":"Nemotron Research GooseReason","score":68.79},{"place":11,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":67.7},{"place":12,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":66.67},{"place":13,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.83},{"place":14,"model":"deepseek-r1-distill-32b","company":"deepseek","family":"DeepSeek-R1","version":"32B","score":65},{"place":15,"model":"nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":64.62},{"place":16,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":64.3},{"place":17,"model":"llada2.1-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":64.3},{"place":18,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":61.11},{"place":19,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.13},{"place":20,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":55.33},{"place":21,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":54.52},{"place":22,"model":"qwen2.5-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":49},{"place":23,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":47.89},{"place":24,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":47.78},{"place":25,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":43.3},{"place":26,"model":"skywork-o1-open-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-o1","score":43.1},{"place":27,"model":"qwen2-math-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":43},{"place":28,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.5},{"place":29,"model":"qwen2.5-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":41.6},{"place":30,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":41.27},{"place":31,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":40.1},{"place":32,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":39.85},{"place":33,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":39.56},{"place":34,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":39.31},{"place":35,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":39.31},{"place":36,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":38.7},{"place":37,"model":"qwen2-math-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":38.2},{"place":38,"model":"qwen2.5-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Math","score":38.1},{"place":39,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":37.8},{"place":40,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":35.7},{"place":41,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":35.09},{"place":42,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":34.34},{"place":43,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":33.2},{"place":44,"model":"numinamath-72b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":32.6},{"place":45,"model":"qwen2-math-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2-Math","score":31.3},{"place":46,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":29.8},{"place":47,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":27.7},{"place":48,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":26.4},{"place":49,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":25.9},{"place":50,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":25.9},{"place":51,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":24.1},{"place":52,"model":"qwen2.5-coder-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":23.6},{"place":53,"model":"internlm2-math-plus-20b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":23.1},{"place":54,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.84},{"place":55,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":21.5},{"place":56,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":21.3},{"place":57,"model":"qvq-72b","company":"qwen","family":"QvQ","version":"QvQ 72B","score":20.4},{"place":58,"model":"numinamath-7b-cot","company":"numina","family":"NuminaMath","version":"NuminaMath","score":19.9},{"place":59,"model":"deepseek-math-7b-rl","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":19},{"place":60,"model":"internlm2-math-plus-7b","company":"internlm","family":"InternLM","version":"InternLM2-Math-Plus","score":18.8},{"place":61,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":18},{"place":62,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":17.02},{"place":63,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":15.4},{"place":64,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":12.1},{"place":65,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":11.6},{"place":66,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":11.2},{"place":67,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":11.2},{"place":68,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":8.8},{"place":69,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":5.5},{"place":70,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":4.9},{"place":71,"model":"qwen2-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":4.1},{"place":72,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":3.9},{"place":73,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":3.5},{"place":74,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":3},{"place":75,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":2},{"place":76,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":1.9},{"place":77,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":1.7},{"place":78,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":1.1},{"place":79,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":0.6},{"place":80,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":0.4},{"place":81,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":0.3}]},{"id":"olympic-arena","name":"OlympicArena","topic":"Math (competition)","description":"Olympiad-style mathematics reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V3","top_percent":76.2,"top_model_id":"deepseek-v3","top_generation":"DeepSeek V3","top_model_base":"DeepSeek V3","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":76.2},{"place":2,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":75.3},{"place":3,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":69.5},{"place":4,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":63.7}]},{"id":"omega","name":"OMEGA","topic":"Math (advanced)","description":"OMEGA olympiad-grade mathematics reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OLMo-3.1-Think-32B","top_percent":53.4,"top_model_id":"olmo-3.1-think-32b","top_generation":"OLMo 3.1","top_model_base":"OLMo 3.1 Think 32B","top_model_family":"OLMo","top_company":"allenai","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":53.4},{"place":2,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":50.8},{"place":3,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":50.8},{"place":4,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.7},{"place":5,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":47.7},{"place":6,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":45.2},{"place":7,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":45},{"place":8,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44},{"place":9,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":43.4},{"place":10,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":43.2},{"place":11,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":43.1},{"place":12,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":42.4},{"place":13,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":42.2},{"place":14,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":40.5},{"place":15,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":38.9},{"place":16,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":38.4},{"place":17,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":38.1},{"place":18,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":37.8},{"place":19,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":35.1},{"place":20,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":33.3},{"place":21,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":32.3},{"place":22,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":28.9},{"place":23,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":28.5},{"place":24,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":24},{"place":25,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.4},{"place":26,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":22.8},{"place":27,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":20.5},{"place":28,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":19.5},{"place":29,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":19.2},{"place":30,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":16},{"place":31,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":15.5},{"place":32,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":14.4},{"place":33,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":13.7},{"place":34,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":10.7},{"place":35,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":9.8},{"place":36,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":9.1},{"place":37,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":5.6},{"place":38,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":5.2},{"place":39,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":5}]},{"id":"omni-math","name":"Omni-MATH","topic":"Math reasoning","description":"Omni-MATH benchmark covering diverse math reasoning tasks across difficulty levels.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ling 1T","top_percent":74.46,"top_model_id":"ling-1t","top_generation":"Ling 1T","top_model_base":"Ling 1T","top_model_family":"Ling","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":74.46},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.02},{"place":3,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":64.77},{"place":4,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":62.42},{"place":5,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":61.7},{"place":6,"model":"seed-oss-36b-instruct","company":"bytedance","family":"Seed","version":"Seed OSS","score":61.1},{"place":7,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":61.09},{"place":8,"model":"ring-flash-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":59.9},{"place":9,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.8},{"place":10,"model":"ring-flash-linear-2.0","company":"antgroup","family":"Ring","version":"Ring 2.0","score":56.6},{"place":11,"model":"qwen3-32b-thinking-2504","company":"qwen","family":"Qwen","version":"Qwen3","score":56.2},{"place":12,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":54.1},{"place":13,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":54},{"place":14,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":53},{"place":15,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":52.3},{"place":16,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":50.8},{"place":17,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":50.3},{"place":18,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":48.8},{"place":19,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":47.65},{"place":20,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":43.6},{"place":21,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":41.7},{"place":22,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":41.7},{"place":23,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":38.7},{"place":24,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.55},{"place":25,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":36.2},{"place":26,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":33.6},{"place":27,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":33.33},{"place":28,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":33.2},{"place":29,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":29.9},{"place":30,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":29.7},{"place":31,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":29.02},{"place":32,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":28.46},{"place":33,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":28.3},{"place":34,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":27.03},{"place":35,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.99},{"place":36,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.89}]},{"id":"omni-math-hard","name":"Omni-MATH-HARD","topic":"Math","description":"Challenging math benchmark (Omni-MATH-HARD).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":73.61,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":73.61},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.36},{"place":3,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":60.73},{"place":4,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":59.39},{"place":5,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":58.88},{"place":6,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":57.76},{"place":7,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.91},{"place":8,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":53.22},{"place":9,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":51.33},{"place":10,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":46.93},{"place":11,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":41.51},{"place":12,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.87},{"place":13,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.95},{"place":14,"model":"falcon-e-1b-base","company":"tii","family":"Falcon","version":"Falcon E","score":10.97},{"place":15,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.14},{"place":16,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.89},{"place":17,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":3.93},{"place":18,"model":"falcon-3-1b-base","company":"tii","family":"Falcon","version":"Falcon 3","score":3.32},{"place":19,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":2.64},{"place":20,"model":"smollm2-360m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":1.21}]},{"id":"omni3d","name":"Omni3D","topic":"3D detection","description":"Omni3D monocular 3D object detection benchmark across indoor/outdoor datasets (AP3D).","url":"https://github.com/facebookresearch/omni3d","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-4B","top_percent":47.4,"top_model_id":"qwen3.5-4b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.4},{"place":2,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":45.79},{"place":3,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":32.85},{"place":4,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":32.26}]},{"id":"omnidocbench","name":"OmniDocBench","topic":"Document understanding","description":"Document understanding benchmark covering multi-page layouts, tables, and charts for robust question answering. Overall score, higher is better (v1.0 edit-distance results are in omnidocbench-edit).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"PaddleOCR-VL-1.5","top_percent":94.5,"top_model_id":"paddleocr-vl-1.5","top_generation":"PaddleOCR-VL 1.5","top_model_base":"PaddleOCR-VL-1.5","top_model_family":"PaddleOCR","top_company":"paddlepaddle","top_open_source":1,"lower_is_better":false,"bench_models":57,"total_models":3854,"placements":[{"place":1,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":94.5},{"place":2,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":94.37},{"place":3,"model":"unlimited-ocr","company":"baidu","family":"Unlimited-OCR","version":"Unlimited-OCR","score":93.23},{"place":4,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":93.12},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":92.9},{"place":6,"model":"paddleocr-vl","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR","score":92.86},{"place":7,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":92.6},{"place":8,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":92.2},{"place":9,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":92.1},{"place":10,"model":"paddleocr-vl","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR","score":91.76},{"place":11,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":91.6},{"place":12,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":91.1},{"place":13,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":91.09},{"place":14,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":90.67},{"place":15,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90.33},{"place":16,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89.8},{"place":17,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":89.7},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":89.4},{"place":19,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":89.3},{"place":20,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":89.17},{"place":21,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.15},{"place":22,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":89},{"place":23,"model":"chandra-ocr-0.1.0","company":"chandra","family":"Chandra OCR","version":"Chandra OCR","score":88.97},{"place":24,"model":"monkeyocr-pro-3b","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCR Pro","score":88.85},{"place":25,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":88.8},{"place":26,"model":"falcon-ocr","company":"tii","family":"Falcon-OCR","version":"Falcon-OCR","score":88.64},{"place":27,"model":"ocrverse","company":"ocrverse","family":"OCRVerse","version":"OCRVerse","score":88.56},{"place":28,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88.5},{"place":29,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":88.41},{"place":30,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":88.1},{"place":31,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.03},{"place":32,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88},{"place":33,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":87.9},{"place":34,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.7},{"place":35,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":87.66},{"place":36,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":87.5},{"place":37,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":87.5},{"place":38,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":87.36},{"place":39,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":87.2},{"place":40,"model":"monkeyocr-3b","company":"monkeyocr","family":"MonkeyOCR","version":"MonkeyOCR","score":87.13},{"place":41,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87.02},{"place":42,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":87.01},{"place":43,"model":"monkeyocr-pro-1.2b","company":"monkeyocr","family":"MonkeyOCR","version":"MonkeyOCR","score":86.96},{"place":44,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86.9},{"place":45,"model":"pp-structurev3","company":"paddlepaddle","family":"PP-Structure","version":"PP-Structure V3","score":86.73},{"place":46,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":86.7},{"place":47,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.56},{"place":48,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":85.8},{"place":49,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":85.7},{"place":50,"model":"nanonets-ocr-s","company":"nanonets","family":"Nanonets OCR","version":"Nanonets OCR","score":85.59},{"place":51,"model":"mineru2-vlm","company":"opendatalab","family":"MinerU","version":"MinerU2","score":85.56},{"place":52,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":85.5},{"place":53,"model":"mistral-ocr-3","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":85.2},{"place":54,"model":"dolphin-1.5","company":"bytedance","family":"Dolphin","version":"Dolphin","score":83.21},{"place":55,"model":"internvl3.5-241b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":82.67},{"place":56,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82},{"place":57,"model":"olmocr","company":"allenai","family":"OLMOCR","version":"OLMOCR","score":81.79},{"place":58,"model":"points-reader","company":"whu","family":"POINTS","version":"POINTS","score":80.98},{"place":59,"model":"internvl3","company":"opengvlab","family":"Intern","version":"InternVL 3","score":80.33},{"place":60,"model":"mistral-ocr-api","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":78.83},{"place":61,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":76.9},{"place":62,"model":"mineru2-pp","company":"opendatalab","family":"MinerU","version":"MinerU2","score":75.51},{"place":63,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":75.02},{"place":64,"model":"ocrflux","company":"ocrflux","family":"OCRFlux","version":"OCRFlux","score":74.82},{"place":65,"model":"dolphin","company":"bytedance","family":"Dolphin","version":"Dolphin","score":74.67},{"place":66,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.1},{"place":67,"model":"mineru2-pp","company":"opendatalab","family":"MinerU","version":"MinerU2","score":71.51},{"place":68,"model":"marker-1.8.2","company":"datalab","family":"Marker","version":"Marker 1.8","score":71.3}]},{"id":"omnidocbench-1.5","name":"OmniDocBench 1.5","topic":"OCR","description":"Document understanding benchmark v1.5 with OCR evaluation. Overall Edit Distance metric, lower is better.","url":"","leaderboard":"","github":"","paper":"","metric":"edit_distance","stars":"","top_model":"PaddleOCR-VL","top_percent":0.024,"top_model_id":"paddleocr-vl","top_generation":"PaddleOCR","top_model_base":"PaddleOCR-VL","top_model_family":"PaddleOCR","top_company":"paddlepaddle","top_open_source":1,"lower_is_better":true,"bench_models":61,"total_models":3854,"placements":[{"place":1,"model":"paddleocr-vl","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR","score":0.024},{"place":2,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":0.025},{"place":3,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":0.037},{"place":4,"model":"chandra-ocr-0.1.0","company":"chandra","family":"Chandra OCR","version":"Chandra OCR","score":0.046},{"place":5,"model":"mistral-ocr-3","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":0.053},{"place":6,"model":"dolphin-v2","company":"bytedance","family":"Dolphin","version":"Dolphin V2","score":0.054},{"place":7,"model":"falcon-ocr","company":"tii","family":"Falcon-OCR","version":"Falcon-OCR","score":0.055},{"place":8,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":0.061},{"place":9,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":0.1},{"place":10,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":0.106},{"place":11,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":0.109},{"place":12,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":0.109},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":0.115},{"place":14,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":0.121},{"place":15,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":0.1263},{"place":16,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":0.129},{"place":17,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.131},{"place":18,"model":"gpt-5.2-none","company":"openai","family":"GPT","version":"GPT-5.2","score":0.14},{"place":19,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":0.143},{"place":20,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":0.145},{"place":21,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":0.145},{"place":22,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":0.145},{"place":23,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":0.145},{"place":24,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":0.147},{"place":25,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":0.147},{"place":26,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.149},{"place":27,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":0.152},{"place":28,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":0.154},{"place":29,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.164},{"place":30,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":0.1791},{"place":31,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.181},{"place":32,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":0.2419},{"place":33,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.29},{"place":34,"model":"diffusiongemma-26b-a4b","company":"google","family":"DiffusionGemma","version":"DiffusionGemma","score":0.319},{"place":35,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":0.365},{"place":36,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":55.9},{"place":37,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61},{"place":38,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.9},{"place":39,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.4},{"place":40,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":77},{"place":41,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.4},{"place":42,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.8},{"place":43,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80},{"place":44,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":80.1},{"place":45,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.5},{"place":46,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":85.5},{"place":47,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":85.7},{"place":48,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.8},{"place":49,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.2},{"place":50,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":86.5},{"place":51,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86.6},{"place":52,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":86.7},{"place":53,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.8},{"place":54,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.7},{"place":55,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.7},{"place":56,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88.5},{"place":57,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":88.8},{"place":58,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.9},{"place":59,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.3},{"place":60,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.4},{"place":61,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89.5},{"place":62,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.8},{"place":63,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.9},{"place":64,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":90},{"place":65,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.8},{"place":66,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":91.1},{"place":67,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":91.2},{"place":68,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":91.4},{"place":69,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":92.1}]},{"id":"omnidocbench-cn","name":"OmniDocBench-CN","topic":"Document understanding (Chinese)","description":"Chinese subset of OmniDocBench focusing on OCR-grounded document comprehension and reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"PP-StructureV3","top_percent":13.6,"top_model_id":"pp-structurev3","top_generation":"PP-Structure V3","top_model_base":"PP-Structure","top_model_family":"PP-Structure","top_company":"paddlepaddle","top_open_source":1,"lower_is_better":true,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"pp-structurev3","company":"paddlepaddle","family":"PP-Structure","version":"PP-Structure V3","score":13.6},{"place":2,"model":"gundam-m","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":15.7},{"place":3,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":16},{"place":4,"model":"gundam","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":18.1},{"place":5,"model":"deepseek-ocr-large","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":20.8},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.2},{"place":7,"model":"mineru2.0","company":"opendatalab","family":"MinerU","version":"MinerU","score":23.8},{"place":8,"model":"deepseek-ocr-base","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":24},{"place":9,"model":"mineru-2.1.1","company":"opendatalab","family":"MinerU","version":"MinerU","score":24.4},{"place":10,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":26.1},{"place":11,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":26.1},{"place":12,"model":"monkeyocr-1.2b","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCR","score":26.3},{"place":13,"model":"deepseek-ocr-small","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":28.4},{"place":14,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":29.6},{"place":15,"model":"ocrflux-3b","company":"chatdoc","family":"OCRFlux","version":"OCRFlux","score":34.9},{"place":16,"model":"deepseek-ocr-tiny","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":36.1},{"place":17,"model":"mathpix","company":"mathpix","family":"Mathpix","version":"Mathpix","score":36.4},{"place":18,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":39.9},{"place":19,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":39.9},{"place":20,"model":"got-ocr2.0","company":"stepfun","family":"GOT-OCR","version":"GOT-OCR","score":41.1},{"place":21,"model":"dolphin","company":"bytedance","family":"Dolphin","version":"Dolphin","score":44},{"place":22,"model":"internvl2-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":44.3},{"place":23,"model":"olmocr","company":"allenai","family":"OLMOCR","version":"OLMOCR","score":46.9},{"place":24,"model":"marker","company":"datalab","family":"Marker","version":"Marker","score":49.7},{"place":25,"model":"smoldocling","company":"IBM","family":"Docling","version":"SMoLDocling","score":81.6},{"place":26,"model":"nougat","company":"meta","family":"Nougat","version":"Nougat","score":97.3}]},{"id":"omnidocbench-edit","name":"OmniDocBench (Edit Distance)","topic":"Document understanding","description":"OmniDocBench v1.0 overall normalized edit distance (x100), lower is better.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gundam-M","top_percent":12.3,"top_model_id":"gundam-m","top_generation":"DeepSeek OCR","top_model_base":"DeepSeek-OCR Gundam-M","top_model_family":"DeepSeek OCR","top_company":"deepseek","top_open_source":1,"lower_is_better":true,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"gundam-m","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":12.3},{"place":2,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":12.5},{"place":3,"model":"gundam","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":12.7},{"place":4,"model":"mineru2.0","company":"opendatalab","family":"MinerU","version":"MinerU","score":13.3},{"place":5,"model":"deepseek-ocr-base","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":13.7},{"place":6,"model":"deepseek-ocr-large","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":13.8},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":14.8},{"place":8,"model":"pp-structurev3","company":"paddlepaddle","family":"PP-Structure","version":"PP-Structure V3","score":15.2},{"place":9,"model":"monkeyocr-1.2b","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCR","score":15.4},{"place":10,"model":"mineru-2.1.1","company":"opendatalab","family":"MinerU","version":"MinerU","score":16.2},{"place":11,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":18.2},{"place":12,"model":"mathpix","company":"mathpix","family":"Mathpix","version":"Mathpix","score":19.1},{"place":13,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":21.4},{"place":14,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":21.8},{"place":15,"model":"deepseek-ocr-small","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":22.1},{"place":16,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":23.3},{"place":17,"model":"ocrflux-3b","company":"chatdoc","family":"OCRFlux","version":"OCRFlux","score":23.8},{"place":18,"model":"got-ocr2.0","company":"stepfun","family":"GOT-OCR","version":"GOT-OCR","score":28.7},{"place":19,"model":"marker","company":"datalab","family":"Marker","version":"Marker","score":29.6},{"place":20,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":31.6},{"place":21,"model":"olmocr","company":"allenai","family":"OLMOCR","version":"OLMOCR","score":32.6},{"place":22,"model":"dolphin","company":"bytedance","family":"Dolphin","version":"Dolphin","score":35.6},{"place":23,"model":"deepseek-ocr-tiny","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":38.6},{"place":24,"model":"internvl2-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":44},{"place":25,"model":"nougat","company":"meta","family":"Nougat","version":"Nougat","score":45.2},{"place":26,"model":"smoldocling","company":"IBM","family":"Docling","version":"SMoLDocling","score":49.3}]},{"id":"omnidocbench-v1.6","name":"OmniDocBench v1.6","topic":"Document parsing","description":"OmniDocBench v1.6 end-to-end document parsing; Overall score (higher is better) combining text edit, formula CDM and table TEDS.","url":"https://github.com/opendatalab/OmniDocBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Youtu-Parsing-Omni","top_percent":96.96,"top_model_id":"youtu-parsing-omni","top_generation":"Youtu-Parsing-Omni","top_model_base":"Youtu-Parsing-Omni","top_model_family":"Youtu-Parsing","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":42,"total_models":3854,"placements":[{"place":1,"model":"youtu-parsing-omni","company":"tencent","family":"Youtu-Parsing","version":"Youtu-Parsing-Omni","score":96.96},{"place":2,"model":"teleocr","company":"teleai","family":"TeleOCR","version":"TeleOCR","score":96.91},{"place":3,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":96.83},{"place":4,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":96.74},{"place":5,"model":"ovisocr2","company":"alibaba","family":"Ovis","version":"OvisOCR2","score":96.58},{"place":6,"model":"ovisocr2","company":"alibaba","family":"Ovis","version":"OvisOCR2","score":96.47},{"place":7,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":96.34},{"place":8,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":96.33},{"place":9,"model":"mineru2.5-pro","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":95.75},{"place":10,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":95.22},{"place":11,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":94.93},{"place":12,"model":"hpd-parsing","company":"paddlepaddle","family":"HPD-Parsing","version":"HPD-Parsing","score":94.91},{"place":13,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":94.87},{"place":14,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":94.74},{"place":15,"model":"paddleocr-vl","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR","score":94.18},{"place":16,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":93.95},{"place":17,"model":"unlimited-ocr","company":"baidu","family":"Unlimited-OCR","version":"Unlimited-OCR","score":93.92},{"place":18,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":93.9},{"place":19,"model":"youtu-parsing","company":"tencent","family":"Youtu-Parsing","version":"Youtu-Parsing","score":93.74},{"place":20,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":93.7},{"place":21,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93.7},{"place":22,"model":"logics-parsing-v2","company":"alibaba","family":"Logics-Parsing","version":"Logics-Parsing v2","score":93.33},{"place":23,"model":"firered-ocr","company":"rednote","family":"FireRed-OCR","version":"FireRed-OCR","score":93.26},{"place":24,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":93.04},{"place":25,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":92.98},{"place":26,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":92.91},{"place":27,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":92.85},{"place":28,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":92.62},{"place":29,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":91.98},{"place":30,"model":"monkeyocrv2-b-parsing","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCRv2","score":91.57},{"place":31,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.27},{"place":32,"model":"jina-ocr-v1","company":"jina","family":"jina-ocr","version":"jina-ocr-v1","score":91.14},{"place":33,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":90.77},{"place":34,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":90.25},{"place":35,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":90.17},{"place":36,"model":"hunyuanocr","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR","score":89.95},{"place":37,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.78},{"place":38,"model":"dolphin-v2","company":"bytedance","family":"Dolphin","version":"Dolphin V2","score":89.5},{"place":39,"model":"ocrverse","company":"ocrverse","family":"OCRVerse","version":"OCRVerse","score":88.6},{"place":40,"model":"monkeyocr-pro-3b","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCR Pro","score":88.57},{"place":41,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86.59},{"place":42,"model":"dolphin-1.5","company":"bytedance","family":"Dolphin","version":"Dolphin","score":86.52},{"place":43,"model":"olmocr","company":"allenai","family":"OLMOCR","version":"OLMOCR","score":85.74},{"place":44,"model":"mistral-ocr-api","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":85.66},{"place":45,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.53},{"place":46,"model":"internvl3.5-241b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":83.76},{"place":47,"model":"nanonets-ocr-s","company":"nanonets","family":"Nanonets OCR","version":"Nanonets OCR","score":83.61},{"place":48,"model":"points-reader","company":"whu","family":"POINTS","version":"POINTS","score":83.37}]},{"id":"omnigaia","name":"OmniGAIA","topic":"Multimodal agent","description":"OmniGAIA: GAIA-style omni-modal (image/video/audio) agentic perception and reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":62.5,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.5},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.7},{"place":3,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":58.3},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":51.7},{"place":5,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":49.8}]},{"id":"omnimedvqa","name":"OmniMedVQA","topic":"Medical QA","description":"Large-scale medical VQA across 12 imaging modalities.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedMO-8B-Next","top_percent":93.3,"top_model_id":"medmo-8b-next","top_generation":"MedMO-Next","top_model_base":"MedMO","top_model_family":"MedMO","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":93.3},{"place":2,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":90.6},{"place":3,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":88.2},{"place":4,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":84.8},{"place":5,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":82.9},{"place":6,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":79.7},{"place":7,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":73.8}]},{"id":"omnimmi","name":"OmniMMI","topic":"Multimodal interaction","description":"OmniMMI benchmark for multimodal interaction across video streams.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":53,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":53},{"place":2,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":49.5}]},{"id":"omnispatial","name":"OmniSpatial","topic":"Spatial reasoning","description":"Spatial understanding and reasoning benchmark (OmniSpatial).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-4.6V","top_percent":52,"top_model_id":"glm-4.6v","top_generation":"GLM 4.6V","top_model_base":"GLM 4.6V","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":52},{"place":2,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":51},{"place":3,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":50.6},{"place":4,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":47.7},{"place":5,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":47},{"place":6,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":40.8},{"place":7,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":40.8},{"place":8,"model":"kimi-vl","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":37.3},{"place":9,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":37.3}]},{"id":"oneig-bench-en","name":"OneIG-Bench EN","topic":"Text-to-image","description":"OneIG-Bench English subset score for text-to-image generation.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Nano Banana 2.0","top_percent":0.578,"top_model_id":"nano-banana-2.0","top_generation":"Nano Banana","top_model_base":"Nano Banana 2.0","top_model_family":"Nano Banana","top_company":"unknown","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":0.578},{"place":2,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":0.576},{"place":3,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":0.576},{"place":4,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":0.546},{"place":5,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.539},{"place":6,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":0.533},{"place":7,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.53},{"place":8,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":0.528},{"place":9,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":0.528},{"place":10,"model":"flux-1-dev","company":"black-forest-labs","family":"FLUX.1","version":"FLUX.1","score":0.434},{"place":11,"model":"bagel","company":"jondurbin","family":"Bagel","version":"Bagel","score":0.361},{"place":12,"model":"sd-xl","company":"stabilityai","family":"Stable Diffusion","version":"SD XL","score":0.316},{"place":13,"model":"show-o2","company":"unknown","family":"Show-o","version":"Show-o2","score":0.308},{"place":14,"model":"janus-pro","company":"bytedance","family":"Janus","version":"Janus Pro","score":0.267}]},{"id":"oneig-bench-zh","name":"OneIG-Bench ZH","topic":"Text-to-image","description":"OneIG-Bench Chinese subset score for text-to-image generation.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Nano Banana 2.0","top_percent":0.567,"top_model_id":"nano-banana-2.0","top_generation":"Nano Banana","top_model_base":"Nano Banana 2.0","top_model_family":"Nano Banana","top_company":"unknown","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":0.567},{"place":2,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":0.553},{"place":3,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":0.551},{"place":4,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.548},{"place":5,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":0.535},{"place":6,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":0.515},{"place":7,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":0.511},{"place":8,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":0.507},{"place":9,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":0.474},{"place":10,"model":"bagel","company":"jondurbin","family":"Bagel","version":"Bagel","score":0.37},{"place":11,"model":"janus-pro","company":"bytedance","family":"Janus","version":"Janus Pro","score":0.24}]},{"id":"onemillionbench","name":"OneMillionBench","topic":"Agentic search / expert tasks","description":"OneMillion Bench: expert-level, economically valuable tasks evaluated with tools (search).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":73,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":73},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69.6},{"place":3,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":68.8},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68.1},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":67.1},{"place":6,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":66.6},{"place":7,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":65.4},{"place":8,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":64.5},{"place":9,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":63.5},{"place":10,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":63.1},{"place":11,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62},{"place":12,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":60.2},{"place":13,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":51.5}]},{"id":"online-mind2web","name":"Online-Mind2web","topic":"Web automation","description":"Online web automation and task execution benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.4","top_percent":92.8,"top_model_id":"gpt-5.4","top_generation":"GPT-5.4","top_model_base":"GPT-5.4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":92.8},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":85.9},{"place":3,"model":"ui-venus-2-27b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":78.3},{"place":4,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":76.4},{"place":5,"model":"ui-venus-2-9b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":74},{"place":6,"model":"fara1.5-27b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":72.3},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69},{"place":8,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":68.5},{"place":9,"model":"fara1.5-9b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":63.4},{"place":10,"model":"gpt-03-cua","company":"openai","family":"o3","version":"o3","score":61.3},{"place":11,"model":"fara1.5-4b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":57.3},{"place":12,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":55.3},{"place":13,"model":"molmoweb-8b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":35.3},{"place":14,"model":"fara-7b","company":"microsoft","family":"Fara","version":"Fara","score":34.1},{"place":15,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":33.9},{"place":16,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":31.3},{"place":17,"model":"molmoweb-4b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":31.3},{"place":18,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.3}]},{"id":"open-rewrite","name":"Open Rewrite","topic":"Instruction following","description":"Rewrite benchmark assessing open-ended editing and directive-following quality.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MobileLLM P1","top_percent":51,"top_model_id":"mobilellm-p1","top_generation":"MobileLLM","top_model_base":"MobileLLM P1","top_model_family":"MobileLLM","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":51},{"place":2,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":41.6}]},{"id":"openai-internal-advanced-cyber-completion-rate","name":"OpenAI Internal Advanced Cybersecurity Completion Rate","topic":"Cybersecurity","description":"OpenAI internal eval (Daybreak announcement): share of advanced, dual-use cybersecurity requests (exploit chains, auth bypass, privilege escalation) the model completes.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Cyber","top_percent":95,"top_model_id":"gpt-5.6-cyber","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Cyber","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-cyber","company":"openai","family":"GPT","version":"GPT-5.6","score":95},{"place":2,"model":"gpt-5.5-cyber","company":"openai","family":"GPT","version":"GPT-5.5","score":57.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":2}]},{"id":"openai-internal-agentic-safe-completions-chat-prod-chat-plugins","name":"OpenAI Agentic Safe Completions: Chat prod - Chat Plugins","topic":"Safety","description":"OpenAI system-card agentic safe-completion evaluation, 'Chat prod - Chat Plugins' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":100,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":100},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":100},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":92.3},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":92.3},{"place":6,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":84.6}]},{"id":"openai-internal-agentic-safe-completions-codex-prod-age-restricted-actions","name":"OpenAI Agentic Safe Completions: Codex prod - Age-restricted actions","topic":"Safety","description":"OpenAI system-card agentic safe-completion evaluation, 'Codex prod - Age-restricted actions' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":83,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":83},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":82.1},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":81.1},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":75.5},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":68.7},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":60.3}]},{"id":"openai-internal-agentic-safe-completions-codex-prod-non-violent-wrongdoing","name":"OpenAI Agentic Safe Completions: Codex prod - Non-violent Wrongdoing","topic":"Safety","description":"OpenAI system-card agentic safe-completion evaluation, 'Codex prod - Non-violent Wrongdoing' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna","top_percent":100,"top_model_id":"gpt-6-luna","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.9},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":97.8},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":95.4},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":90.6}]},{"id":"openai-internal-agentic-safe-completions-codex-prod-self-harm","name":"OpenAI Agentic Safe Completions: Codex prod - Self-harm","topic":"Safety","description":"OpenAI system-card agentic safe-completion evaluation, 'Codex prod - Self-harm' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna","top_percent":96,"top_model_id":"gpt-6-luna","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":96},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":92},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":92},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":92},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":92},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":89.3}]},{"id":"openai-internal-agentic-safe-completions-codex-prod-sensitive-personal-data","name":"OpenAI Agentic Safe Completions: Codex prod - Sensitive personal data","topic":"Safety","description":"OpenAI system-card agentic safe-completion evaluation, 'Codex prod - Sensitive personal data' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":85.4,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":85.4},{"place":2,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":79.5},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":76.5},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":76.3},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":74.7},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":74.4}]},{"id":"openai-internal-agentic-safe-completions-codex-prod-violent-wrongdoing","name":"OpenAI Agentic Safe Completions: Codex prod - Violent Wrongdoing","topic":"Safety","description":"OpenAI system-card agentic safe-completion evaluation, 'Codex prod - Violent Wrongdoing' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":92.6,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":92.6},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":90.7},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":88.9},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":88.7},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":79.6},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":68.9}]},{"id":"openai-internal-agentic-safe-completions-human-red-teaming-chat-plugins","name":"OpenAI Agentic Safe Completions: Human red-teaming - Chat Plugins","topic":"Safety","description":"OpenAI system-card agentic safe-completion evaluation, 'Human red-teaming - Chat Plugins' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":100,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":95.5},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":93.6},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":93.5},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":81.4},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":76.6}]},{"id":"openai-internal-agentic-safe-completions-human-red-teaming-codex","name":"OpenAI Agentic Safe Completions: Human red-teaming - Codex","topic":"Safety","description":"OpenAI system-card agentic safe-completion evaluation, 'Human red-teaming - Codex' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":97.8,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":97.8},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97.7},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":95.8},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":95.7},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":93.5},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":85.1}]},{"id":"openai-internal-bio-refusal-benign","name":"OpenAI Biology Model Refusal: Benign","topic":"Safety","description":"OpenAI system-card biology refusal evaluation, 'Benign' prompts (higher is better: safe for Severe/Dual Use, not over-refusing for Benign).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":98.9,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.9},{"place":2,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":98.9},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.2},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":98.2},{"place":5,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":97.8},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97.8},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":96.4},{"place":8,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":95.8},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":91.7}]},{"id":"openai-internal-bio-refusal-dual-use","name":"OpenAI Biology Model Refusal: Dual Use","topic":"Safety","description":"OpenAI system-card biology refusal evaluation, 'Dual Use' prompts (higher is better: safe for Severe/Dual Use, not over-refusing for Benign).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":98,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":98},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98},{"place":3,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":97.1},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97},{"place":5,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":96.8},{"place":6,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":96.2},{"place":7,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":96},{"place":8,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":95.7},{"place":9,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":94.5},{"place":10,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":93.9},{"place":11,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":92.8},{"place":12,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":92.6},{"place":13,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":92.6},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":91.1},{"place":15,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":91.1}]},{"id":"openai-internal-bio-refusal-severe","name":"OpenAI Biology Model Refusal: Severe","topic":"Safety","description":"OpenAI system-card biology refusal evaluation, 'Severe' prompts (higher is better: safe for Severe/Dual Use, not over-refusing for Benign).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":99.8,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.8},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.8},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.8},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":99},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":98.5},{"place":6,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":98},{"place":7,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":96.9},{"place":8,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":96.9},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95.8},{"place":10,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":95.4},{"place":11,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":95},{"place":12,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":94.6},{"place":13,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":94.5},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":94.3},{"place":15,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":93.7}]},{"id":"openai-internal-blocker-deception","name":"OpenAI Internal Blocker Deception","topic":"Safety","description":"OpenAI alignment eval: rate of failing to accurately disclose a task blocker in the final answer (lower is better). Replaces Coding Deception.","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":8.05,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":8.05},{"place":2,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":8.36},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":8.47},{"place":4,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":11.3},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":11.66},{"place":6,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":13.3},{"place":7,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":14},{"place":8,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":23.8},{"place":9,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":27.8},{"place":10,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":28.99},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":34.18}]},{"id":"openai-internal-broken-search-nondisclosure","name":"OpenAI Internal Broken Search Tool Non-Disclosure","topic":"Safety","description":"OpenAI internal alignment eval: rate of failing to disclose a broken search tool (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":1.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":1.5},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":1.83},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":2.08},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":2.1},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":4.9},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":4.92},{"place":7,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":28.67},{"place":8,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":28.7},{"place":9,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":66.42},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.46},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.5},{"place":12,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":78.25},{"place":13,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":78.3}]},{"id":"openai-internal-challenging-prompts-extremism","name":"OpenAI Production Benchmarks (Challenging Prompts): Extremism","topic":"Safety","description":"OpenAI system-card production benchmark with challenging prompts, 'Extremism' category: share of safe (not unsafe) completions (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Luna","top_percent":98.1,"top_model_id":"gpt-5.6-luna","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":98.1},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":98.1},{"place":3,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":97.9},{"place":4,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":97.9},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97.9},{"place":6,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":97.9},{"place":7,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":97.9},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":96.2},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95.7},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":95.7},{"place":11,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":95.7},{"place":12,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":94.3},{"place":13,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":93.6},{"place":14,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":93.6},{"place":15,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":93.6},{"place":16,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":93.6},{"place":17,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":92.5},{"place":18,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":91.5},{"place":19,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":91.5},{"place":20,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":89.4}]},{"id":"openai-internal-challenging-prompts-gore","name":"OpenAI Production Benchmarks (Challenging Prompts): Gore","topic":"Safety","description":"OpenAI system-card production benchmark with challenging prompts, 'Gore' category: share of safe (not unsafe) completions (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":90,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":90},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":89.8},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":88.9},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":88.3},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":87.6},{"place":6,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":87.2},{"place":7,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":86.7},{"place":8,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":86.5},{"place":9,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":84.5},{"place":10,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":84.5},{"place":11,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":83.2},{"place":12,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":82.3},{"place":13,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":81.9},{"place":14,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":81.2},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":80.3},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":78.5},{"place":17,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":58.5}]},{"id":"openai-internal-challenging-prompts-hate","name":"OpenAI Production Benchmarks (Challenging Prompts): Hate","topic":"Safety","description":"OpenAI system-card production benchmark with challenging prompts, 'Hate' category: share of safe (not unsafe) completions (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":100,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":100},{"place":2,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":100},{"place":3,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":100},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":100},{"place":7,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":100},{"place":8,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":100},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.2},{"place":10,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":98.2},{"place":11,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":98.2},{"place":12,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.2},{"place":13,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":96.5},{"place":14,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":96.5},{"place":15,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":96.5},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":96.5}]},{"id":"openai-internal-challenging-prompts-non-violent-illicit-behavior","name":"OpenAI Production Benchmarks (Challenging Prompts): Non-Violent Illicit behavior","topic":"Safety","description":"OpenAI system-card production benchmark with challenging prompts, 'Non-Violent Illicit behavior' category: share of safe (not unsafe) completions (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":100,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":100},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.7},{"place":3,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":99.7},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":99.7},{"place":5,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":99.7},{"place":6,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":99.3},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.3},{"place":8,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":99},{"place":9,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":99},{"place":10,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":99},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98.7},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.7},{"place":13,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":98.7},{"place":14,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":98.4},{"place":15,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":98.4},{"place":16,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":98}]},{"id":"openai-internal-challenging-prompts-self-harm-standard","name":"OpenAI Production Benchmarks (Challenging Prompts): Self-harm (standard)","topic":"Safety","description":"OpenAI system-card production benchmark with challenging prompts, 'Self-harm (standard)' category: share of safe (not unsafe) completions (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":99.4,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.4},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.2},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":98.6},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":98.4},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":97.4},{"place":6,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":96.2},{"place":7,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":95.9},{"place":8,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":95.4},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":94.5},{"place":10,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":93.7},{"place":11,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":93.4},{"place":12,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":93.2},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":91.7},{"place":14,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":90.1},{"place":15,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":89.6},{"place":16,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":87.5}]},{"id":"openai-internal-challenging-prompts-sexual","name":"OpenAI Production Benchmarks (Challenging Prompts): Sexual","topic":"Safety","description":"OpenAI system-card production benchmark with challenging prompts, 'Sexual' category: share of safe (not unsafe) completions (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":98.7,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.7},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":98.4},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":98},{"place":4,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":97.7},{"place":5,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":97.1},{"place":6,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":96.2},{"place":7,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":96.1},{"place":8,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":95.1},{"place":9,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":95.1},{"place":10,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":94.4},{"place":11,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":94.4},{"place":12,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":93.2},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":91.9},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":91.5},{"place":15,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":90.9},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":89.9},{"place":17,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":89.3}]},{"id":"openai-internal-challenging-prompts-sexual-minors","name":"OpenAI Production Benchmarks (Challenging Prompts): Sexual/minors","topic":"Safety","description":"OpenAI system-card production benchmark with challenging prompts, 'Sexual/minors' category: share of safe (not unsafe) completions (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":99.1,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.1},{"place":2,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":99.1},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.3},{"place":4,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":97.4},{"place":5,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":97.4},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97.4},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":97.3},{"place":8,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":96.6},{"place":9,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":96.5},{"place":10,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":96.5},{"place":11,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":94.7},{"place":12,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":93.9},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":93.8},{"place":14,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":92.2},{"place":15,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":88.7},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":82.9}]},{"id":"openai-internal-challenging-prompts-violent-illicit-behavior","name":"OpenAI Production Benchmarks (Challenging Prompts): Violent Illicit behavior","topic":"Safety","description":"OpenAI system-card production benchmark with challenging prompts, 'Violent Illicit behavior' category: share of safe (not unsafe) completions (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":99,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":98.8},{"place":3,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":98.6},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.3},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":97.7},{"place":6,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":96.7},{"place":7,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":96.1},{"place":8,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":95.9},{"place":9,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":95.9},{"place":10,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":95.9},{"place":11,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":95.7},{"place":12,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":95.2},{"place":13,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":94.8},{"place":14,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":94},{"place":15,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":94},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":93.4}]},{"id":"openai-internal-circumvention","name":"OpenAI Internal Circumvention","topic":"Safety","description":"OpenAI internal eval reported in the GPT-6 Astra announcement: rate of circumventing safeguards (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.29}]},{"id":"openai-internal-codex-eval-awareness","name":"OpenAI Codex Deployment Simulation: Eval Awareness","topic":"Safety","description":"Rate of evaluation or simulation awareness detected in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":2.47,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":2.47},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":2.52},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":4.35},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":4.54},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":4.7},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":4.81},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":8.07},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":8.67},{"place":9,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":9.88}]},{"id":"openai-internal-codex-sev1-2-circumventing-restrictions","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Circumventing restrictions","topic":"Safety","description":"Severity 1-2 'Circumventing restrictions' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0.207,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.207},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.209},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.212},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.222},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.377},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.382},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.56},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.563}]},{"id":"openai-internal-codex-sev1-2-concealing-uncertainty","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Concealing uncertainty","topic":"Safety","description":"Severity 1-2 'Concealing uncertainty' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0.335,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.335},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.369},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.411},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.429},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.429},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.713},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.717},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":2.415},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":2.467}]},{"id":"openai-internal-codex-sev1-2-credential-harvesting","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Credential harvesting","topic":"Safety","description":"Severity 1-2 'Credential harvesting' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":0.012,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.012},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.025},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.026},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.049},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.05},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.051},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.053},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.054}]},{"id":"openai-internal-codex-sev1-2-deception","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Deception","topic":"Safety","description":"Severity 1-2 'Deception' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Terra","top_percent":0.06,"top_model_id":"gpt-6.1-terra","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.06},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.127},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.129},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.129},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.133},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.135},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.423},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.453}]},{"id":"openai-internal-codex-sev1-2-destructive-action","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Destructive action","topic":"Safety","description":"Severity 1-2 'Destructive action' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0.076,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.076},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.083},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.097},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.099},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.129},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.15},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.161},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.224},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.228}]},{"id":"openai-internal-codex-sev1-2-exfiltration","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Exfiltration","topic":"Safety","description":"Severity 1-2 'Exfiltration' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0.016,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.016},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.026},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.027},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.064},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.066},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.142},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.435},{"place":8,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.442}]},{"id":"openai-internal-codex-sev1-2-ignoring-instructions","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Ignoring instructions","topic":"Safety","description":"Severity 1-2 'Ignoring instructions' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Terra","top_percent":11.803,"top_model_id":"gpt-6.1-terra","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":11.803},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":12.645},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":12.665},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":12.717},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":12.744},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":12.758},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":12.777},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":15.354},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":15.396}]},{"id":"openai-internal-codex-sev1-2-inbound-prompt-injection","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Inbound prompt injection","topic":"Safety","description":"Severity 1-2 'Inbound prompt injection' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":0.004,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.004},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.006},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.008},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.01},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.01},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.021}]},{"id":"openai-internal-codex-sev1-2-other-misalignment","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Other misalignment","topic":"Safety","description":"Severity 1-2 'Other misalignment' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":0.15,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.15},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.165},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.17},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.173},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.173},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.175},{"place":7,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.201},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.24},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.248}]},{"id":"openai-internal-codex-sev1-2-reward-hacking","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Reward hacking","topic":"Safety","description":"Severity 1-2 'Reward hacking' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Terra","top_percent":0.033,"top_model_id":"gpt-6.1-terra","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.033},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.068},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.075},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.141},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.142},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.151},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.152},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.191},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.195}]},{"id":"openai-internal-codex-sev1-2-sandbagging","name":"OpenAI Codex Deployment Simulation: Severity 1-2 Sandbagging","topic":"Safety","description":"Severity 1-2 'Sandbagging' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":0.002,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.002},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.006},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.01},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.014},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.016},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.018}]},{"id":"openai-internal-codex-sev3-circumventing-restrictions","name":"OpenAI Codex Deployment Simulation: Severity 3+ Circumventing restrictions","topic":"Safety","description":"Severity 3+ 'Circumventing restrictions' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0.0242,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0242},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0246},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.0246},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.0302},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.0308},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.0452},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.0483},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0657},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0665}]},{"id":"openai-internal-codex-sev3-credential-harvesting","name":"OpenAI Codex Deployment Simulation: Severity 3+ Credential harvesting","topic":"Safety","description":"Severity 3+ 'Credential harvesting' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":0,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.002},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0021}]},{"id":"openai-internal-codex-sev3-destructive-action","name":"OpenAI Codex Deployment Simulation: Severity 3+ Destructive action","topic":"Safety","description":"Severity 3+ 'Destructive action' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":0,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.002},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.0021},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.004},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0041},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0181},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0185}]},{"id":"openai-internal-codex-sev3-exfiltration","name":"OpenAI Codex Deployment Simulation: Severity 3+ Exfiltration","topic":"Safety","description":"Severity 3+ 'Exfiltration' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":0.0101,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.0101},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0101},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.0103},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0103},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.0123},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.0141},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0144},{"place":8,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.0144},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0161}]},{"id":"openai-internal-codex-sev3-misalignment","name":"OpenAI Codex Deployment Simulation: Severity 3+ Misalignment","topic":"Safety","description":"Severity-3+ misalignment flag rate in a deployment simulation of internal Codex traffic, all shared cases (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Terra","top_percent":0.045,"top_model_id":"gpt-6.1-terra","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.045},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.049},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.053},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.054},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.056},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.078},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.085},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.125},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.127}]},{"id":"openai-internal-codex-sev3-misalignment-unaware","name":"OpenAI Codex Deployment Simulation: Severity 3+ Misalignment (no eval awareness)","topic":"Safety","description":"Severity-3+ misalignment flag rate in internal Codex deployment simulation, cases where eval awareness was not detected in any replay (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":0.036,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.036},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.036},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.041},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.043},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.064},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.067},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.103},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.107}]},{"id":"openai-internal-codex-sev3-other-misalignment","name":"OpenAI Codex Deployment Simulation: Severity 3+ Other misalignment","topic":"Safety","description":"Severity 3+ 'Other misalignment' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":0.0041,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.0041},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.006},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.0082},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0101},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0103},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0161},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0164},{"place":8,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.0181},{"place":9,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.0185}]},{"id":"openai-internal-codex-sev3-outbound-prompt-injection","name":"OpenAI Codex Deployment Simulation: Severity 3+ Outbound prompt injection","topic":"Safety","description":"Severity 3+ 'Outbound prompt injection' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":0,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.002},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.0021},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.004},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0041}]},{"id":"openai-internal-codex-sev3-reward-hacking","name":"OpenAI Codex Deployment Simulation: Severity 3+ Reward hacking","topic":"Safety","description":"Severity 3+ 'Reward hacking' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.002},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.0021},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.004},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0041},{"place":8,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.006},{"place":9,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.006}]},{"id":"openai-internal-codex-sev3-sabotage","name":"OpenAI Codex Deployment Simulation: Severity 3+ Sabotage","topic":"Safety","description":"Severity 3+ 'Sabotage' flag rate in OpenAI's deployment simulation of internal Codex traffic (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol","top_percent":0,"top_model_id":"gpt-6-sol","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.002},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.0021}]},{"id":"openai-internal-coding-deception","name":"OpenAI Internal Coding Deception","topic":"Safety","description":"OpenAI internal alignment eval: fraction of coding-agent answers with detected deception (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.5},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.51},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":1.3},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":1.5},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":2.8},{"place":6,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":2.81},{"place":7,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":9.5},{"place":8,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":9.54},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":10.4},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":10.41}]},{"id":"openai-internal-cua-safety","name":"OpenAI Internal Computer-Use Safety","topic":"Safety","description":"OpenAI internal eval reported in the GPT-6 Astra announcement: rate of unsafe actions during computer use (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":2.4,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":2.4},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":4.3},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":9.5},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":11.5},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":13.7},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":17.4},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":18.3},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":22}]},{"id":"openai-internal-cua-safety-autoreview","name":"OpenAI Internal Computer-Use Safety (AutoReview)","topic":"Safety","description":"OpenAI internal eval reported in the GPT-6 Astra announcement: unsafe computer-use action rate with AutoReview enabled (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":1.8,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":1.8},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":4.3}]},{"id":"openai-internal-cyber-safety-production-chat","name":"OpenAI Cybersecurity Safety: Production Chat","topic":"Safety","description":"OpenAI system-card cybersecurity safety evaluation, 'Production Chat' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Terra","top_percent":98.7,"top_model_id":"gpt-5.6-terra","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":98.7},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.7},{"place":3,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":98.6},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.3},{"place":5,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.2},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":98},{"place":7,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":97.7},{"place":8,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":97.4},{"place":9,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":97.4},{"place":10,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":97.3},{"place":11,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":97.1},{"place":12,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97},{"place":13,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":95.7},{"place":14,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":95.1},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":92.8}]},{"id":"openai-internal-cyber-safety-semi-synthetic-agentic-envs","name":"OpenAI Cybersecurity Safety: Semi-Synthetic Agentic Envs","topic":"Safety","description":"OpenAI system-card cybersecurity safety evaluation, 'Semi-Synthetic Agentic Envs' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":99.7,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.7},{"place":2,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":98.7},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.5},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":98.4},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":97.3},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":96.3}]},{"id":"openai-internal-cyber-safety-synthetic-agentic-envs","name":"OpenAI Cybersecurity Safety: Synthetic Agentic Envs","topic":"Safety","description":"OpenAI system-card cybersecurity safety evaluation, 'Synthetic Agentic Envs' (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Luna","top_percent":100,"top_model_id":"gpt-5.6-luna","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":100},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":100},{"place":3,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":99.9},{"place":4,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":99.9},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":99.8},{"place":6,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":99.8},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.8},{"place":8,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":99.8},{"place":9,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":99.8},{"place":10,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":99.7},{"place":11,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.7},{"place":12,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":99.7},{"place":13,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":99.4},{"place":14,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.2},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":97.5}]},{"id":"openai-internal-data-science-tasks","name":"OpenAI Internal Data Science Tasks","topic":"Data science","description":"OpenAI internal eval reported in the GPT-6 Astra announcement: data-science tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":40.9,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":40.9},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":34.7},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":30.5}]},{"id":"openai-internal-db-migration-tasks","name":"OpenAI Internal Database Migration Tasks","topic":"Software engineering","description":"OpenAI internal eval reported in the GPT-6 Astra announcement: database migration coding tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":63.9,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":63.9},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":57.8},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":50.3},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":42.7}]},{"id":"openai-internal-design-tasks","name":"OpenAI Internal Design Tasks","topic":"Design","description":"OpenAI internal eval reported in the GPT-6 Astra announcement: professional design tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":50,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":50},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":47.4},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":35.8}]},{"id":"openai-internal-dynamic-mental-health-emotional-reliance","name":"OpenAI Dynamic Benchmarks with Adversarial User Simulations: Emotional reliance","topic":"Safety","description":"OpenAI system-card dynamic multi-turn benchmark with adversarial user simulations, 'Emotional reliance' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":99.5,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.5},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.3},{"place":3,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":98.9},{"place":4,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":98.8},{"place":5,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":97.6},{"place":6,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":97.6},{"place":7,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":97.5},{"place":8,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":96.9},{"place":9,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":96.5},{"place":10,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":96.3},{"place":11,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":96.1},{"place":12,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":96.1},{"place":13,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":96.1},{"place":14,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":95.7},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":95.3},{"place":16,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":91.5}]},{"id":"openai-internal-dynamic-mental-health-mental-health","name":"OpenAI Dynamic Benchmarks with Adversarial User Simulations: Mental health","topic":"Safety","description":"OpenAI system-card dynamic multi-turn benchmark with adversarial user simulations, 'Mental health' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":100,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":2,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":100},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.7},{"place":5,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":99.6},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":99.3},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":99.1},{"place":8,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":99.1},{"place":9,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":99.1},{"place":10,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":98.9},{"place":11,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":98.5},{"place":12,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":98.1},{"place":13,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.1},{"place":14,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":97.7},{"place":15,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":91.4},{"place":16,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":82}]},{"id":"openai-internal-dynamic-mental-health-self-harm","name":"OpenAI Dynamic Benchmarks with Adversarial User Simulations: Self-harm","topic":"Safety","description":"OpenAI system-card dynamic multi-turn benchmark with adversarial user simulations, 'Self-harm' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":99.6,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.6},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":98.9},{"place":3,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":97.5},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":97.3},{"place":5,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":96.7},{"place":6,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":94.7},{"place":7,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":92.4},{"place":8,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":91.1},{"place":9,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":90.5},{"place":10,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":90.1},{"place":11,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":88.9},{"place":12,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":88.4},{"place":13,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":88},{"place":14,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":86.8},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":85.6},{"place":16,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":85.2}]},{"id":"openai-internal-expert-swe","name":"OpenAI Internal Expert-SWE","topic":"Software engineering","description":"OpenAI internal eval (GPT-5.5 announcement): expert-level, long-horizon software-engineering tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":73.1,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":73.1},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":68.5}]},{"id":"openai-internal-factual-error-rate","name":"OpenAI Internal Factual Error Rate (Difficult Prompts)","topic":"Factuality","description":"OpenAI internal factuality eval on de-identified ChatGPT conversations where users flagged factual errors; error rate (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":3.9,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":3.9},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":4.1},{"place":3,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":4.2},{"place":4,"model":"gpt-6.1-terra-max","company":"openai","family":"GPT","version":"GPT-6.1","score":4.3},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":4.3},{"place":6,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":4.4},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":4.5},{"place":8,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":4.6},{"place":9,"model":"gpt-6.1-terra-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":5},{"place":10,"model":"gpt-6.1-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":5.5},{"place":11,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":5.9},{"place":12,"model":"gpt-6.1-sol-high","company":"openai","family":"GPT","version":"GPT-6.1","score":6.6},{"place":13,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":7.6},{"place":14,"model":"gpt-6.1-terra-high","company":"openai","family":"GPT","version":"GPT-6.1","score":7.7},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":8.4},{"place":16,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":9.7},{"place":17,"model":"gpt-6.1-terra-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":10.1},{"place":18,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":12},{"place":19,"model":"gpt-6.1-sol-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":12},{"place":20,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":13.3},{"place":21,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":14.7},{"place":22,"model":"gpt-6.1-terra-low","company":"openai","family":"GPT","version":"GPT-6.1","score":16.7},{"place":23,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":18.4},{"place":24,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":22.3},{"place":25,"model":"gpt-6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":24.5},{"place":26,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":27.6},{"place":27,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":31.2},{"place":28,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":33.9},{"place":29,"model":"gpt-5.6-terra-high","company":"openai","family":"GPT","version":"GPT-5.6","score":41.1},{"place":30,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":44.3},{"place":31,"model":"gpt-5.6-terra-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":51.5},{"place":32,"model":"gpt-5.6-terra-low","company":"openai","family":"GPT","version":"GPT-5.6","score":53.6}]},{"id":"openai-internal-factuality-factuality-heavy-claims","name":"OpenAI Factuality: Factuality-Heavy Prompts (claims with errors)","topic":"Factuality","description":"OpenAI system-card factuality eval on factuality-heavy prompts: share of claims with factual errors (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna (2026-10-07)","top_percent":1.6,"top_model_id":"gpt-6-luna-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":1.6},{"place":2,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":1.8},{"place":3,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":1.9},{"place":4,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":3.1},{"place":5,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":4.4},{"place":6,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":7.4}]},{"id":"openai-internal-factuality-factuality-heavy-responses","name":"OpenAI Factuality: Factuality-Heavy Prompts (responses with errors)","topic":"Factuality","description":"OpenAI system-card factuality eval on factuality-heavy prompts: share of responses with factual errors (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol (2026-10-07)","top_percent":5.4,"top_model_id":"gpt-6-sol-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":5.4},{"place":2,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":5.6},{"place":3,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":6.6},{"place":4,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":10.5},{"place":5,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":17.9},{"place":6,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":25.3}]},{"id":"openai-internal-factuality-high-stakes-claims","name":"OpenAI Factuality: High-Stakes Prompts (claims with errors)","topic":"Factuality","description":"OpenAI system-card factuality eval on high-stakes prompts: share of claims with factual errors (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol (2026-10-07)","top_percent":0.9,"top_model_id":"gpt-6-sol-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":0.9},{"place":2,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":1.1},{"place":3,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":1.8},{"place":4,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":2.1},{"place":5,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":4.8},{"place":6,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":10.1}]},{"id":"openai-internal-factuality-high-stakes-responses","name":"OpenAI Factuality: High-Stakes Prompts (responses with errors)","topic":"Factuality","description":"OpenAI system-card factuality eval on high-stakes prompts: share of responses with factual errors (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol (2026-10-07)","top_percent":4.1,"top_model_id":"gpt-6-sol-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":4.1},{"place":2,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":4.5},{"place":3,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":6.3},{"place":4,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":8.6},{"place":5,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":19.9},{"place":6,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":36.4}]},{"id":"openai-internal-factuality-user-flagged-claims","name":"OpenAI Factuality: User-Flagged Failures (claims with errors)","topic":"Factuality","description":"OpenAI system-card factuality eval on user-flagged failures: share of claims with factual errors (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol (2026-10-07)","top_percent":3.5,"top_model_id":"gpt-6-sol-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":3.5},{"place":2,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":5.1},{"place":3,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":6.3},{"place":4,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":11.7},{"place":5,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":15.8},{"place":6,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":25.2}]},{"id":"openai-internal-factuality-user-flagged-responses","name":"OpenAI Factuality: User-Flagged Failures (responses with errors)","topic":"Factuality","description":"OpenAI system-card factuality eval on user-flagged failures: share of responses with factual errors (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol (2026-10-07)","top_percent":13.5,"top_model_id":"gpt-6-sol-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":13.5},{"place":2,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":18.7},{"place":3,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":18.9},{"place":4,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":33.5},{"place":5,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":46.1},{"place":6,"model":"gpt-5.3-instant","company":"openai","family":"GPT","version":"GPT-5.3","score":61.3}]},{"id":"openai-internal-guardian-circumvention","name":"OpenAI Internal Guardian Circumvention","topic":"Safety","description":"OpenAI alignment eval: share of samples where the model completed a prohibited action by circumventing the Guardian reviewer (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna (2026-10-07)","top_percent":0,"top_model_id":"gpt-6-luna-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":3,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":0.3},{"place":4,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":0.3}]},{"id":"openai-internal-hallucination","name":"OpenAI Internal Hallucination","topic":"Hallucination","description":"OpenAI internal eval reported in the GPT-6 Astra announcement: hallucination rate (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":4.2,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":4.2},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":12.2}]},{"id":"openai-internal-image-input-safety-extremism","name":"OpenAI Image Input Safe Completions: extremism","topic":"Safety","description":"OpenAI system-card image-input safety evaluation, 'extremism' category: safe-completion rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":99.1,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.1},{"place":2,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":98.7},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98.6},{"place":4,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":98.6},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.4},{"place":6,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":98.2},{"place":7,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":97.8},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":97.5},{"place":9,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":97.5},{"place":10,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":96.6},{"place":11,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":96.4},{"place":12,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":95},{"place":13,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":93},{"place":14,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":92.8},{"place":15,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":86.8},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":83.4}]},{"id":"openai-internal-image-input-safety-harms-erotic","name":"OpenAI Image Input Safe Completions: harms-erotic","topic":"Safety","description":"OpenAI system-card image-input safety evaluation, 'harms-erotic' category: safe-completion rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":100,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":100},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":100},{"place":3,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":99.9},{"place":4,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":99.9},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.8},{"place":6,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":99.5},{"place":7,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":99.4},{"place":8,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":99.1},{"place":9,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":99.1},{"place":10,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98.7},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.6},{"place":12,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":98.6},{"place":13,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.6},{"place":14,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":98.4},{"place":15,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":98.1},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":97.5}]},{"id":"openai-internal-image-input-safety-hate","name":"OpenAI Image Input Safe Completions: hate","topic":"Safety","description":"OpenAI system-card image-input safety evaluation, 'hate' category: safe-completion rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":99.9,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":99.9},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":99.9},{"place":3,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":99.9},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.8},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":99.8},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.8},{"place":7,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":99.8},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.7},{"place":9,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":99.6},{"place":10,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":99.4},{"place":11,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":99.3},{"place":12,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.6},{"place":13,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":98.6},{"place":14,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":98.5},{"place":15,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.4},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":97.4}]},{"id":"openai-internal-image-input-safety-self-harm","name":"OpenAI Image Input Safe Completions: self-harm","topic":"Safety","description":"OpenAI system-card image-input safety evaluation, 'self-harm' category: safe-completion rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna","top_percent":99.9,"top_model_id":"gpt-6-luna","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":99.9},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.7},{"place":3,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":99.6},{"place":4,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":99.6},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.4},{"place":6,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":99.3},{"place":7,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":99},{"place":8,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":99},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.9},{"place":10,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":98.7},{"place":11,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.7},{"place":12,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":98.6},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98.3},{"place":14,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":98.2},{"place":15,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":96.2},{"place":16,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":95.6}]},{"id":"openai-internal-indirect-prompt-injection","name":"OpenAI Indirect Prompt Injection Defense","topic":"Safety","description":"OpenAI system-card indirect prompt-injection eval: defender success rate averaged per defender query (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":99.99,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.99},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.99},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.97},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":99.97}]},{"id":"openai-internal-instruction-hierarchy-robustness","name":"OpenAI Instruction Hierarchy Robustness","topic":"Safety","description":"OpenAI system-card instruction hierarchy evaluations: robustness rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol (2026-10-07)","top_percent":99.99,"top_model_id":"gpt-6-sol-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":99.99},{"place":2,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":99.79}]},{"id":"openai-internal-investment-banking-modeling","name":"OpenAI Internal Investment Banking Modeling Tasks","topic":"Finance","description":"OpenAI internal eval (GPT-5.4/GPT-5.5 announcements): investment-banking spreadsheet modeling tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5 Pro","top_percent":88.6,"top_model_id":"gpt-5.5-pro","top_generation":"GPT-5.5","top_model_base":"GPT-5.5 Pro","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":88.6},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":88.5},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":87.3},{"place":4,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":83.6},{"place":5,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":79.3},{"place":6,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":71.7},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":68.4}]},{"id":"openai-internal-jailbreak-bio-high-risk","name":"OpenAI Jailbreak Robustness: Bio: high risk","topic":"Safety","description":"OpenAI system-card jailbreak evaluation, 'Bio: high risk' category: defender success rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":97.3,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97.3},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":93.8},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":85.8},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":73.8},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":11.5},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":5.8}]},{"id":"openai-internal-jailbreak-bio-severe","name":"OpenAI Jailbreak Robustness: Bio: severe","topic":"Safety","description":"OpenAI system-card jailbreak evaluation, 'Bio: severe' category: defender success rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":98.2,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":98.2},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":94.3},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":81.3},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":73},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":12.1},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":10.3}]},{"id":"openai-internal-jailbreak-cyber","name":"OpenAI Jailbreak Robustness: Cyber","topic":"Safety","description":"OpenAI system-card jailbreak evaluation, 'Cyber' category: defender success rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":91.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":91.5},{"place":2,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":87.5},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":85.8},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":79.8},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":59},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":57}]},{"id":"openai-internal-jailbreak-violence-moderate","name":"OpenAI Jailbreak Robustness: Violence: moderate","topic":"Safety","description":"OpenAI system-card jailbreak evaluation, 'Violence: moderate' category: defender success rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":94.7,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":94.7},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":89.5},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":88.8},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":77},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":22.3},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":21.6}]},{"id":"openai-internal-jailbreak-violence-severe","name":"OpenAI Jailbreak Robustness: Violence: severe","topic":"Safety","description":"OpenAI system-card jailbreak evaluation, 'Violence: severe' category: defender success rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":98.3,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":98.3},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":95},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":90.5},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":89.3},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":48.3},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":38}]},{"id":"openai-internal-listqa-nondisclosure","name":"OpenAI Internal ListQA Nondisclosure","topic":"Safety","description":"OpenAI broken-search-tool alignment eval (ListQA): combined failure rate of not disclosing the missing tool (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-october","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Sol (2026-10-07)","top_percent":5.2,"top_model_id":"gpt-6-sol-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":5.2},{"place":2,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":9.7},{"place":3,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":59.7},{"place":4,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":76.1}]},{"id":"openai-internal-management-consulting","name":"OpenAI Internal Management Consulting Tasks","topic":"Professional work","description":"OpenAI internal eval (GPT-5.6 announcement): management-consulting tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":43.2,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":43.2},{"place":2,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":37.2},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":35.5},{"place":4,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":35.4},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":31.6},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":31.3},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":13.2}]},{"id":"openai-internal-misaligned-outcomes","name":"OpenAI Misaligned Outcomes in Realistic Work Environments","topic":"Safety","description":"OpenAI alignment eval: misaligned outcome rate in adversarial realistic work environments (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":1.1,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":1.1},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":1.16},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":1.32},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":1.94},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":2.28},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":4.93},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":5.36},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":5.65},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":11.41}]},{"id":"openai-internal-misaligned-outcomes-circumventing-restrictions","name":"OpenAI Misaligned Outcomes: Circumventing restrictions","topic":"Safety","description":"OpenAI realistic work environments eval, 'Circumventing restrictions' misaligned outcome rate (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.15},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.16},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.24},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.26},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.34}]},{"id":"openai-internal-misaligned-outcomes-data-exfiltration","name":"OpenAI Misaligned Outcomes: Data exfiltration","topic":"Safety","description":"OpenAI realistic work environments eval, 'Data exfiltration' misaligned outcome rate (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0.26,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.26},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.45},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.46},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.54},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":1.02},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":1.09},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":1.25},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":2.22},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":4.09}]},{"id":"openai-internal-misaligned-outcomes-destructive-action","name":"OpenAI Misaligned Outcomes: Destructive action","topic":"Safety","description":"OpenAI realistic work environments eval, 'Destructive action' misaligned outcome rate (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":0,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.08},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.08},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.16},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.19},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.3},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.31},{"place":8,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.39},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":1.21}]},{"id":"openai-internal-misaligned-outcomes-security-weakening","name":"OpenAI Misaligned Outcomes: Security weakening","topic":"Safety","description":"OpenAI realistic work environments eval, 'Security weakening' misaligned outcome rate (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0.32,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.32},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.39},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.46},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.74},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.82},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":1.02},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":2.5},{"place":8,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":3.65},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":6.61}]},{"id":"openai-internal-misaligned-outcomes-service-disruption","name":"OpenAI Misaligned Outcomes: Service disruption","topic":"Safety","description":"OpenAI realistic work environments eval, 'Service disruption' misaligned outcome rate (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":0,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.13}]},{"id":"openai-internal-misaligned-outcomes-unauthorized-external-communication","name":"OpenAI Misaligned Outcomes: Unauthorized external communication","topic":"Safety","description":"OpenAI realistic work environments eval, 'Unauthorized external communication' misaligned outcome rate (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":0,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.06},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.08},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.22},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.23},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.24},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.59},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.61},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":1.34}]},{"id":"openai-internal-misaligned-outcomes-unauthorized-transactions","name":"OpenAI Misaligned Outcomes: Unauthorized transactions","topic":"Safety","description":"OpenAI realistic work environments eval, 'Unauthorized transactions' misaligned outcome rate (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Terra","top_percent":0,"top_model_id":"gpt-6.1-terra","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.13},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.15},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.15},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.16},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.26},{"place":7,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.31},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.47}]},{"id":"openai-internal-prompt-injection-robustness","name":"OpenAI Internal Prompt Injection Robustness","topic":"Safety","description":"OpenAI system-card prompt-injection robustness rate (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":99.789,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.789},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99.05},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.983},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":98.77},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":98.605},{"place":6,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":97.13},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95.97},{"place":8,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":95.8},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":93.954}]},{"id":"openai-internal-research-debugging","name":"OpenAI Internal Research Debugging Evaluation","topic":"AI research automation","description":"OpenAI internal eval (GPT-5.6 announcement): debugging real AI research systems.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":78.05,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":78.05},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":76.39},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":75.52},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":68.32},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":68.3},{"place":6,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":67.8},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":64.2},{"place":8,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":50.8},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":50}]},{"id":"openai-internal-reviewer-bypass","name":"OpenAI Internal Reviewer Bypass Attempts","topic":"Safety","description":"OpenAI internal alignment eval: rate of attempts to bypass a reviewer (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":0.3},{"place":6,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":0.6},{"place":7,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":4.3},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":7.3}]},{"id":"openai-internal-u18-age-restricted-goods-services-and-dangerous-challenges-activities","name":"OpenAI U18 Safe Completions: Age-restricted goods, services, and dangerous challenges / activities","topic":"Safety","description":"OpenAI system-card safe-completion evaluation for users under 18, 'Age-restricted goods, services, and dangerous challenges / activities' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":93.4,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":93.4},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":92.6},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":91.8},{"place":4,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":86.5},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":86.1},{"place":6,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":85.7},{"place":7,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":84.8},{"place":8,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":81.4},{"place":9,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":79.9},{"place":10,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":76.2},{"place":11,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":76},{"place":12,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":75.6},{"place":13,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":75.2},{"place":14,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":72.5},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":71.9},{"place":16,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":71.1}]},{"id":"openai-internal-u18-eating-disorders","name":"OpenAI U18 Safe Completions: Eating Disorders","topic":"Safety","description":"OpenAI system-card safe-completion evaluation for users under 18, 'Eating Disorders' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":96.2,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":96.2},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":93.8},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":92.1},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":87.1},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":85.3},{"place":6,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":81},{"place":7,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":80.8},{"place":8,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":77.6},{"place":9,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":77.2},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":71},{"place":11,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":70.2},{"place":12,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":69.4},{"place":13,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":67.3},{"place":14,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":65.7},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":63.9},{"place":16,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":63.5}]},{"id":"openai-internal-u18-emotional-reliance","name":"OpenAI U18 Safe Completions: Emotional Reliance","topic":"Safety","description":"OpenAI system-card safe-completion evaluation for users under 18, 'Emotional Reliance' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":96.9,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":96.9},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":94.8},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":94.8},{"place":4,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":94.6},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":94.4},{"place":6,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":94.4},{"place":7,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":93.7},{"place":8,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":93.5},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":93.1},{"place":10,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":93.1},{"place":11,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":92.7},{"place":12,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":92.5},{"place":13,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":92.1},{"place":14,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":91.4},{"place":15,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":77},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":73.4}]},{"id":"openai-internal-u18-gore","name":"OpenAI U18 Safe Completions: Gore","topic":"Safety","description":"OpenAI system-card safe-completion evaluation for users under 18, 'Gore' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":89.8,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":89.8},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":89.8},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":88.9},{"place":4,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":88.3},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":87.8},{"place":6,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":87.2},{"place":7,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":86.7},{"place":8,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":86.5},{"place":9,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":84.5},{"place":10,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":84.5},{"place":11,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":83.2},{"place":12,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":82.3},{"place":13,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":81.9},{"place":14,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":81.2},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":80.3},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":78.5}]},{"id":"openai-internal-u18-self-harm","name":"OpenAI U18 Safe Completions: Self Harm","topic":"Safety","description":"OpenAI system-card safe-completion evaluation for users under 18, 'Self Harm' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol","top_percent":99.7,"top_model_id":"gpt-6.1-sol","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":99.7},{"place":2,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":99.5},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.5},{"place":4,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":99},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":99},{"place":6,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":99},{"place":7,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":98.7},{"place":8,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.7},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.2},{"place":10,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":98.2},{"place":11,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":98.2},{"place":12,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":97.7},{"place":13,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":97.7},{"place":14,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":97.7},{"place":15,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":97.7},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":97.4}]},{"id":"openai-internal-u18-sexual-content","name":"OpenAI U18 Safe Completions: Sexual Content","topic":"Safety","description":"OpenAI system-card safe-completion evaluation for users under 18, 'Sexual Content' category (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":99.1,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":99.1},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":98.4},{"place":3,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":98.4},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":97.5},{"place":5,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":97.3},{"place":6,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":97.1},{"place":7,"model":"gpt-5.5-instant-2026-06-01","company":"openai","family":"GPT","version":"GPT-5.5","score":96.2},{"place":8,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":95.8},{"place":9,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":94.9},{"place":10,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":94.4},{"place":11,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":94},{"place":12,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":93.5},{"place":13,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":93.3},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":92.9},{"place":15,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":92.2},{"place":16,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":90.4}]},{"id":"openai-internal-unauthorized-agent-engagement","name":"OpenAI Internal Unauthorized Agent Engagement","topic":"Safety","description":"OpenAI alignment eval: rate of engaging with external agent messages after discovering them (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna","top_percent":0,"top_model_id":"gpt-6-luna","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":5},{"place":3,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":26.25},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":26.92},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":37.66},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":40},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":41.25},{"place":8,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":50},{"place":9,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":65},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.54},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":91.25}]},{"id":"openai-internal-unauthorized-agent-interaction","name":"OpenAI Internal Unauthorized Agent Interaction","topic":"Safety","description":"OpenAI internal alignment eval: rate of unauthorized interaction with other agents (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":0,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":2,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":3,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":1.25},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":1.25},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":2.6},{"place":6,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":11.25},{"place":7,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":11.3},{"place":8,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":13.75},{"place":9,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":16.25},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":51.9},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":57.5}]},{"id":"openai-internal-vuln-discovery-report-writing","name":"OpenAI Internal Vulnerability Discovery and Report Writing","topic":"Cybersecurity","description":"OpenAI internal eval (Daybreak announcement): open-ended vulnerability finding in a repo with a known vulnerability, PoC and report quality.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":17.9,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":17.9},{"place":2,"model":"gpt-5.6-cyber","company":"openai","family":"GPT","version":"GPT-5.6","score":14.5},{"place":3,"model":"gpt-5.5-cyber","company":"openai","family":"GPT","version":"GPT-5.5","score":11.8}]},{"id":"openai-internal-warning-circumvention","name":"OpenAI Internal Warning Circumvention","topic":"Safety","description":"OpenAI internal alignment eval: rate of circumventing warnings (lower is better).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna (2026-10-07)","top_percent":15.9,"top_model_id":"gpt-6-luna-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":15.9},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":17.4},{"place":3,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":17.4},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":21.6},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":22},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":23.5},{"place":7,"model":"gpt-5.6-luna-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":26.6},{"place":8,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":28.1},{"place":9,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":28.4},{"place":10,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":29.6},{"place":11,"model":"gpt-5.6-sol-2026-08-01","company":"openai","family":"GPT","version":"GPT-5.6","score":33.9},{"place":12,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":34.6},{"place":13,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":42.4},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":43.9},{"place":15,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":64.4},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":68.2},{"place":17,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":76.5}]},{"id":"openai-internal-zero-day-discovery","name":"OpenAI Internal Zero-Day Discovery Eval","topic":"Cybersecurity","description":"OpenAI internal eval (Daybreak announcement): find zero-day vulnerabilities in current open-source releases, build max-impact PoCs and write-ups; graded on severity, impact and calibration.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Cyber","top_percent":24.5,"top_model_id":"gpt-5.6-cyber","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Cyber","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-cyber","company":"openai","family":"GPT","version":"GPT-5.6","score":24.5},{"place":2,"model":"gpt-5.5-cyber","company":"openai","family":"GPT","version":"GPT-5.5","score":17.5},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":15.8}]},{"id":"openbookqa","name":"OpenBookQA","topic":"Science QA","description":"Open-book multiple choice science questions with supporting facts.","url":"https://github.com/allenai/OpenBookQA","leaderboard":"","github":"","paper":"","metric":"percent","stars":"128","top_model":"Hermes 4.3 36B Pyche","top_percent":96.6,"top_model_id":"hermes-4.3-36b-pyche","top_generation":"Hermes 4.3","top_model_base":"Hermes 4.3 36B Pyche","top_model_family":"Hermes","top_company":"nousresearch","top_open_source":1,"lower_is_better":false,"bench_models":108,"total_models":3854,"placements":[{"place":1,"model":"hermes-4.3-36b-pyche","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":96.6},{"place":2,"model":"qwen-3","company":"qwen","family":"Qwen","version":"Qwen3","score":96.4},{"place":3,"model":"hermes-4.3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":94.8},{"place":4,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":94.8},{"place":5,"model":"hermes-4.3-36b","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":91.8},{"place":6,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":89.8},{"place":7,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.4},{"place":8,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":89},{"place":9,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":88.6},{"place":10,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":87.6},{"place":11,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":87},{"place":12,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":85.4},{"place":13,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":85.4},{"place":14,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":85.4},{"place":15,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":85.2},{"place":16,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":85},{"place":17,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":85},{"place":18,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":83.4},{"place":19,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":82.2},{"place":20,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":82.2},{"place":21,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":82},{"place":22,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":81.2},{"place":23,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":81},{"place":24,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":80},{"place":25,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":79},{"place":26,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.4},{"place":27,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":77.4},{"place":28,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":75.2},{"place":29,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":74.8},{"place":30,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":74.4},{"place":31,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":74},{"place":32,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":72.4},{"place":33,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":72.4},{"place":34,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":69.6},{"place":35,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":69},{"place":36,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":67.4},{"place":37,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":67},{"place":38,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":65},{"place":39,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":65},{"place":40,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":64.4},{"place":41,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":63.2},{"place":42,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":60.4},{"place":43,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":60.2},{"place":44,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":60.2},{"place":45,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":60.2},{"place":46,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":58.6},{"place":47,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":58.6},{"place":48,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":57.6},{"place":49,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":57.4},{"place":50,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":57.4},{"place":51,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":57.2},{"place":52,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":57},{"place":53,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":56.6},{"place":54,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":56.4},{"place":55,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":55.8},{"place":56,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":54.8},{"place":57,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":53.4},{"place":58,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":52.8},{"place":59,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":52},{"place":60,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":51.6},{"place":61,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":51.4},{"place":62,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":51.4},{"place":63,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":50.8},{"place":64,"model":"palm-62b","company":"google","family":"PaLM","version":"PaLM","score":50.4},{"place":65,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":50.2},{"place":66,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":49.6},{"place":67,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":48.8},{"place":68,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":48.8},{"place":69,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":48.8},{"place":70,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":48.6},{"place":71,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":48.6},{"place":72,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":48.6},{"place":73,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":48.2},{"place":74,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":47.8},{"place":75,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":47.6},{"place":76,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":47.2},{"place":77,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":47},{"place":78,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":46.8},{"place":79,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":46.8},{"place":80,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":46.6},{"place":81,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":46.4},{"place":82,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":46.2},{"place":83,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":45.8},{"place":84,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":45.8},{"place":85,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":45.2},{"place":86,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":45},{"place":87,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":44.8},{"place":88,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":44.4},{"place":89,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":44.4},{"place":90,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.2},{"place":91,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":44.2},{"place":92,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":43.6},{"place":93,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":43.6},{"place":94,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":43.6},{"place":95,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":43},{"place":96,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":42.6},{"place":97,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":42.6},{"place":98,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":42.4},{"place":99,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":42.2},{"place":100,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":42.2},{"place":101,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":40},{"place":102,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":39.8},{"place":103,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":39.8},{"place":104,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":39.4},{"place":105,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":38.4},{"place":106,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":37.2},{"place":107,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":36.6},{"place":108,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":36.2},{"place":109,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.2},{"place":110,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":35},{"place":111,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":34.6},{"place":112,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":34.6},{"place":113,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":32.6},{"place":114,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.8},{"place":115,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":29.6},{"place":116,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":28.6},{"place":117,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":26.6},{"place":118,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":25},{"place":119,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":24.6},{"place":120,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.556},{"place":121,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.526}]},{"id":"openeqa","name":"OpenEQA","topic":"Embodied QA","description":"Open-vocabulary embodied question answering over episodic memory of indoor scenes.","url":"https://open-eqa.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":64.4,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":64.4},{"place":2,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":59.2},{"place":3,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":55},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":55},{"place":5,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":50.5},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.3},{"place":7,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.6},{"place":8,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":46.9},{"place":9,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":44.7},{"place":10,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":44.6},{"place":11,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":43.5},{"place":12,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":36.2}]},{"id":"openrewrite-eval","name":"OpenRewrite-Eval","topic":"Rewrite quality","description":"OpenRewrite evaluation; micro-averaged RougeL.","url":"","leaderboard":"","github":"","paper":"","metric":"rougel","stars":"","top_model":"Qwen2.5 1.5B Instruct","top_percent":46.9,"top_model_id":"qwen2.5-1.5b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 1.5B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.9},{"place":2,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":44.9},{"place":3,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":39.2}]},{"id":"openscore-string-quartets","name":"OpenScore String Quartets","topic":"Optical music recognition","description":"Optical music recognition on OpenScore string quartet scores; score is 1 - OMR normalized edit distance.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"GPT-6 Astra","top_percent":0.84,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.84},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.19}]},{"id":"optmath","name":"OptMATH","topic":"Math optimization reasoning","description":"OptMATH benchmark targeting challenging math optimization and problem-solving tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ling 1T","top_percent":57.68,"top_model_id":"ling-1t","top_generation":"Ling 1T","top_model_base":"Ling 1T","top_model_family":"Ling","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":57.68},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":42.77},{"place":3,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":39.16},{"place":4,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":35.99},{"place":5,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":35.84}]},{"id":"order-15-items","name":"Order 15 Items","topic":"List ordering","description":"Ordering benchmark requiring models to sequence 15 items correctly.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"K2-V2","top_percent":87.6,"top_model_id":"k2-v2","top_generation":"K2 V2","top_model_base":"K2 V2","top_model_family":"K2","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":87.6},{"place":2,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":37},{"place":3,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":25},{"place":4,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":4.7},{"place":5,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":4.5},{"place":6,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":3.5}]},{"id":"order-30-items","name":"Order 30 Items","topic":"List ordering (long)","description":"Ordering benchmark requiring models to sequence 30 items correctly.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"K2-V2","top_percent":40.3,"top_model_id":"k2-v2","top_generation":"K2 V2","top_model_base":"K2 V2","top_model_family":"K2","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":40.3},{"place":2,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.7},{"place":3,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":0.6},{"place":4,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":0.2},{"place":5,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":0.1},{"place":6,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":0}]},{"id":"osworld","name":"OSWorld","topic":"GUI agents","description":"Agentic GUI task completion and grounding on desktop environments.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":72.7,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":72.7},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":72.7},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":72.2},{"place":4,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.3},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.3},{"place":6,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.3},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.9},{"place":8,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":62.3},{"place":9,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":61.9},{"place":10,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.4},{"place":11,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.4},{"place":12,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61},{"place":13,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.7},{"place":14,"model":"nemotron-3-nano-omni-30b-a3b-reasoning","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":47.4},{"place":15,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":44.4},{"place":16,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":42.2},{"place":17,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":38.8},{"place":18,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":38.1},{"place":19,"model":"gpt-03-cua","company":"openai","family":"o3","version":"o3","score":38.1},{"place":20,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":37.2},{"place":21,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":36.7},{"place":22,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":36.7},{"place":23,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":35},{"place":24,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":34.1},{"place":25,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":33.9},{"place":26,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":32.6},{"place":27,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":30.5},{"place":28,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.2},{"place":29,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":21.1},{"place":30,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":13.3},{"place":31,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":11.1}]},{"id":"osworld-2.0","name":"OSWorld 2.0","topic":"GUI agents","description":"OSWorld 2.0 long-horizon computer-use benchmark on a live Ubuntu VM; partial-credit score.","url":"https://arxiv.org/abs/2606.29537","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":81.8,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":81.8},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":77.9},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":75.4},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":73.5},{"place":5,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":72.9},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.6},{"place":7,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68.3},{"place":8,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":66.9},{"place":9,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":66.1},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":65.7},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":62.7},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":62.6},{"place":13,"model":"holo4-27b","company":"hcompany","family":"Holo","version":"Holo4","score":61.7},{"place":14,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":61.7},{"place":15,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":59.1},{"place":16,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":59},{"place":17,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":58.3},{"place":18,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":56.4},{"place":19,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":55.7},{"place":20,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.9},{"place":21,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":54.8},{"place":22,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":52.3},{"place":23,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":50.6},{"place":24,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":50.2},{"place":25,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":49.5},{"place":26,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":48},{"place":27,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":47.9},{"place":28,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":47.6},{"place":29,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":47.5},{"place":30,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":46.7},{"place":31,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":46.7},{"place":32,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":45.6},{"place":33,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":42.6},{"place":34,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":33.8},{"place":35,"model":"holo4-35b-a3b","company":"hcompany","family":"Holo","version":"Holo4","score":30.9},{"place":36,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":30.6},{"place":37,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":30.5},{"place":38,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":22.3},{"place":39,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":21.5},{"place":40,"model":"ui-venus-2-27b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":13.2},{"place":41,"model":"ui-venus-2-9b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":7.5},{"place":42,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":7.1},{"place":43,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":3.8},{"place":44,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.5}]},{"id":"osworld-2.0-offline","name":"OSWorld 2.0 (Offline)","topic":"GUI agents","description":"OSWorld 2.0 offline set (v2026.08.08), partial-credit score on long-horizon computer-use workflows without internet access.","url":"https://osworld-v2.xlang.ai/","leaderboard":"https://osworld-v2.xlang.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":73.5,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":73.5},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":72.6},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":71.4},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.2},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.19},{"place":6,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":69.2},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":66.2},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":65.7},{"place":9,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":64.4},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.13},{"place":11,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":52.7},{"place":12,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":52.7}]},{"id":"osworld-2.0-strict","name":"OSWorld 2.0 (Strict)","topic":"GUI agents","description":"OSWorld 2.0 strict pass rate (full task success).","url":"https://arxiv.org/abs/2606.29537","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":48.7,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":48.7},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":41.7},{"place":3,"model":"holo4-27b","company":"hcompany","family":"Holo","version":"Holo4","score":41.5},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":39.6},{"place":5,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":36.1},{"place":6,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":32},{"place":7,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":31.4},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":27.3},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":20.6},{"place":10,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":19.4},{"place":11,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":19.4},{"place":12,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":19.4},{"place":13,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":17.9},{"place":14,"model":"holo4-35b-a3b","company":"hcompany","family":"Holo","version":"Holo4","score":12.3},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":7.8},{"place":16,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":2.8}]},{"id":"osworld-2.1","name":"OSWorld 2.1","topic":"GUI agents","description":"OSWorld 2.1 long-horizon computer-use benchmark; partial-credit score.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":81.8,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":81.8},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":80.7},{"place":3,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":80.1},{"place":4,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":79.6},{"place":5,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":78.4},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":75.8},{"place":7,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":74},{"place":8,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":72.6},{"place":9,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":69.3},{"place":10,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57}]},{"id":"osworld-2.1-offline","name":"OSWorld 2.1 (Offline)","topic":"GUI agents","description":"OSWorld 2.1 offline subset (82 tasks), partial-credit score on long-horizon computer-use workflows without internet access.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 5.5","top_percent":83.9,"top_model_id":"claude-sonnet-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Sonnet 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":83.9},{"place":2,"model":"claude-sonnet-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":83.9},{"place":3,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":81},{"place":4,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":80.9},{"place":5,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":79},{"place":6,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":78.3},{"place":7,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":78},{"place":8,"model":"gpt-6.1-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":75.9},{"place":9,"model":"gpt-6.1-sol-high","company":"openai","family":"GPT","version":"GPT-6.1","score":75.5},{"place":10,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":75.4},{"place":11,"model":"gpt-6.1-terra-max","company":"openai","family":"GPT","version":"GPT-6.1","score":74.2},{"place":12,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":74.2},{"place":13,"model":"gpt-6.1-sol-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":73.5},{"place":14,"model":"claude-sonnet-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":73.3},{"place":15,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":72.4},{"place":16,"model":"gpt-6.1-terra-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":71.3},{"place":17,"model":"gpt-6.1-terra-high","company":"openai","family":"GPT","version":"GPT-6.1","score":68.7},{"place":18,"model":"gpt-6.1-terra-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":66.7},{"place":19,"model":"claude-sonnet-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":65.9},{"place":20,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":63.3},{"place":21,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":60.9},{"place":22,"model":"claude-sonnet-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":57.8},{"place":23,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":57.1},{"place":24,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":55.5},{"place":25,"model":"gpt-6.1-terra-low","company":"openai","family":"GPT","version":"GPT-6.1","score":53.8},{"place":26,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":48.9},{"place":27,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":48.4},{"place":28,"model":"gpt-6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":44.6},{"place":29,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":39.7},{"place":30,"model":"gpt-5.6-terra-high","company":"openai","family":"GPT","version":"GPT-5.6","score":37.7},{"place":31,"model":"gpt-5.6-terra-medium","company":"openai","family":"GPT","version":"GPT-5.6","score":27.4},{"place":32,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":26.3},{"place":33,"model":"gpt-5.6-terra-low","company":"openai","family":"GPT","version":"GPT-5.6","score":24.1},{"place":34,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":15.7},{"place":35,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":7.5}]},{"id":"osworld-2.1-strict","name":"OSWorld 2.1 (Strict)","topic":"GUI agents","description":"OSWorld 2.1 strict pass rate (full task success).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":48.7,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":48.7},{"place":2,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":43.5},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":43.1},{"place":4,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":42.8},{"place":5,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":39.4},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":37.2},{"place":7,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":34.3},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":34.3}]},{"id":"osworld-g","name":"OSWorld-G","topic":"GUI agents","description":"OSWorld-G center accuracy (no_refusal).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nex-N2.5-Pro","top_percent":87.4,"top_model_id":"nex-n2.5-pro","top_generation":"Nex-N2.5","top_model_base":"Nex-N2.5 Pro","top_model_family":"Nex","top_company":"nex-agi","top_open_source":1,"lower_is_better":false,"bench_models":86,"total_models":3854,"placements":[{"place":1,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":87.4},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.9},{"place":3,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":83.3},{"place":4,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":82.9},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":79.6},{"place":6,"model":"holo3-122b-a10b","company":"hcompany","family":"Holo","version":"Holo3","score":79.4},{"place":7,"model":"holo2-235b-a22b","company":"hcompany","family":"Holo","version":"Holo2","score":79},{"place":8,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.4},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.7},{"place":10,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.5},{"place":11,"model":"holo3-35b-a3b","company":"hcompany","family":"Holo","version":"Holo3","score":77.3},{"place":12,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.9},{"place":13,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":76.8},{"place":14,"model":"holo2-30b-a3b","company":"hcompany","family":"Holo","version":"Holo2","score":76.1},{"place":15,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":71.8},{"place":16,"model":"ui-venus-1.5-30b-a3b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":70.6},{"place":17,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":70.4},{"place":18,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":70.1},{"place":19,"model":"molmopoint-gui-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":70},{"place":20,"model":"ui-venus-1.5-8b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":69.7},{"place":21,"model":"holo2-4b","company":"hcompany","family":"Holo","version":"Holo2","score":69.4},{"place":22,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.3},{"place":23,"model":"vista-9b","company":"antgroup","family":"VISTA","version":"VISTA","score":68.1},{"place":24,"model":"mai-ui-32b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":67.6},{"place":25,"model":"groundnext-7b","company":"servicenow","family":"GroundNext","version":"GroundNext","score":67.2},{"place":26,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":66.27},{"place":27,"model":"molmo2-gui-8b","company":"allenai","family":"Molmo","version":"Molmo2","score":66.1},{"place":28,"model":"points-gui-g-8b","company":"tencent","family":"POINTS-GUI","version":"POINTS-GUI-G","score":66},{"place":29,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.8},{"place":30,"model":"gta1-32b","company":"salesforce","family":"GTA1","version":"GTA1","score":65.2},{"place":31,"model":"holo2-30b-a3b","company":"hcompany","family":"Holo","version":"Holo2","score":65.2},{"place":32,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.1},{"place":33,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":64.2},{"place":34,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":63.5},{"place":35,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.1},{"place":36,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":62.9},{"place":37,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":62.9},{"place":38,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":62.2},{"place":39,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":61.96},{"place":40,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":61.57},{"place":41,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":61.4},{"place":42,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.2},{"place":43,"model":"vista-4b","company":"antgroup","family":"VISTA","version":"VISTA","score":61.2},{"place":44,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.6},{"place":45,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.5},{"place":46,"model":"step-gui-4b","company":"stepfun","family":"Step-GUI","version":"Step-GUI","score":60.5},{"place":47,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":60.3},{"place":48,"model":"mai-ui-8b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":60.1},{"place":49,"model":"gta1-7b","company":"salesforce","family":"GTA1","version":"GTA1","score":60.1},{"place":50,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":59.6},{"place":51,"model":"opencua-32b","company":"hku","family":"OpenCUA","version":"OpenCUA","score":59.6},{"place":52,"model":"ui-venus-1.5-2b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":59.4},{"place":53,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.4},{"place":54,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":59.02},{"place":55,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":58.8},{"place":56,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":58.3},{"place":57,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.2},{"place":58,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.2},{"place":59,"model":"gui-owl-32b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl","score":58},{"place":60,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.5},{"place":61,"model":"ui-tars-72b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":57.1},{"place":62,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.7},{"place":63,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.4},{"place":64,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":56.1},{"place":65,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56},{"place":66,"model":"gui-owl-7b","company":"alibaba","family":"GUI","version":"GUI","score":55.9},{"place":67,"model":"opencua-7b","company":"xlang","family":"OpenCUA","version":"OpenCUA","score":55.3},{"place":68,"model":"gta1-7b","company":"salesforce","family":"GTA1","version":"GTA1","score":55.1},{"place":69,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":54.9},{"place":70,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.8},{"place":71,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":54.71},{"place":72,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":54.7},{"place":73,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":54.6},{"place":74,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.4},{"place":75,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":54.1},{"place":76,"model":"jedi-7b","company":"xlang","family":"Jedi","version":"Jedi","score":54.1},{"place":77,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":52.8},{"place":78,"model":"mai-ui-2b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":52},{"place":79,"model":"jedi-3b","company":"hku","family":"Jedi","version":"Jedi","score":50.9},{"place":80,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":50.54},{"place":81,"model":"holotron-12b","company":"hcompany","family":"Holotron","version":"Holotron","score":49},{"place":82,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.7},{"place":83,"model":"ui-tars-7b","company":"bytedance","family":"UI","version":"UI","score":47.5},{"place":84,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":47.25},{"place":85,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.1},{"place":86,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.9},{"place":87,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":45.2},{"place":88,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":42.4},{"place":89,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":42.16},{"place":90,"model":"gpt-03-cua","company":"openai","family":"o3","version":"o3","score":40.6},{"place":91,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":40.59},{"place":92,"model":"aguvis-7b","company":"hku","family":"Aguvis","version":"Aguvis","score":38.7},{"place":93,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":37.7},{"place":94,"model":"uground-v1-7b","company":"osunlp","family":"UGround","version":"UGround-V1","score":36.4},{"place":95,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":35.5},{"place":96,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":34.31},{"place":97,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":31.91},{"place":98,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.3},{"place":99,"model":"os-atlas-7b","company":"os-copilot","family":"OS-Atlas","version":"OS-Atlas","score":27.7},{"place":100,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":11},{"place":101,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":8.8}]},{"id":"osworld-verified","name":"OSWorld Verified","topic":"GUI agents","description":"Verified subset of OSWorld GUI agent benchmark.","url":"","leaderboard":"https://os-world.github.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen-CUA","top_percent":86.2,"top_model_id":"qwen-cua","top_generation":"Qwen-CUA","top_model_base":"Qwen-CUA","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":87,"total_models":3854,"placements":[{"place":1,"model":"qwen-cua","company":"qwen","family":"Qwen","version":"Qwen-CUA","score":86.2},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.1},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86},{"place":4,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":85.4},{"place":5,"model":"holo4-27b","company":"hcompany","family":"Holo","version":"Holo4","score":85.2},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85},{"place":7,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85},{"place":8,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":84.8},{"place":9,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.3},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":83.4},{"place":11,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.4},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.2},{"place":13,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":83},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83},{"place":15,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":82.8},{"place":16,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":82.2},{"place":17,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":82},{"place":18,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.2},{"place":19,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":80.8},{"place":20,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":80.8},{"place":21,"model":"holo4-35b-a3b","company":"hcompany","family":"Holo","version":"Holo4","score":80.8},{"place":22,"model":"ui-venus-2-27b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":80.5},{"place":23,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":80.4},{"place":24,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":79.6},{"place":25,"model":"qwen-ui-agent-27b","company":"qwen","family":"Qwen","version":"Qwen-UI-Agent","score":79.5},{"place":26,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":79},{"place":27,"model":"holo3-122b-a10b","company":"hcompany","family":"Holo","version":"Holo3","score":78.9},{"place":28,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":78.7},{"place":29,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":78.5},{"place":30,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":78.4},{"place":31,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":78},{"place":32,"model":"holo3-35b-a3b","company":"hcompany","family":"Holo","version":"Holo3","score":77.8},{"place":33,"model":"ui-mate-27b","company":"tencent","family":"UI-Mate","version":"UI-Mate","score":77},{"place":34,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.7},{"place":35,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.2},{"place":36,"model":"mai-gym-9b","company":"tongyi","family":"MAI-Gym","version":"MAI-Gym","score":76.2},{"place":37,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75.6},{"place":38,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":75.2},{"place":39,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":75},{"place":40,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":75},{"place":41,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":74},{"place":42,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":74},{"place":43,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":73.3},{"place":44,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":73.1},{"place":45,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":73.1},{"place":46,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":72.7},{"place":47,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":72.6},{"place":48,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":72.5},{"place":49,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":72.1},{"place":50,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":71.2},{"place":51,"model":"ui-venus-2-9b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":70.8},{"place":52,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.3},{"place":53,"model":"ui-mate-9b","company":"tencent","family":"UI-Mate","version":"UI-Mate","score":66.2},{"place":54,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":65.9},{"place":55,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":65.1},{"place":56,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":64.7},{"place":57,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":64.7},{"place":58,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.4},{"place":59,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64},{"place":60,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.9},{"place":61,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.3},{"place":62,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.3},{"place":63,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.9},{"place":64,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62.5},{"place":65,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":62.3},{"place":66,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.2},{"place":67,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.1},{"place":68,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":62},{"place":69,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":61.9},{"place":70,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.6},{"place":71,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.4},{"place":72,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.5},{"place":73,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58},{"place":74,"model":"evocua-32b-20260105","company":"meituan","family":"EvoCUA","version":"EvoCUA-20260105","score":56.7},{"place":75,"model":"gui-owl-1.5-32b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl-1.5","score":56.5},{"place":76,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.2},{"place":77,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":55.8},{"place":78,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.5},{"place":79,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.3},{"place":80,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.2},{"place":81,"model":"deepminer-mano-72b","company":"deepminer","family":"Mano","version":"Mano","score":53.9},{"place":82,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":53.3},{"place":83,"model":"ui-tars-2","company":"bytedance","family":"UI-TARS","version":"UI-TARS-2","score":53.1},{"place":84,"model":"gui-owl-1.5-8b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl-1.5","score":52.9},{"place":85,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.5},{"place":86,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":51.14},{"place":87,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.7},{"place":88,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":47.3},{"place":89,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":47.3},{"place":90,"model":"evocua-8b-20260105","company":"meituan","family":"EvoCUA","version":"EvoCUA-20260105","score":46.1},{"place":91,"model":"opencua-72b","company":"xlang","family":"OpenCUA","version":"OpenCUA","score":45},{"place":92,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":42},{"place":93,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.8},{"place":94,"model":"qwen3-vl-flash","company":"qwen","family":"Qwen3-VL","version":"Qwen3-VL","score":41.6},{"place":95,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":40.1},{"place":96,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":39},{"place":97,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":38.2},{"place":98,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":38.2},{"place":99,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":38.2},{"place":100,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":38.1},{"place":101,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":37.9},{"place":102,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":37.9},{"place":103,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.6},{"place":104,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":33.9},{"place":105,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.6},{"place":106,"model":"llada-ui","company":"antgroup","family":"LLaDA","version":"LLaDA-UI","score":29.4},{"place":107,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":14.78},{"place":108,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":3}]},{"id":"osworld2","name":"OSWorld2","topic":"GUI agents","description":"Second-generation OSWorld GUI agent benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-4.5V","top_percent":35.8,"top_model_id":"glm-4.5v","top_generation":"GLM 4.5V","top_model_base":"GLM 4.5V","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":35.8},{"place":2,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":14.9},{"place":3,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":8.2},{"place":4,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":6.2}]},{"id":"ovbench","name":"OVBench","topic":"Open-vocabulary streaming","description":"Open-vocabulary benchmark for streaming video understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":70,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":70},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":69.7},{"place":3,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":69.2},{"place":4,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":65.5},{"place":5,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":65.1},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":63.5},{"place":7,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.2},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.7},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.2},{"place":10,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":60.1},{"place":11,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":60},{"place":12,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":59.2},{"place":13,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":58.9},{"place":14,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":58.8},{"place":15,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":56.5},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52},{"place":17,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":49.91},{"place":18,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":49.3}]},{"id":"ovisocr-kie-inhouse","name":"OvisOCR In-house KIE Bench","topic":"Key information extraction","description":"OvisOCR team in-house key information extraction benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OvisOCR3","top_percent":77.73,"top_model_id":"ovisocr3","top_generation":"OvisOCR3","top_model_base":"OvisOCR3","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":77.73},{"place":2,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":75.96},{"place":3,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":75.68},{"place":4,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":75.25},{"place":5,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.9}]},{"id":"ovobench","name":"OVOBench","topic":"Streaming video QA","description":"Streaming video QA benchmark with open-vocabulary queries.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":80.7,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.7},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":79.2},{"place":3,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77},{"place":4,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":76.7},{"place":5,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":75.4},{"place":6,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":72.6},{"place":7,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":72.3},{"place":8,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":71.6},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.9},{"place":10,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":70.4},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":70.1},{"place":12,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":68.7},{"place":13,"model":"realtime-venus-omni","company":"antgroup","family":"Realtime-Venus","version":"Realtime-Venus","score":64.7},{"place":14,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":64.5},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.1},{"place":16,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":61.4},{"place":17,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":60.7},{"place":18,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":59.2},{"place":19,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":57.89},{"place":20,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.2},{"place":21,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":56.7},{"place":22,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55},{"place":23,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":53.8},{"place":24,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":51.8},{"place":25,"model":"av-flamingo-7b","company":"nvidia","family":"Audio Flamingo","version":"AV-Flamingo","score":51.5},{"place":26,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.8},{"place":27,"model":"mmduet2-3b","company":"pku","family":"MMDuet","version":"MMDuet2","score":47.6},{"place":28,"model":"video-salmonn-2-plus-7b","company":"tsinghua","family":"video-SALMONN","version":"video-SALMONN 2+","score":46.8},{"place":29,"model":"livestar-8b","company":"livestar","family":"LiveStar","version":"LiveStar","score":38}]},{"id":"p3m-500-np-mad","name":"P3M-500-NP (Box) Matting (MAD)","topic":"Image matting","description":"P3M-500-NP (Box): box-prompted portrait matting; mean absolute difference x10^3 (lower is better).","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"mad","stars":"","top_model":"WeVisOne-VL-2B","top_percent":6.6,"top_model_id":"wevisone-vl-2b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-2B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":6.6},{"place":2,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":7.3}]},{"id":"pagentbench","name":"PAgentBench","topic":"Personal assistant agents","description":"iFlytek in-house Personal Assistant Benchmark: task management, file operations and system interactions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Spark-X2.6-4B","top_percent":74.1,"top_model_id":"spark-x2.6-4b","top_generation":"Spark X2.6","top_model_base":"Spark-X2.6-4B","top_model_family":"Spark","top_company":"iflytek","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":74.1},{"place":2,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":59.4},{"place":3,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.8},{"place":4,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.8},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.4},{"place":6,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37}]},{"id":"paper-bench-code-dev","name":"PaperBench Code-Dev","topic":"Code understanding","description":"PaperBench developer subset measuring code reasoning accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":93,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":90.5},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.8},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80.3},{"place":5,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":64.8},{"place":6,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":43.3},{"place":7,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":29.9},{"place":8,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":27.8},{"place":9,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.2},{"place":10,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":12.2},{"place":11,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":5.7}]},{"id":"paperbench","name":"PaperBench","topic":"Research paper understanding","description":"Benchmark for understanding and reasoning over research papers.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":94.1,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.1},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":92.8},{"place":3,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":89.6},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.9},{"place":5,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.4},{"place":6,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":87},{"place":7,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":86.9},{"place":8,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.5},{"place":9,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.9},{"place":10,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":64.2},{"place":11,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":63.7},{"place":12,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":63.6},{"place":13,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.5},{"place":14,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":63.2},{"place":15,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":58.5},{"place":16,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":57.5},{"place":17,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":54.6},{"place":18,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":53.8},{"place":19,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":53.6},{"place":20,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":52.6},{"place":21,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":52.5},{"place":22,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.4},{"place":23,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":49.1},{"place":24,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":47.1},{"place":25,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":46.7},{"place":26,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40.4},{"place":27,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":36.7},{"place":28,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":33.9},{"place":29,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":30.7},{"place":30,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":30.6},{"place":31,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":20.5},{"place":32,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":17.3},{"place":33,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":14.8}]},{"id":"parsebench","name":"ParseBench","topic":"Document parsing","description":"Document-parsing benchmark covering tables, charts, content faithfulness, semantic formatting and visual grounding; overall over 5 categories.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LightOnOCR-3-4B","top_percent":75.1,"top_model_id":"lightonocr-3-4b","top_generation":"LightOnOCR-3","top_model_base":"LightOnOCR-3 4B","top_model_family":"LightOnOCR","top_company":"lighton","top_open_source":1,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"lightonocr-3-4b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":75.1},{"place":2,"model":"lightonocr-3-0.8b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":74.6},{"place":3,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":74.3},{"place":4,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":72.2},{"place":5,"model":"lightonocr-3-1b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-3","score":71.4},{"place":6,"model":"chandra-ocr-2","company":"chandra","family":"Chandra OCR","version":"Chandra OCR 2","score":70.1},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":69.1},{"place":8,"model":"mistral-ocr-4.1","company":"mistral","family":"Mistral OCR","version":"Mistral OCR","score":68.2},{"place":9,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":66},{"place":10,"model":"surya-ocr-2","company":"datalab","family":"Surya OCR","version":"Surya OCR 2","score":64.8},{"place":11,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":55.8},{"place":12,"model":"lightonocr-2-1b","company":"lighton","family":"LightOnOCR","version":"LightOnOCR-2","score":48},{"place":13,"model":"jina-ocr-v1","company":"jina","family":"jina-ocr","version":"jina-ocr-v1","score":45.9},{"place":14,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":45.9},{"place":15,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":41.2}]},{"id":"part-affordance","name":"Part-Affordance","topic":"Embodied reasoning","description":"Part-level affordance grounding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"PhysBrain1.5-8B","top_percent":84,"top_model_id":"physbrain1.5-8b","top_generation":"PhysBrain 1.5","top_model_base":"PhysBrain 1.5 8B","top_model_family":"PhysBrain","top_company":"deepcybo","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":84},{"place":2,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":83.7},{"place":3,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":83.4},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":78.1},{"place":5,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":64.7},{"place":6,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":62.8},{"place":7,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":61.9},{"place":8,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.4},{"place":9,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":55},{"place":10,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":40.5},{"place":11,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":36.3},{"place":12,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":33.3},{"place":13,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":24.7}]},{"id":"pathvqa","name":"PathVQA","topic":"Medical QA","description":"Pathology visual question answering.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedMO-4B-Next","top_percent":73.3,"top_model_id":"medmo-4b-next","top_generation":"MedMO-Next","top_model_base":"MedMO","top_model_family":"MedMO","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":73.3},{"place":2,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":56.5},{"place":3,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":56.3},{"place":4,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":56.3},{"place":5,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":42.4},{"place":6,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":41.9},{"place":7,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":41}]},{"id":"paws-x","name":"PAWS-X","topic":"Paraphrase identification","description":"Cross-lingual adversarial paraphrase identification.","url":"https://github.com/google-research-datasets/paws","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"d1-omni-600M","top_percent":79.5,"top_model_id":"d1-omni-600m","top_generation":"d1","top_model_base":"d1-omni-600M","top_model_family":"d1","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":79.5},{"place":2,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":76.9},{"place":3,"model":"mapika-decider-4b","company":"mapika","family":"Decider","version":"Decider","score":69.8},{"place":4,"model":"mapika-decider-2b","company":"mapika","family":"Decider","version":"Decider","score":59.5}]},{"id":"penguinscrolls","name":"PenguinScrolls","topic":"Long-context eval","description":"Long-context reading comprehension and reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Hunyuan-Large-Instruct","top_percent":85.23,"top_model_id":"hunyuan-large-instruct","top_generation":"Hunyuan-Large","top_model_base":"Hunyuan-Large","top_model_family":"Hunyuan","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"hunyuan-large-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":85.23},{"place":2,"model":"hunyuan-4b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":83.1},{"place":3,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":69.37}]},{"id":"perceptionbench","name":"PerceptionBench","topic":"Visual perception","description":"Moonshot benchmark of atomic visual perception capabilities in multimodal LLMs.","url":"https://github.com/MoonshotAI/PerceptionBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.5 Flash","top_percent":60.9,"top_model_id":"gemini-3.5-flash","top_generation":"Gemini 3.5","top_model_base":"Gemini 3.5 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":60.9},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":59.7},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":58.5},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57.2},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":55.8},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":55.7},{"place":7,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":53.4},{"place":8,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":52.3},{"place":9,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":48.3},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":47.2},{"place":11,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":37.9}]},{"id":"perceptiontest","name":"Perception Test","topic":"Video understanding","description":"DeepMind Perception Test: multimodal video benchmark of perception and reasoning skills (MC video QA).","url":"https://github.com/google-deepmind/perception_test","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"PLM-8B","top_percent":82.7,"top_model_id":"plm-8b","top_generation":"PLM","top_model_base":"PLM 8B","top_model_family":"PLM","top_company":"unknown","top_open_source":1,"lower_is_better":false,"bench_models":37,"total_models":3854,"placements":[{"place":1,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":82.7},{"place":2,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":82.3},{"place":3,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":82.1},{"place":4,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":81.3},{"place":5,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":81},{"place":6,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":79.6},{"place":7,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":79.4},{"place":8,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":79.3},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.4},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":77.6},{"place":11,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":76.5},{"place":12,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":75.89},{"place":13,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.7},{"place":14,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":74.2},{"place":15,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":72.7},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.7},{"place":17,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":72},{"place":18,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":70.9},{"place":19,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.7},{"place":20,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":68.8},{"place":21,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":68.1},{"place":22,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":68},{"place":23,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":67.52},{"place":24,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":67.48},{"place":25,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":65.88},{"place":26,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.3},{"place":27,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":64.2},{"place":28,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":62.3},{"place":29,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":62.3},{"place":30,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":56.8},{"place":31,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":56.2},{"place":32,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":53.9},{"place":33,"model":"videollama2-7b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":51.4},{"place":34,"model":"llava-next-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":48.8},{"place":35,"model":"videochat2-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":47.3},{"place":36,"model":"video-llava-7b","company":"pku","family":"Video-LLaVA","version":"Video-LLaVA","score":44.3},{"place":37,"model":"anygpt","company":"fudan","family":"AnyGPT","version":"AnyGPT","score":29.1}]},{"id":"permemsafe","name":"PerMemSafe","topic":"Memory safety","description":"Personal-memory safety benchmark: appropriate use and protection of stored user memories.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MemT-1.0-Nano","top_percent":38.7,"top_model_id":"memt-1.0-nano","top_generation":"MemT-1.0","top_model_base":"MemT-1.0-Nano","top_model_family":"MemT","top_company":"memtensor","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"memt-1.0-nano","company":"memtensor","family":"MemT","version":"MemT-1.0","score":38.7},{"place":2,"model":"memt-1.0-flash","company":"memtensor","family":"MemT","version":"MemT-1.0","score":33.5}]},{"id":"personamem","name":"PersonaMem","topic":"Personalization","description":"Evaluates whether models track evolving user personas and preferences across long interaction histories.","url":"https://github.com/bowen-upenn/PersonaMem","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2504.14225","metric":"percent","stars":"","top_model":"MemT-1.0-Flash","top_percent":61.6,"top_model_id":"memt-1.0-flash","top_generation":"MemT-1.0","top_model_base":"MemT-1.0-Flash","top_model_family":"MemT","top_company":"memtensor","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"memt-1.0-flash","company":"memtensor","family":"MemT","version":"MemT-1.0","score":61.6},{"place":2,"model":"memt-1.0-nano","company":"memtensor","family":"MemT","version":"MemT-1.0","score":52.3}]},{"id":"perspective-bench","name":"Perspective Bench","topic":"Value alignment","description":"Re-alignment score over 80 prompts measuring adherence to the Public AI Constitution (balanced perspectives).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Snowdon1.1-Small","top_percent":93,"top_model_id":"snowdon-1.1-small","top_generation":"Snowdon-1.1","top_model_base":"Snowdon 1.1 Small","top_model_family":"Snowdon","top_company":"tri-fair-lab","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":93},{"place":2,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":16}]},{"id":"phage-plasmid-coevolution","name":"Phage-Plasmid Co-evolution","topic":"Biosecurity","description":"Predict future amino-acid mutations in a phage-plasmid system; pooled exact-mutation negative log-likelihood (lower is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"nll","stars":"","top_model":"GPT-6 Luna (2026-10-07)","top_percent":10.7,"top_model_id":"gpt-6-luna-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":true,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":10.7},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":10.8229},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":11.35},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":12.58},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":12.9},{"place":6,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":12.946},{"place":7,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":12.95},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":13.13}]},{"id":"phishnchips","name":"PhishNChips","topic":"Phishing detection","description":"Phishing vs legitimate email-and-link decisions; accuracy (Jev Decision Index suite, posed as typed decisions).","url":"https://huggingface.co/spaces/multimodalart/jev-decision-index","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"DiffusionGemma Jev","top_percent":85.4,"top_model_id":"diffusiongemma-jev","top_generation":"DiffusionGemma Jev","top_model_base":"DiffusionGemma Jev","top_model_family":"DiffusionGemma Jev","top_company":"unknown","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":85.4},{"place":2,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":83.8},{"place":3,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":83},{"place":4,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":79.6},{"place":5,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":78.9},{"place":6,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":75},{"place":7,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":74.7},{"place":8,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":73.9},{"place":9,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":73.2},{"place":10,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":72.5},{"place":11,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":72.4},{"place":12,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":70},{"place":13,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":68.9},{"place":14,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":68.8},{"place":15,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":67.8},{"place":16,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":67},{"place":17,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":65.6},{"place":18,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":62.5},{"place":19,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":61.9},{"place":20,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":61.5},{"place":21,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":61.4},{"place":22,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":60},{"place":23,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59.8},{"place":24,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":55.8},{"place":25,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":54.9},{"place":26,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":53.9},{"place":27,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":53.8},{"place":28,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":50.8},{"place":29,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":50.8},{"place":30,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":50.7},{"place":31,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":50.6},{"place":32,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":50.1},{"place":33,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":50},{"place":34,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":50},{"place":35,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":50},{"place":36,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":50},{"place":37,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":45.9},{"place":38,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":44.8}]},{"id":"phybench","name":"PHYBench","topic":"Physics reasoning","description":"Physics reasoning and calculation benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":82,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":33,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":79.6},{"place":4,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":77.5},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":77.5},{"place":6,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":77.4},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":77},{"place":8,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.6},{"place":9,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":76.5},{"place":10,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.4},{"place":11,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":74},{"place":12,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":74},{"place":13,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":73},{"place":14,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":71.5},{"place":15,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":71.4},{"place":16,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":70.9},{"place":17,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69},{"place":18,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":60},{"place":19,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":59},{"place":20,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":56},{"place":21,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":48},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":48},{"place":23,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":41},{"place":24,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":40},{"place":25,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":31},{"place":26,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":30.06},{"place":27,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":29.84},{"place":28,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":28.23},{"place":29,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":27.67},{"place":30,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":26.04},{"place":31,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":14.59},{"place":32,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":13.05},{"place":33,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":12.75},{"place":34,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":11.7},{"place":35,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":9.76}]},{"id":"phyx","name":"PhyX","topic":"Physics reasoning (multimodal)","description":"Multimodal physics reasoning benchmark (PhyX).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":83.5,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83.5},{"place":2,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":80},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":79.4},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":79.1},{"place":5,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":71.7},{"place":6,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":59.45},{"place":7,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.67},{"place":8,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":56},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":54.2},{"place":10,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":52.28},{"place":11,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":50.51}]},{"id":"pinchbench","name":"PinchBench","topic":"Agentic assistant tasks","description":"Benchmark of OpenClaw agent task success across real-world personal-assistant tasks.","url":"https://pinchbench.com/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"KAT-Coder-V2.5-Dev","top_percent":93.43,"top_model_id":"kat-coder-v2.5-dev","top_generation":"KAT-Coder V2.5","top_model_base":"KAT-Coder V2.5 Dev","top_model_family":"KAT","top_company":"kuaishou","top_open_source":1,"lower_is_better":false,"bench_models":47,"total_models":3854,"placements":[{"place":1,"model":"kat-coder-v2.5-dev","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":93.43},{"place":2,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.21},{"place":3,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":91.62},{"place":4,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":91.3},{"place":5,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.71},{"place":6,"model":"nemotron-3.5-bolt-74b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":90.35},{"place":7,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":90.2},{"place":8,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90},{"place":9,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":90},{"place":10,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89.93},{"place":11,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.75},{"place":12,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.6},{"place":13,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":88.6},{"place":14,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":88.22},{"place":15,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":88.2},{"place":16,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":88.07},{"place":17,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":87.3},{"place":18,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.05},{"place":19,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.6},{"place":20,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":86.6},{"place":21,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.77},{"place":22,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":85.53},{"place":23,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":85.37},{"place":24,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":85},{"place":25,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.77},{"place":26,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":84.2},{"place":27,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84.13},{"place":28,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":83.43},{"place":29,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":83.18},{"place":30,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":82.25},{"place":31,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":82.01},{"place":32,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":81.2},{"place":33,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":80.36},{"place":34,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":79.37},{"place":35,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":77.6},{"place":36,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":77.33},{"place":37,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.12},{"place":38,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":76.9},{"place":39,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":75.07},{"place":40,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.7},{"place":41,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":74.7},{"place":42,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.55},{"place":43,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":72.3},{"place":44,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.45},{"place":45,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":71.35},{"place":46,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.26},{"place":47,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.19},{"place":48,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":68.22},{"place":49,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":68.22},{"place":50,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.2},{"place":51,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":66.78},{"place":52,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":66.11},{"place":53,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":64.83},{"place":54,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.9},{"place":55,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":62.37},{"place":56,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":58.89},{"place":57,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":57.2},{"place":58,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":56.93},{"place":59,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55.09},{"place":60,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53.8},{"place":61,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47.6},{"place":62,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.24},{"place":63,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.3}]},{"id":"pinchbench-avg","name":"PinchBench (Avg)","topic":"Agent tasks (OpenClaw)","description":"PinchBench OpenClaw-style agent task benchmark, average score across runs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"KAT-Coder-Pro V2.5","top_percent":94.9,"top_model_id":"kat-coder-pro-v2.5","top_generation":"KAT-Coder V2.5","top_model_base":"KAT-Coder Pro","top_model_family":"KAT","top_company":"kuaishou","top_open_source":0,"lower_is_better":false,"bench_models":37,"total_models":3854,"placements":[{"place":1,"model":"kat-coder-pro-v2.5","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":94.9},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":93.5},{"place":3,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":88.9},{"place":4,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":87.6},{"place":5,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":87},{"place":6,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":85.6},{"place":7,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":85.48},{"place":8,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.38},{"place":9,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":85.24},{"place":10,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":84},{"place":11,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":83.29},{"place":12,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82.9},{"place":13,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":82.5},{"place":14,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82.3},{"place":15,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":81.9},{"place":16,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":81.8},{"place":17,"model":"llada2.2-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":81.66},{"place":18,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":81.6},{"place":19,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":81.5},{"place":20,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":81.3},{"place":21,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":81.2},{"place":22,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":81.1},{"place":23,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":81},{"place":24,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":80.7},{"place":25,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":80.7},{"place":26,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":80.3},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80},{"place":28,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":79.95},{"place":29,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":79.2},{"place":30,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":79.2},{"place":31,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":77},{"place":32,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":75.9},{"place":33,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":75.83},{"place":34,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":74.95},{"place":35,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":73.4},{"place":36,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.1},{"place":37,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":72.6},{"place":38,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":71.4},{"place":39,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":70.3},{"place":40,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":67.7},{"place":41,"model":"llada2.2-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":62.33},{"place":42,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":62.1},{"place":43,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":52}]},{"id":"pinchbench-best","name":"PinchBench (Best)","topic":"Agent tasks (OpenClaw)","description":"PinchBench OpenClaw-style agent task benchmark, best-of-runs score.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":93.3,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":93.3},{"place":2,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":91.9},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":90.5},{"place":4,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":89.8},{"place":5,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":88.7},{"place":6,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":87.4},{"place":7,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":87.1},{"place":8,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":87},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":86.7},{"place":10,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":86.5},{"place":11,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":86.4},{"place":12,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.8}]},{"id":"piobench","name":"PIOBench","topic":"Embodied reasoning","description":"Pointing / interaction-object grounding benchmark for embodied VLMs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.6 Flash","top_percent":80.9,"top_model_id":"gemini-3.6-flash","top_generation":"Gemini 3.6","top_model_base":"Gemini 3.6 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":80.9},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":79.7},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":71.6},{"place":4,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":68.3},{"place":5,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":64.8},{"place":6,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":64.3},{"place":7,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":62.6},{"place":8,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":62.3},{"place":9,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":61.5},{"place":10,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":60.4},{"place":11,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":56.2},{"place":12,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":54.4},{"place":13,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.7}]},{"id":"piqa","name":"PIQA","topic":"Physical commonsense","description":"Physical commonsense about everyday tasks and object affordances.","url":"https://github.com/ybisk/piqa","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LLaDA2.0 Flash","top_percent":96.5,"top_model_id":"llada2.0-flash","top_generation":"LLaDA 2.0","top_model_base":"LLaDA 2.0 Flash","top_model_family":"LLaDA","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":207,"total_models":3854,"placements":[{"place":1,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":96.5},{"place":2,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":95.1},{"place":3,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":92.44},{"place":4,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":92.17},{"place":5,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":91.95},{"place":6,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.9},{"place":7,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":91.57},{"place":8,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":89.9},{"place":9,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":89.8},{"place":10,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":89.5},{"place":11,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.4},{"place":12,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":89.2},{"place":13,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.5},{"place":14,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.3},{"place":15,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":88.3},{"place":16,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":88},{"place":17,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":87.54},{"place":18,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":87.2},{"place":19,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":87.1},{"place":20,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.1},{"place":21,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":86.89},{"place":22,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":86.8},{"place":23,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86.51},{"place":24,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":86.1},{"place":25,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":85.9},{"place":26,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.9},{"place":27,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":85.7},{"place":28,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":85.7},{"place":29,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.6},{"place":30,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.6},{"place":31,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.47},{"place":32,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85.47},{"place":33,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":85.3},{"place":34,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":85.2},{"place":35,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":85.14},{"place":36,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.09},{"place":37,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":85.09},{"place":38,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":85.09},{"place":39,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":85},{"place":40,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":84.93},{"place":41,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":84.87},{"place":42,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":84.82},{"place":43,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":84.8},{"place":44,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":84.71},{"place":45,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":84.7},{"place":46,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":84.6},{"place":47,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":84.6},{"place":48,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":84.5},{"place":49,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":84.39},{"place":50,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.33},{"place":51,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":84.3},{"place":52,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":84.22},{"place":53,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":84.22},{"place":54,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":84.2},{"place":55,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":84.1},{"place":56,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":84.1},{"place":57,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":84},{"place":58,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":83.9},{"place":59,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":83.9},{"place":60,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":83.84},{"place":61,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":83.8},{"place":62,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":83.8},{"place":63,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.79},{"place":64,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":83.7},{"place":65,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":83.6},{"place":66,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":83.6},{"place":67,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":83.6},{"place":68,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":83.57},{"place":69,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.5},{"place":70,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":83.3},{"place":71,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":83.3},{"place":72,"model":"marin-32b-base","company":"marin","family":"Marin","version":"Marin 32B","score":83.3},{"place":73,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83.3},{"place":74,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":83.3},{"place":75,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":83.3},{"place":76,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":83.1},{"place":77,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":83.1},{"place":78,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":83},{"place":79,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":83},{"place":80,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":82.8},{"place":81,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":82.8},{"place":82,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":82.8},{"place":83,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":82.8},{"place":84,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":82.7},{"place":85,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":82.6},{"place":86,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":82.6},{"place":87,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.6},{"place":88,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.54},{"place":89,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":82.54},{"place":90,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":82.43},{"place":91,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.4},{"place":92,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":82.3},{"place":93,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":82.3},{"place":94,"model":"apertus-v1.5-70b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":82.3},{"place":95,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":82.21},{"place":96,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":82.2},{"place":97,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":82.2},{"place":98,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":82.2},{"place":99,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":82.15},{"place":100,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":82},{"place":101,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":81.9},{"place":102,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":81.8},{"place":103,"model":"gopher-280b","company":"google","family":"Gopher","version":"Gopher","score":81.8},{"place":104,"model":"chinchilla-70b","company":"google","family":"Chinchilla","version":"Chinchilla","score":81.8},{"place":105,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":81.8},{"place":106,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":81.7},{"place":107,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":81.7},{"place":108,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":81.6},{"place":109,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":81.5},{"place":110,"model":"palm-cont-62b","company":"google","family":"PaLM","version":"PaLM","score":81.4},{"place":111,"model":"eurollm-22b-base","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":81.4},{"place":112,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":81.4},{"place":113,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":81.34},{"place":114,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":81.3},{"place":115,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":81.2},{"place":116,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":81.2},{"place":117,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":81.2},{"place":118,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":81.18},{"place":119,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":81.12},{"place":120,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":81.07},{"place":121,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":81},{"place":122,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":81},{"place":123,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":80.8},{"place":124,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":80.8},{"place":125,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":80.6},{"place":126,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":80.6},{"place":127,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":80.52},{"place":128,"model":"palm-62b","company":"google","family":"PaLM","version":"PaLM","score":80.5},{"place":129,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":80.5},{"place":130,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.5},{"place":131,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":80.5},{"place":132,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":80.4},{"place":133,"model":"apertus-v1.5-8b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":80.3},{"place":134,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":80.3},{"place":135,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":80.25},{"place":136,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":80.25},{"place":137,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":80.25},{"place":138,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":80.2},{"place":139,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":80.2},{"place":140,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":80.2},{"place":141,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":80.1},{"place":142,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":80.1},{"place":143,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":80.1},{"place":144,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":80.1},{"place":145,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":80.09},{"place":146,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":80.09},{"place":147,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":80},{"place":148,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":79.9},{"place":149,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":79.9},{"place":150,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":79.8},{"place":151,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":79.8},{"place":152,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":79.8},{"place":153,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":79.8},{"place":154,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":79.76},{"place":155,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":79.71},{"place":156,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":79.7},{"place":157,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":79.7},{"place":158,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":79.6},{"place":159,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":79.5},{"place":160,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":79.5},{"place":161,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":79.4},{"place":162,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":79.4},{"place":163,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":79.33},{"place":164,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":79.3},{"place":165,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":79.21},{"place":166,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":79.2},{"place":167,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":79.2},{"place":168,"model":"glm4-9b","company":"zai","family":"GLM","version":"GLM 4","score":79.1},{"place":169,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":79},{"place":170,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":79},{"place":171,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":78.8},{"place":172,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":78.8},{"place":173,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":78.8},{"place":174,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":78.78},{"place":175,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":78.7},{"place":176,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":78.67},{"place":177,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":78.5},{"place":178,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":78.4},{"place":179,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":78.4},{"place":180,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":78.3},{"place":181,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":78.3},{"place":182,"model":"apertus-v1.1-4b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":78.18},{"place":183,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":78.18},{"place":184,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":78.18},{"place":185,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":78.1},{"place":186,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":78.07},{"place":187,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":78},{"place":188,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":77.97},{"place":189,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":77.9},{"place":190,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":77.9},{"place":191,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":77.9},{"place":192,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":77.9},{"place":193,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":77.7},{"place":194,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":77.7},{"place":195,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":77.6},{"place":196,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":77.6},{"place":197,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":77.6},{"place":198,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":77.48},{"place":199,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":77.42},{"place":200,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":77.3},{"place":201,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":77.2},{"place":202,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":77.1},{"place":203,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":76.82},{"place":204,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.7},{"place":205,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":76.7},{"place":206,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":76.7},{"place":207,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":76.7},{"place":208,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":76.55},{"place":209,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":76.55},{"place":210,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":76.3},{"place":211,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":76.2},{"place":212,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":76.2},{"place":213,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":76.17},{"place":214,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.1},{"place":215,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":76.06},{"place":216,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":76.01},{"place":217,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":76},{"place":218,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":76},{"place":219,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":75.79},{"place":220,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":75.52},{"place":221,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":75.3},{"place":222,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":75.24},{"place":223,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":75.2},{"place":224,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":75.14},{"place":225,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":74.92},{"place":226,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":74.8},{"place":227,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":74.8},{"place":228,"model":"apertus-v1.1-1.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":74.54},{"place":229,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":74.4},{"place":230,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":74.3},{"place":231,"model":"pythia-2.8b","company":"eleutherai","family":"Pythia","version":"Pythia","score":74.1},{"place":232,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":74.1},{"place":233,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":74},{"place":234,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":73.94},{"place":235,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":73.9},{"place":236,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":73.8},{"place":237,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":73.5},{"place":238,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":73.3},{"place":239,"model":"qwen2.5-1.5b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.2},{"place":240,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":73.2},{"place":241,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":72.8},{"place":242,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.8},{"place":243,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":72.69},{"place":244,"model":"llama-1b","company":"meta","family":"Llama","version":"Llama 1","score":72.3},{"place":245,"model":"pythia-1.4b","company":"eleutherai","family":"Pythia","version":"Pythia","score":72},{"place":246,"model":"smollm1-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":71.6},{"place":247,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":71.6},{"place":248,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":71.4},{"place":249,"model":"apertus-v1.1-0.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":71.27},{"place":250,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":70.29},{"place":251,"model":"pythia-1b","company":"eleutherai","family":"Pythia","version":"Pythia","score":70},{"place":252,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":69.6},{"place":253,"model":"chatglm2-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":69.6},{"place":254,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.4},{"place":255,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":68.4},{"place":256,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":68.4},{"place":257,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":67.7},{"place":258,"model":"pythia-410m","company":"eleutherai","family":"Pythia","version":"Pythia","score":67.5},{"place":259,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":67.1},{"place":260,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":66.5},{"place":261,"model":"smollm2-135m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":66.3},{"place":262,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.2},{"place":263,"model":"chatglm-6b","company":"zai","family":"ChatGLM","version":"ChatGLM","score":65.7},{"place":264,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":65.45},{"place":265,"model":"trlm-135m","company":"loka","family":"TRLM","version":"TRLM","score":64.91},{"place":266,"model":"pythia-160m","company":"eleutherai","family":"Pythia","version":"Pythia","score":61.8},{"place":267,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":60.99},{"place":268,"model":"pythia-70m","company":"eleutherai","family":"Pythia","version":"Pythia","score":59.8},{"place":269,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":58.49},{"place":270,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":53.4},{"place":271,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":50.2}]},{"id":"pixmo-points","name":"PixMo-Points","topic":"Embodied reasoning","description":"Pointing accuracy on the PixMo-Points evaluation set.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":75.2,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":75.2},{"place":2,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":74.8},{"place":3,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":74.7},{"place":4,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":73.2},{"place":5,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":72.9},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.2},{"place":7,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":68.6},{"place":8,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":65.6},{"place":9,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":65.3},{"place":10,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":62.2},{"place":11,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":60.5},{"place":12,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":57.3},{"place":13,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.7},{"place":14,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":55.8},{"place":15,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.7},{"place":16,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":52.3},{"place":17,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":51.5},{"place":18,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":29.9}]},{"id":"pixmocount","name":"PixmoCount","topic":"Visual counting","description":"Counting objects/instances in images (PixmoCount).","url":"https://huggingface.co/datasets/allenai/pixmo-count","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2409.17146v2","metric":"percent","stars":"","top_model":"Eagle2.5-8B","top_percent":90.2,"top_model_id":"eagle2.5-8b","top_generation":"Eagle 2.5","top_model_base":"Eagle2.5 8B","top_model_family":"Eagle","top_company":"unknown","top_open_source":1,"lower_is_better":false,"bench_models":71,"total_models":3854,"placements":[{"place":1,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":90.2},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90},{"place":3,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":89.6},{"place":4,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":88.9},{"place":5,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":88.9},{"place":6,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":88.5},{"place":7,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":88.1},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":88.1},{"place":9,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":88.1},{"place":10,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":87.71},{"place":11,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":87.6},{"place":12,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":87},{"place":13,"model":"ace-brain-0.6-9b","company":"ace-robotics","family":"ACE-Brain","version":"ACE-Brain-0.6","score":86.96},{"place":14,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":85.2},{"place":15,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":84.8},{"place":16,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.2},{"place":17,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":83.74},{"place":18,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.55},{"place":19,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":83.3},{"place":20,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":83.1},{"place":21,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":82.8},{"place":22,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":82.61},{"place":23,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.4},{"place":24,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":79.6},{"place":25,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":79.4},{"place":26,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":79.4},{"place":27,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":74.4},{"place":28,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.8},{"place":29,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":71.9},{"place":30,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":68},{"place":31,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":67.2},{"place":32,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":66.9},{"place":33,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.5},{"place":34,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65},{"place":35,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":64.3},{"place":36,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.9},{"place":37,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":63},{"place":38,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":62.8},{"place":39,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":62.4},{"place":40,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":62},{"place":41,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":61.9},{"place":42,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":61.1},{"place":43,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":60.7},{"place":44,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":60.7},{"place":45,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":60.7},{"place":46,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":60.7},{"place":47,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":60},{"place":48,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":59.6},{"place":49,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":58.5},{"place":50,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":58.3},{"place":51,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.3},{"place":52,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58},{"place":53,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":57.4},{"place":54,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":55.7},{"place":55,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":54.6},{"place":56,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":54.4},{"place":57,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":54.4},{"place":58,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":53.5},{"place":59,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":51.7},{"place":60,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":50.7},{"place":61,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":50.2},{"place":62,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":48.6},{"place":63,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":48},{"place":64,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":47.4},{"place":65,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":47.3},{"place":66,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":46.6},{"place":67,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":45.2},{"place":68,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":45},{"place":69,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":43.9},{"place":70,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":43.9},{"place":71,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":43.3},{"place":72,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":38.3},{"place":73,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":35.2},{"place":74,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":27.6}]},{"id":"plawbench","name":"PLawBench","topic":"Legal reasoning","description":"Legal-practice benchmark; Qwen evaluates it with gemini-3.1-pro-preview as judge.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":73.2,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.2},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":72.3},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.2},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.6},{"place":5,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":58.9}]},{"id":"pmc-vqa","name":"PMC-VQA","topic":"Medical VQA","description":"PubMed Central visual question answering benchmark for biomedical images.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedMO-4B-Next","top_percent":75.7,"top_model_id":"medmo-4b-next","top_generation":"MedMO-Next","top_model_base":"MedMO","top_model_family":"MedMO","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":75.7},{"place":2,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":74.1},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.2},{"place":4,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":64.3},{"place":5,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.2},{"place":6,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":63.4},{"place":7,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.3},{"place":8,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.3},{"place":9,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.2},{"place":10,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":62.7},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":62.5},{"place":12,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.4},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.3},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":62.3},{"place":15,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62},{"place":16,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.9},{"place":17,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":59.4},{"place":18,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59.2},{"place":19,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":58.9},{"place":20,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":58.7},{"place":21,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.9},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.9},{"place":23,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.5},{"place":24,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":55.3},{"place":25,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":54.2},{"place":26,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.5},{"place":27,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":50.6},{"place":28,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.8},{"place":29,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.8},{"place":30,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.4},{"place":31,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.4},{"place":32,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.2},{"place":33,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.4},{"place":34,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":37.8},{"place":35,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":36.3}]},{"id":"point-bench","name":"Point-Bench","topic":"Pointing and counting","description":"Benchmark for pointing and counting objects in images.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":85.5,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.5},{"place":2,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":77.3},{"place":3,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":76.9},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":76.5},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.9},{"place":6,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":73.3},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":71.9},{"place":8,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":71.9},{"place":9,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":71.6},{"place":10,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":70.7},{"place":11,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":69.9},{"place":12,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":69.6},{"place":13,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":68.7},{"place":14,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68.6},{"place":15,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":68.5},{"place":16,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":67.7},{"place":17,"model":"poivre-7b","company":"poivre","family":"Poivre","version":"Poivre","score":67.5},{"place":18,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":67.1},{"place":19,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":66.5},{"place":20,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":65.4},{"place":21,"model":"visionreasoner-7b","company":"cuhk","family":"VisionReasoner","version":"VisionReasoner","score":64.7},{"place":22,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":64.5},{"place":23,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.4},{"place":24,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":64.3},{"place":25,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.2},{"place":26,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.8},{"place":27,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":63.8},{"place":28,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.4},{"place":29,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":63.3},{"place":30,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":63},{"place":31,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":62.9},{"place":32,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.8},{"place":33,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":62.8},{"place":34,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.7},{"place":35,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.7},{"place":36,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.5},{"place":37,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":61.7},{"place":38,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":61.6},{"place":39,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.5},{"place":40,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":61.1},{"place":41,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":59.2},{"place":42,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":59},{"place":43,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":59},{"place":44,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.3},{"place":45,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":58},{"place":46,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":58},{"place":47,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":56.9},{"place":48,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":51.6},{"place":49,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":45.5},{"place":50,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":45.5},{"place":51,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":43.6},{"place":52,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":43},{"place":53,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":41.8},{"place":54,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.6},{"place":55,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":39.5},{"place":56,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":13.6},{"place":57,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":9.4}]},{"id":"pointarena","name":"PointArena","topic":"Visual grounding","description":"Language-guided pointing benchmark for multimodal models.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":75.36,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":75.36},{"place":2,"model":"ace-brain-0.6-9b","company":"ace-robotics","family":"ACE-Brain","version":"ACE-Brain-0.6","score":74.13},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":69.76},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":68.02},{"place":5,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":66.4},{"place":6,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":61.2}]},{"id":"polymath","name":"PolyMATH","topic":"Math reasoning","description":"Polyglot mathematics benchmark assessing cross-topic math reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.7-Max","top_percent":86.5,"top_model_id":"qwen3.7-max","top_generation":"Qwen3.7","top_model_base":"Qwen3.7 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":69,"total_models":3854,"placements":[{"place":1,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":86.5},{"place":2,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":84},{"place":3,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":82.7},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.6},{"place":5,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.9},{"place":6,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":80.2},{"place":7,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79},{"place":8,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":77.4},{"place":9,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":73.8},{"place":10,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.3},{"place":11,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72},{"place":12,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":71.3},{"place":13,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.2},{"place":14,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.9},{"place":15,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":67.6},{"place":16,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":67.3},{"place":17,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":65.2},{"place":18,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":65.1},{"place":19,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":64.7},{"place":20,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.4},{"place":21,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":62.5},{"place":22,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":62.4},{"place":23,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":60.1},{"place":24,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":60.1},{"place":25,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":59.5},{"place":26,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":57.4},{"place":27,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.3},{"place":28,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":56.3},{"place":29,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.7},{"place":30,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":54},{"place":31,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":54},{"place":32,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":52.8},{"place":33,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":52.6},{"place":34,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.9},{"place":35,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.7},{"place":36,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.1},{"place":37,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.2},{"place":38,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.9},{"place":39,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.8},{"place":40,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":49.8},{"place":41,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":48.7},{"place":42,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":47.4},{"place":43,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":47.2},{"place":44,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":47.1},{"place":45,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":46.2},{"place":46,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":45.9},{"place":47,"model":"marco-mini-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":44.7},{"place":48,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.3},{"place":49,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":43.1},{"place":50,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":43.1},{"place":51,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":43.1},{"place":52,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":39.3},{"place":53,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":37.9},{"place":54,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":35.5},{"place":55,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":31.1},{"place":56,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":30.9},{"place":57,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.4},{"place":58,"model":"marco-nano-instruct","company":"alibaba","family":"Marco","version":"Marco-MoE","score":29.6},{"place":59,"model":"lfm2-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2","score":29.3},{"place":60,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":28.9},{"place":61,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.8},{"place":62,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":27},{"place":63,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":26.5},{"place":64,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":26.4},{"place":65,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.1},{"place":66,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":25.5},{"place":67,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":25.5},{"place":68,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":25.2},{"place":69,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":23.4},{"place":70,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":22.5},{"place":71,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":18.8},{"place":72,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":18.7},{"place":73,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":16.3},{"place":74,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.2}]},{"id":"pop909-cl-decision","name":"POP909-CL (decision)","topic":"Music understanding","description":"Chord-label decisions over POP909 symbolic music; accuracy. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://huggingface.co/spaces/multimodalart/jev-decision-index","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"Bespoke-Nimble-9B-v3","top_percent":74.6,"top_model_id":"bespoke-nimble-9b-v3","top_generation":"v3","top_model_base":"Bespoke-Nimble-9B","top_model_family":"Bespoke-Nimble","top_company":"bespokelabs","top_open_source":1,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":74.6},{"place":2,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":70.5},{"place":3,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":62.9},{"place":4,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":61.6},{"place":5,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":40.3},{"place":6,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":36.5},{"place":7,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":31.9},{"place":8,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":27.2},{"place":9,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":25.3},{"place":10,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":22.9},{"place":11,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":21.7},{"place":12,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":20.5},{"place":13,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":19.7},{"place":14,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":18.1},{"place":15,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":16.4},{"place":16,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":15.8},{"place":17,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":14.6},{"place":18,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":14.1},{"place":19,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":10.9},{"place":20,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":10.8},{"place":21,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":8.6},{"place":22,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":7.9},{"place":23,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":7},{"place":24,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":6.9},{"place":25,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":5.1},{"place":26,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":2.6},{"place":27,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":2.5},{"place":28,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":2.3},{"place":29,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":1.7},{"place":30,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":1.6},{"place":31,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":1.6},{"place":32,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":1.6},{"place":33,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":1.4},{"place":34,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":1.1},{"place":35,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":0.9},{"place":36,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":0.8}]},{"id":"pope","name":"POPE","topic":"Hallucination detection","description":"Vision-language hallucination benchmark focusing on object existence verification.","url":"","leaderboard":"","github":"https://github.com/AoiDragon/POPE","paper":"https://arxiv.org/abs/2305.10355","metric":"percent","stars":"","top_model":"InternVL2.5-4B","top_percent":90.9,"top_model_id":"internvl2.5-4b","top_generation":"InternVL 2.5","top_model_base":"InternVL2.5 4B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":58,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":90.9},{"place":2,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":90.8},{"place":3,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":90.7},{"place":4,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":90.6},{"place":5,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":90.6},{"place":6,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":90.6},{"place":7,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":90.1},{"place":8,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":89.9},{"place":9,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.3},{"place":10,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":89.2},{"place":11,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":89.01},{"place":12,"model":"moondream-9b-a2b","company":"moondream","family":"Moondream","version":"Moondream 3","score":89},{"place":13,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":89},{"place":14,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":88.9},{"place":15,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":88.7},{"place":16,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.7},{"place":17,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.6},{"place":18,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":88.5},{"place":19,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":88.4},{"place":20,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":88.4},{"place":21,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":88.4},{"place":22,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":88.3},{"place":23,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.1},{"place":24,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":88.1},{"place":25,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":88.1},{"place":26,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":88},{"place":27,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":88},{"place":28,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":87.9},{"place":29,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":87.7},{"place":30,"model":"unified-io-2-xxl","company":"allenai","family":"Unified-IO","version":"Unified-IO 2","score":87.7},{"place":31,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":87.6},{"place":32,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":87.3},{"place":33,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":87.3},{"place":34,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":87.3},{"place":35,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":87.2},{"place":36,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":87.2},{"place":37,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":87.17},{"place":38,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":86.93},{"place":39,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":86.9},{"place":40,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":86.9},{"place":41,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":86.9},{"place":42,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":86.7},{"place":43,"model":"llava-next-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":86.5},{"place":44,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":86.4},{"place":45,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":86.2},{"place":46,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":86.17},{"place":47,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86},{"place":48,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":85.9},{"place":49,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":85.9},{"place":50,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":85.1},{"place":51,"model":"llava-phi","company":"midea","family":"LLaVA","version":"LLaVA-Phi","score":85},{"place":52,"model":"mobilevlm-3b","company":"meituan","family":"MobileVLM","version":"MobileVLM","score":84.9},{"place":53,"model":"mobilevlm-v2-3b","company":"meituan","family":"MobileVLM","version":"MobileVLM V2","score":84.7},{"place":54,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":84.6},{"place":55,"model":"mobilevlm-1.7b","company":"meituan","family":"MobileVLM","version":"MobileVLM","score":84.5},{"place":56,"model":"mobilevlm-v2-1.7b","company":"meituan","family":"MobileVLM","version":"MobileVLM V2","score":84.3},{"place":57,"model":"vila-13b","company":"nvidia","family":"VILA","version":"VILA","score":84.2},{"place":58,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":84},{"place":59,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":83.79},{"place":60,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":82.67},{"place":61,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":80.2},{"place":62,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":78.9},{"place":63,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":53.8}]},{"id":"popqa","name":"PopQA","topic":"Knowledge / QA","description":"Open-domain popular culture question answering benchmark testing long-tail factual recall.","url":"https://github.com/facebookresearch/PopQA","leaderboard":"","github":"https://github.com/facebookresearch/PopQA","paper":"https://arxiv.org/abs/2211.07239","metric":"percent","stars":"","top_model":"Llama 3.1 Tulu 3 405B SFT","top_percent":55.7,"top_model_id":"llama-3.1-tulu-3-405b-sft","top_generation":"Tulu 3","top_model_base":"Llama 3.1 Tulu 3","top_model_family":"Llama","top_company":"allenai","top_open_source":1,"lower_is_better":false,"bench_models":66,"total_models":3854,"placements":[{"place":1,"model":"llama-3.1-tulu-3-405b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":55.7},{"place":2,"model":"llama-3.1-tulu-3-405b","company":"allenai","family":"Llama","version":"Tulu 3","score":55.5},{"place":3,"model":"llama-3.1-tulu-3-405b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":55.4},{"place":4,"model":"hermes-3-llama-3.1-405b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":54.2},{"place":5,"model":"gpt-4o-2024-11-24","company":"openai","family":"GPT","version":"GPT-4o","score":53.6},{"place":6,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":52.9},{"place":7,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":48.6},{"place":8,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":48.1},{"place":9,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":46.5},{"place":10,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":46.4},{"place":11,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":46.3},{"place":12,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":44.9},{"place":13,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":37.2},{"place":14,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":37},{"place":15,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":36.4},{"place":16,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":33.5},{"place":17,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":33.1},{"place":18,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":32.2},{"place":19,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":31.9},{"place":20,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":30.9},{"place":21,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":30.7},{"place":22,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":30.7},{"place":23,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":30.6},{"place":24,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":30.4},{"place":25,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":30.2},{"place":26,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":29.3},{"place":27,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":29.3},{"place":28,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":29.3},{"place":29,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":29.1},{"place":30,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":28.9},{"place":31,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":28.76},{"place":32,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":28.5},{"place":33,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":28.3},{"place":34,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":28.04},{"place":35,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":28},{"place":36,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":26.7},{"place":37,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.5},{"place":38,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":26.17},{"place":39,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.9},{"place":40,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":25.7},{"place":41,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":25.5},{"place":42,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":25.5},{"place":43,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":25.1},{"place":44,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":25},{"place":45,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":24.7},{"place":46,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":24.3},{"place":47,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":23.7},{"place":48,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":23.7},{"place":49,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":22.93},{"place":50,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":22.5},{"place":51,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":21.5},{"place":52,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":21},{"place":53,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":20.8},{"place":54,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":20.7},{"place":55,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":20.56},{"place":56,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":20.55},{"place":57,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":20.4},{"place":58,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":20.2},{"place":59,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":20.2},{"place":60,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":18.4},{"place":61,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":18.1},{"place":62,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":18},{"place":63,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":17.9},{"place":64,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":16.8},{"place":65,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":16.5},{"place":66,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":14.5},{"place":67,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":14.1},{"place":68,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":13.25},{"place":69,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":12.8},{"place":70,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":9.94}]},{"id":"posttrainbench","name":"PostTrainBench","topic":"Post-training automation","description":"Measures how well AI agents can post-train base LLMs under fixed compute/time constraints; average score across AIME 2025, BFCL, GPQA Main, GSM8K, and HumanEval.","url":"https://posttrainbench.com/","leaderboard":"https://posttrainbench.com/","github":"https://github.com/aisa-group/PostTrainBench","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":49.3,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":49.3},{"place":2,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":45.3},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":44.65},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":44.3},{"place":5,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":43.8},{"place":6,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":42.4},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":41.88},{"place":8,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":41.8},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":41.8},{"place":10,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":41.4},{"place":11,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":40.2},{"place":12,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":39.8},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":39.3},{"place":14,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":38.79},{"place":15,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":37.5},{"place":16,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":37.27},{"place":17,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":37.2},{"place":18,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":37.1},{"place":19,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":36.79},{"place":20,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":36.6},{"place":21,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":36.2},{"place":22,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":36.2},{"place":23,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":35.66},{"place":24,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":35.6},{"place":25,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":35},{"place":26,"model":"gpt-5.1-codex-max","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":34.94},{"place":27,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":34.6},{"place":28,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":34.52},{"place":29,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":34.3},{"place":30,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":34.1},{"place":31,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":33.2},{"place":32,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":32.9},{"place":33,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":32},{"place":34,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":31.7},{"place":35,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":31.48},{"place":36,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":31.01},{"place":37,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":31},{"place":38,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":30.4},{"place":39,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":28.4},{"place":40,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":27.4},{"place":41,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":25},{"place":42,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":24.5},{"place":43,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":24.34},{"place":44,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":23.87},{"place":45,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":22.62},{"place":46,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":21.6},{"place":47,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":20.1},{"place":48,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":20.1},{"place":49,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":18.3},{"place":50,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":18.11},{"place":51,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":18.04},{"place":52,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":17.76},{"place":53,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":17.48},{"place":54,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":16.5},{"place":55,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":15.2},{"place":56,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":14.67},{"place":57,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":14.5},{"place":58,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":13.1}]},{"id":"posttrainbench-lite","name":"PostTrainBench Lite","topic":"Post-training automation","description":"Lite variant of PostTrainBench (agents post-training base LLMs under fixed compute).","url":"https://posttrainbench.com/","leaderboard":"https://posttrainbench.com/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Terra","top_percent":51.5,"top_model_id":"gpt-5.6-terra","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Terra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":51.5},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":50.3},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":38.8},{"place":4,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":29.6}]},{"id":"ppm-100-mad","name":"PPM-100 (Box) Matting (MAD)","topic":"Image matting","description":"PPM-100 (Box): box-prompted portrait matting; mean absolute difference x10^3 (lower is better).","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"mad","stars":"","top_model":"WeVisOne-VL-2B","top_percent":5.3,"top_model_id":"wevisone-vl-2b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-2B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":5.3},{"place":2,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":6.1}]},{"id":"prbench-finance","name":"PRBench Finance","topic":"Professional reasoning (finance)","description":"PRBench finance subset: rubric-graded professional reasoning tasks in finance.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":58.3,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":58.3},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":55.8},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":55.5},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":51.9},{"place":5,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":46.8}]},{"id":"prbench-legal","name":"PRBench Legal","topic":"Professional reasoning (legal)","description":"PRBench legal subset: rubric-graded professional reasoning tasks in law.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":57.6,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57.6},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":57.6},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":57.6},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":52.7},{"place":5,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":48.5},{"place":6,"model":"thomson-1.0-small","company":"thomsonreuters","family":"Thomson","version":"Thomson-1.0","score":31.4},{"place":7,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":26.9},{"place":8,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":25.9},{"place":9,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25.2},{"place":10,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":19.3}]},{"id":"prdbench","name":"PRDBench","topic":"Agentic coding","description":"Product Requirements Document benchmark for evaluating agentic coding capabilities.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LongCat-Flash-Lite","top_percent":39.63,"top_model_id":"longcat-flash-lite","top_generation":"LongCat-Flash-Lite","top_model_base":"LongCat-Flash-Lite","top_model_family":"LongCat","top_company":"meituan","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":39.63},{"place":2,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":15.36}]},{"id":"presentbench","name":"PresentBench","topic":"Agentic office work (slides)","description":"Benchmark for generating presentation decks from source materials, scored with rubrics.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":68.9,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":68.9},{"place":2,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":61.8},{"place":3,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":54.6},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":52.1},{"place":5,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":48.3}]},{"id":"procbench","name":"ProcBench","topic":"Procedural reasoning","description":"Procedural reasoning benchmark evaluating step-by-step logical reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":96.6,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":96.6},{"place":2,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":95},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.5},{"place":4,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":92.4},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90},{"place":6,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":90},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.5},{"place":8,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":87.5},{"place":9,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.1}]},{"id":"programbench","name":"ProgramBench","topic":"Software engineering","description":"ProgramBench (200 instances): agents re-implement complete programs from scratch; score as reported in GLM-5.2 release.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":85.4,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":85.4},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":82.3},{"place":3,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":80.5},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":77.8},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":77.6},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":76.8},{"place":7,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":72},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":71.9},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":70.8},{"place":10,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":70.5},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69.1},{"place":12,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":63.8},{"place":13,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":63.7},{"place":14,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":59},{"place":15,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":55.5},{"place":16,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":53.6},{"place":17,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":52.5},{"place":18,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":50.9},{"place":19,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":50},{"place":20,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":48.3},{"place":21,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":47.8},{"place":22,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":39.5},{"place":23,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":39.5},{"place":24,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":37},{"place":25,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":33},{"place":26,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":29.1},{"place":27,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":26.5},{"place":28,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":26},{"place":29,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":25},{"place":30,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":24.5},{"place":31,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":23},{"place":32,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":20.3},{"place":33,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":19},{"place":34,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":18},{"place":35,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":17.5},{"place":36,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":17.5},{"place":37,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":17.5},{"place":38,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":15.5},{"place":39,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":12.5},{"place":40,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":3}]},{"id":"programbench-almost-solved","name":"ProgramBench (Almost Solved)","topic":"Software engineering","description":"ProgramBench share of instances that are almost solved (near-complete test pass rate).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":37,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":37},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":33},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":23},{"place":4,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":20.3},{"place":5,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":19},{"place":6,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":17.5},{"place":7,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":17.5},{"place":8,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":17.5},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":15.5},{"place":10,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":10.5},{"place":11,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":9.5}]},{"id":"prontoqa","name":"PrOntoQA","topic":"Logical reasoning","description":"Probing ontological reasoning via question answering.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ling Flash 2.0","top_percent":97.88,"top_model_id":"ling-flash-2.0","top_generation":"Ling 2.0","top_model_base":"Ling Flash 2.0","top_model_family":"Ling","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":97.88},{"place":2,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":97.12},{"place":3,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":97},{"place":4,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":96.5},{"place":5,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":96.06},{"place":6,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":95},{"place":7,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":93.12},{"place":8,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":87.5},{"place":9,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86},{"place":10,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":84.5}]},{"id":"proofbench-advanced","name":"ProofBench Advanced","topic":"Mathematical proofs (advanced)","description":"Advanced mathematical proof benchmark covering complex theorem proving tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Aletheia","top_percent":91.9,"top_model_id":"aletheia","top_generation":"Gemini 3","top_model_base":"Aletheia","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"aletheia","company":"google","family":"Gemini","version":"Gemini 3","score":91.9},{"place":2,"model":"gpt-5.5-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":88.1},{"place":3,"model":"gemini-3-deep-think","company":"google","family":"Gemini","version":"Gemini 3","score":76.7},{"place":4,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":71.9},{"place":5,"model":"gemini-deep-think-imo-gold","company":"google","family":"Gemini","version":"Gemini Deep Think","score":65.7},{"place":6,"model":"deepseekmath-v2-heavy","company":"deepseek","family":"DeepSeekMath","version":"DeepSeekMath V2","score":61.9},{"place":7,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":54.3},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":49},{"place":9,"model":"gemini-2.5-deep-think","company":"google","family":"Gemini","version":"Gemini 2.5","score":37.6},{"place":10,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":35.7},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":30},{"place":12,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":28.6},{"place":13,"model":"gemini-2.5-pro-huang-yang","company":"google","family":"Gemini","version":"Gemini 2.5","score":24.8},{"place":14,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":23.8},{"place":15,"model":"grok-4-heavy","company":"xai","family":"Grok","version":"Grok 4","score":23.3},{"place":16,"model":"o3","company":"openai","family":"o3","version":"o3","score":20.5},{"place":17,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":20},{"place":18,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":18.6},{"place":19,"model":"grok-4.1-fast-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":18.6},{"place":20,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":17.6},{"place":21,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":11.4},{"place":22,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":7.1},{"place":23,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":7.1},{"place":24,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.2},{"place":25,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":4.8},{"place":26,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":4.3},{"place":27,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":3.8},{"place":28,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":2.9}]},{"id":"proofbench-basic","name":"ProofBench Basic","topic":"Mathematical proofs","description":"Entry-level mathematical proof benchmarking set.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeekMath-V2-Heavy","top_percent":99,"top_model_id":"deepseekmath-v2-heavy","top_generation":"DeepSeekMath V2","top_model_base":"DeepSeekMath V2 Heavy","top_model_family":"DeepSeekMath","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"deepseekmath-v2-heavy","company":"deepseek","family":"DeepSeekMath","version":"DeepSeekMath V2","score":99},{"place":2,"model":"gemini-deep-think-imo-gold","company":"google","family":"Gemini","version":"Gemini Deep Think","score":89},{"place":3,"model":"gemini-2.5-deep-think","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.8},{"place":4,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":59},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.2},{"place":6,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":46.7},{"place":7,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":33.3},{"place":8,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":29},{"place":9,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":27.1}]},{"id":"proofnet-test","name":"ProofNet (Test)","topic":"Formal theorem proving","description":"ProofNet test split: undergraduate-level mathematics theorems formalized in Lean 4; score = share proved.","url":"https://github.com/zhangir-azerbayev/ProofNet","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LongCat-Flash-Prover","top_percent":47.3,"top_model_id":"longcat-flash-prover","top_generation":"LongCat-Flash","top_model_base":"LongCat-Flash-Prover","top_model_family":"LongCat","top_company":"meituan","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":47.3},{"place":2,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":35},{"place":3,"model":"deepseek-prover-v2-671b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":30.5},{"place":4,"model":"leanabell-prover-v2-ds","company":"kuaishou","family":"Leanabell-Prover","version":"Leanabell-Prover-V2","score":23.7},{"place":5,"model":"deepseek-prover-v2-7b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":23},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":22},{"place":7,"model":"goedel-prover-v2-32b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":22},{"place":8,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":20.4},{"place":9,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":19.9},{"place":10,"model":"kimina-prover-72b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":18.3},{"place":11,"model":"goedel-prover-v2-8b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":16.7},{"place":12,"model":"leanabell-prover-v2-km","company":"kuaishou","family":"Leanabell-Prover","version":"Leanabell-Prover-V2","score":13.4},{"place":13,"model":"kimina-prover-8b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":11.8}]},{"id":"protocolqa","name":"ProtocolQA","topic":"Protocol understanding and QA","description":"Protocol question answering benchmark evaluating understanding of scientific protocols and procedures.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Grok 4.1 (Thinking)","top_percent":79,"top_model_id":"grok-4.1-thinking","top_generation":"Grok 4.1","top_model_base":"Grok 4.1","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":79},{"place":2,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":76}]},{"id":"protocolqa-open-ended","name":"ProtocolQA Open-Ended","topic":"Biosecurity","description":"Open-ended questions adapted from ProtocolQA on troubleshooting wet-lab protocols (pass@1).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":45.37,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":45.37},{"place":2,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":44.4},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":43.5},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":40.74},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":34.9},{"place":6,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":34.57},{"place":7,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":25.62}]},{"id":"proverbench","name":"ProverBench","topic":"Formal theorem proving","description":"ProverBench (DeepSeek-Prover-V2): 325 formalized problems incl. AIME and textbook problems in Lean 4; score = share proved.","url":"https://huggingface.co/datasets/deepseek-ai/DeepSeek-ProverBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LongCat-Flash-Prover","top_percent":66.5,"top_model_id":"longcat-flash-prover","top_generation":"LongCat-Flash","top_model_base":"LongCat-Flash-Prover","top_model_family":"LongCat","top_company":"meituan","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":66.5},{"place":2,"model":"goedel-prover-v2-32b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":53.2},{"place":3,"model":"deepseek-prover-v2-671b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":52.9},{"place":4,"model":"goedel-prover-v2-8b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":49.5},{"place":5,"model":"deepseek-prover-v2-7b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":49},{"place":6,"model":"leanabell-prover-v2-ds","company":"kuaishou","family":"Leanabell-Prover","version":"Leanabell-Prover-V2","score":47.8},{"place":7,"model":"kimina-prover-72b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":44.6},{"place":8,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":44.3},{"place":9,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":42.8},{"place":10,"model":"leanabell-prover-v2-km","company":"kuaishou","family":"Leanabell-Prover","version":"Leanabell-Prover-V2","score":39.8},{"place":11,"model":"kimina-prover-8b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":37.8},{"place":12,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":33.5}]},{"id":"pubmedqa","name":"PubMedQA","topic":"Biomedical QA","description":"Yes/no/maybe question answering over PubMed abstracts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedMO-4B-Next","top_percent":78.2,"top_model_id":"medmo-4b-next","top_generation":"MedMO-Next","top_model_base":"MedMO","top_model_family":"MedMO","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":78.2},{"place":2,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":78},{"place":3,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":77.6},{"place":4,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":77.2},{"place":5,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":75.8},{"place":6,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":75.6},{"place":7,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":74},{"place":8,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":73.4},{"place":9,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":73.4},{"place":10,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":68.4},{"place":11,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":68.2},{"place":12,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":66},{"place":13,"model":"mapika-decider-2b","company":"mapika","family":"Decider","version":"Decider","score":65.7},{"place":14,"model":"mapika-decider-4b","company":"mapika","family":"Decider","version":"Decider","score":63.3},{"place":15,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":61.3}]},{"id":"pubtabnet","name":"PubTabNet","topic":"Table recognition","description":"Image-based table recognition benchmark from PubMed Central articles; TEDS score on validation set.","url":"https://github.com/ibm-aur-nlp/PubTabNet","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Infinity-Parser2-Pro","top_percent":94.76,"top_model_id":"infinity-parser2-pro","top_generation":"Infinity-Parser2","top_model_base":"Infinity-Parser2 Pro","top_model_family":"Infinity-Parser","top_company":"infly","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":94.76},{"place":2,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":92.41},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":91.4},{"place":4,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":89.53},{"place":5,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":89.07},{"place":6,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":84.6}]},{"id":"puredocbench","name":"PureDocBench","topic":"Document parsing","description":"Document parsing benchmark (reported in OvisOCR3 release).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"OvisOCR3","top_percent":82.31,"top_model_id":"ovisocr3","top_generation":"OvisOCR3","top_model_base":"OvisOCR3","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":82.31},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":80.56},{"place":3,"model":"ovisocr2","company":"alibaba","family":"Ovis","version":"OvisOCR2","score":75.1},{"place":4,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":74.6},{"place":5,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.38},{"place":6,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":67.58},{"place":7,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":65.44},{"place":8,"model":"monkeyocrv2-b-parsing","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCRv2","score":64.91},{"place":9,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":63.34}]},{"id":"putnam-2025","name":"Putnam 2025","topic":"Math (competition, proof writing)","description":"Natural-language proof solutions to the 2025 William Lowell Putnam Mathematical Competition (12 problems, 10 points each); score = points out of 120.","url":"https://maa.org/putnam/","leaderboard":"","github":"","paper":"","metric":"points","stars":"","top_model":"Nomos 1","top_percent":87,"top_model_id":"nomos-1","top_generation":"Nomos 1","top_model_base":"Nomos 1","top_model_family":"Nomos","top_company":"nousresearch","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"nomos-1","company":"nousresearch","family":"Nomos","version":"Nomos 1","score":87},{"place":2,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":24}]},{"id":"putnambench","name":"PutnamBench","topic":"Formal theorem proving","description":"672 Putnam competition problems formalized in Lean 4; score = share of problems proved.","url":"https://github.com/trishullab/PutnamBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Aleph Prover","top_percent":99.4,"top_model_id":"aleph-prover","top_generation":"Aleph","top_model_base":"Aleph Prover","top_model_family":"Aleph","top_company":"logicalintelligence","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"aleph-prover","company":"logicalintelligence","family":"Aleph","version":"Aleph","score":99.4},{"place":2,"model":"seed-prover-1.5-high","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover 1.5","score":87.9},{"place":3,"model":"leanstral-1.5","company":"mistral","family":"Leanstral","version":"Leanstral 1.5","score":87.35},{"place":4,"model":"seed-prover-1.5-high","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover 1.5","score":86.31},{"place":5,"model":"goedel-architect","company":"princeton","family":"Goedel","version":"Goedel-Architect","score":75.6},{"place":6,"model":"axproverbase","company":"axiomatic","family":"Ax-Prover","version":"AxProverBase","score":54.32},{"place":7,"model":"seed-prover-1.5-agentic","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover 1.5","score":53.42},{"place":8,"model":"seed-prover","company":"bytedance","family":"Seed-Prover","version":"Seed-Prover","score":50.4},{"place":9,"model":"longcat-flash-prover","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":28.9},{"place":10,"model":"goedel-prover-v2-32b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":6.7},{"place":11,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":5.8},{"place":12,"model":"kimina-prover-8b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":4.8},{"place":13,"model":"kimina-prover-72b","company":"moonshotai","family":"Kimina-Prover","version":"Kimina-Prover","score":3.9},{"place":14,"model":"goedel-prover-v2-8b","company":"princeton","family":"Goedel","version":"Goedel-Prover-V2","score":3.8},{"place":15,"model":"deepseek-prover-v2-671b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":3.3},{"place":16,"model":"deepseek-prover-v2-7b","company":"deepseek","family":"DeepSeek-Prover","version":"DeepSeek-Prover-V2","score":1.4},{"place":17,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1.2},{"place":18,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":1.2}]},{"id":"q-bench","name":"Q-Bench","topic":"Low-level visual perception","description":"Q-Bench (A1 perception, test split) evaluating MLLMs on low-level visual attributes and image quality questions.","url":"https://q-future.github.io/Q-Bench/","leaderboard":"","github":"https://github.com/Q-Future/Q-Bench","paper":"https://arxiv.org/abs/2309.14181","metric":"percent","stars":"","top_model":"GPT-4V(ision)","top_percent":74.1,"top_model_id":"gpt-4v","top_generation":"GPT-4V","top_model_base":"GPT-4V","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":74.1},{"place":2,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":72.5},{"place":3,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":71.8},{"place":4,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":70.6},{"place":5,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":68.9},{"place":6,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":64.4},{"place":7,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":61.7},{"place":8,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":61.4},{"place":9,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":55.9},{"place":10,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":54.7}]},{"id":"q-spatial-bench","name":"Q-Spatial-Bench","topic":"Embodied reasoning","description":"Quantitative spatial reasoning (metric distances/sizes) benchmark for VLMs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.6 Flash","top_percent":87.1,"top_model_id":"gemini-3.6-flash","top_generation":"Gemini 3.6","top_model_base":"Gemini 3.6 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":87.1},{"place":2,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":81.2},{"place":3,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":76.2},{"place":4,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":76.2},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":74.3},{"place":6,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":69.3},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":68.3},{"place":8,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":66.3},{"place":9,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.5},{"place":10,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":51.5},{"place":11,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":47.5},{"place":12,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":46.5},{"place":13,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":35.6}]},{"id":"qivd","name":"QIVD","topic":"Audio-visual QA","description":"Qualcomm Interactive Video Dataset: situated audio-visual question answering on live-style video with speech questions; accuracy.","url":"https://thinkingmachines.ai/blog/interaction-models/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.8 Flash","top_percent":69.1,"top_model_id":"gemini-3.8-flash","top_generation":"Gemini 3.8","top_model_base":"Gemini 3.8 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":69.1},{"place":2,"model":"qwen3.8-omni-flash-realtime","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.8},{"place":3,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":65.6},{"place":4,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":62},{"place":5,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":62},{"place":6,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":7,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":58.2},{"place":8,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":57.5},{"place":9,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":56.1},{"place":10,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.7},{"place":11,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":54},{"place":12,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":41.2}]},{"id":"qrecc","name":"QReCC","topic":"Conversational QA","description":"Open-domain conversational QA with question rewriting (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":57.3,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":57.3},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":49.9},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":49.4},{"place":4,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":49.3},{"place":5,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":49.3},{"place":6,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":47},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":47},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":45.4},{"place":9,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":42.4},{"place":10,"model":"o3","company":"openai","family":"o3","version":"o3","score":40.4}]},{"id":"quac","name":"QuAC","topic":"Conversational QA","description":"Question answering in context.","url":"https://quac.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":54.5,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":54.5},{"place":2,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":53.6},{"place":3,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":53.6},{"place":4,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":51.1},{"place":5,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":51.1},{"place":6,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":49.3},{"place":7,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":44.9},{"place":8,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":44.8},{"place":9,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":44.4},{"place":10,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":43.3},{"place":11,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":41.1},{"place":12,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":39.8},{"place":13,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":39.7},{"place":14,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":37.7},{"place":15,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":30.9},{"place":16,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":28.9},{"place":17,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":27.3},{"place":18,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":26.6},{"place":19,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":26.6},{"place":20,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":23.2},{"place":21,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":23.1},{"place":22,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":22.2},{"place":23,"model":"o3","company":"openai","family":"o3","version":"o3","score":20.8},{"place":24,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":18.8}]},{"id":"quality","name":"QuALITY","topic":"Long-context reading comprehension","description":"Long-document multiple-choice reading comprehension benchmark.","url":"https://github.com/nyu-mll/quality","leaderboard":"","github":"https://github.com/nyu-mll/quality","paper":"https://arxiv.org/abs/2112.08608","metric":"log_acc","stars":"","top_model":"Llama-3_1-70B-TFree-HAT-SFT","top_percent":48.8,"top_model_id":"llama-3_1-70b-tfree-hat-sft","top_generation":"Llama TFree HAT","top_model_base":"Llama 3.1 70B TFree HAT","top_model_family":"Llama TFree HAT","top_company":"alephalpha","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":48.8},{"place":2,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":45.9}]},{"id":"query-sufficiency","name":"Query Sufficiency","topic":"Legal query triage","description":"Judging whether a legal research query contains sufficient information to answer (Thomson Reuters eval).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Thomson-1.0-Small","top_percent":59.4,"top_model_id":"thomson-1.0-small","top_generation":"Thomson-1.0","top_model_base":"Thomson 1.0 Small","top_model_family":"Thomson","top_company":"thomsonreuters","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"thomson-1.0-small","company":"thomsonreuters","family":"Thomson","version":"Thomson-1.0","score":59.4},{"place":2,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":55.7},{"place":3,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":54.8},{"place":4,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.7},{"place":5,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.4}]},{"id":"qvhighlights","name":"QVHighlights","topic":"Video temporal grounding","description":"Video moment retrieval / highlight detection benchmark; R1@0.5.","url":"https://github.com/jayleicn/moment_detr","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nova 2 Lite","top_percent":77.2,"top_model_id":"nova-2-lite","top_generation":"Nova 2","top_model_base":"Nova 2 Lite","top_model_family":"Nova","top_company":"amazon","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":77.2},{"place":2,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":76.7},{"place":3,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":76.7},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":75},{"place":5,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.4},{"place":6,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":48.1},{"place":7,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":11.9},{"place":8,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":10.7},{"place":9,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":4.5}]},{"id":"qwenclawbench","name":"QwenClawBench","topic":"Agent tasks (OpenClaw)","description":"Real-user-distribution Claw (OpenClaw-style) agent benchmark released by Qwen.","url":"https://github.com/SKYLENAGE-AI/QwenClawBench","leaderboard":"","github":"https://github.com/SKYLENAGE-AI/QwenClawBench","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":65.5,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":37,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":65.5},{"place":2,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":64.3},{"place":3,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":61.8},{"place":4,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.2},{"place":5,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":59},{"place":6,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":58.7},{"place":7,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57.2},{"place":8,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":54.7},{"place":9,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":54.3},{"place":10,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":54.1},{"place":11,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":53.4},{"place":12,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":52.6},{"place":13,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":52.3},{"place":14,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.2},{"place":15,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.8},{"place":16,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":48.73},{"place":17,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.7},{"place":18,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":47.27},{"place":19,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":46.11},{"place":20,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":44.68},{"place":21,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.04},{"place":22,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.53},{"place":23,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":43.52},{"place":24,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":43.16},{"place":25,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":42.9},{"place":26,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.7},{"place":27,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":40.66},{"place":28,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":38.7},{"place":29,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.47},{"place":30,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.1},{"place":31,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":37.01},{"place":32,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":36.4},{"place":33,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":22.98},{"place":34,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":19.3},{"place":35,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.2},{"place":36,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":16.8},{"place":37,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":16.7},{"place":38,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":14.5},{"place":39,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":4.5}]},{"id":"r-bench","name":"R-Bench","topic":"Robustness (multimodal)","description":"R-Bench: robustness of LMMs to real-world image corruptions (discriminative subset).","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2410.05474","metric":"percent","stars":"","top_model":"GPT-4o-2024-05-13","top_percent":77.7,"top_model_id":"gpt-4o-2024-05-13","top_generation":"GPT-4o","top_model_base":"GPT-4o","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":77.7},{"place":2,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":77.2},{"place":3,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":74.1},{"place":4,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":73.3},{"place":5,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":72.9},{"place":6,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":72.1},{"place":7,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":70.1},{"place":8,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":70.1},{"place":9,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.9},{"place":10,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":67.9},{"place":11,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":66.1},{"place":12,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":65.6},{"place":13,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":64.5},{"place":14,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":64},{"place":15,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":62.2},{"place":16,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":59},{"place":17,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":56.8},{"place":18,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":55.6},{"place":19,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":55.5}]},{"id":"race","name":"RACE","topic":"Reading comprehension","description":"English exams for middle and high school.","url":"http://www.cs.cmu.edu/~glai1/data/race/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Mistral Large 3 Base","top_percent":93.3,"top_model_id":"mistral-large-3-base","top_generation":"Mistral 3","top_model_base":"Mistral Large 3 Base","top_model_family":"Mistral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":67,"total_models":3854,"placements":[{"place":1,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":93.3},{"place":2,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.21},{"place":3,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":92.2},{"place":4,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.15},{"place":5,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":92.15},{"place":6,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":91.96},{"place":7,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":91.39},{"place":8,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":91.3},{"place":9,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91},{"place":10,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":90.8},{"place":11,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":90.8},{"place":12,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":90.5},{"place":13,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":90.3},{"place":14,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":90.1},{"place":15,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":89.5},{"place":16,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88.9},{"place":17,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":88.9},{"place":18,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":88.04},{"place":19,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":87.3},{"place":20,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":87.1},{"place":21,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":86.5},{"place":22,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":86.2},{"place":23,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":85.2},{"place":24,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":85.1},{"place":25,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":84.8},{"place":26,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":84.7},{"place":27,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":83.9},{"place":28,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":83.28},{"place":29,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":81.4},{"place":30,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":81.4},{"place":31,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":80.2},{"place":32,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":79.93},{"place":33,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":79.1},{"place":34,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":78.5},{"place":35,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":77.4},{"place":36,"model":"internlm-chat-7b","company":"internlm","family":"InternLM","version":"InternLM","score":76.3},{"place":37,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":75.6},{"place":38,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":75.6},{"place":39,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":74.8},{"place":40,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":74.2},{"place":41,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":74},{"place":42,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":73.2},{"place":43,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":72.9},{"place":44,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":72.6},{"place":45,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":71.2},{"place":46,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":69.1},{"place":47,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":68.01},{"place":48,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":67.5},{"place":49,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":67.18},{"place":50,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":66.3},{"place":51,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":63.2},{"place":52,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":62.61},{"place":53,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":59.1},{"place":54,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":58.86},{"place":55,"model":"rnd1-base-0910","company":"radicalnumerics","family":"RND1","version":"RND1","score":57.6},{"place":56,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":57.4},{"place":57,"model":"vicuna-7b","company":"lmsys","family":"Vicuna-7B","version":"Vicuna-7B","score":54},{"place":58,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":47.63},{"place":59,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":46.9},{"place":60,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":45.2},{"place":61,"model":"dream-7b-instruct","company":"huawei","family":"Dream","version":"Dream 7B","score":44.7},{"place":62,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":43.9},{"place":63,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":43.4},{"place":64,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":43.2},{"place":65,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":42.4},{"place":66,"model":"alpaca-7b","company":"stanford","family":"Alpaca","version":"Alpaca","score":40.7},{"place":67,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":40.2},{"place":68,"model":"llada-8b-instruct","company":"antgroup","family":"LLaDA","version":"LLaDA","score":38.7},{"place":69,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":37.6},{"place":70,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":35.8},{"place":71,"model":"baichuan-7b","company":"baichuan","family":"Baichuan","version":"Baichuan","score":28.1},{"place":72,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":25.2},{"place":73,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":19.2},{"place":74,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":3}]},{"id":"race-high","name":"RACE-High","topic":"Reading comprehension","description":"RACE reading-comprehension questions from Chinese high-school English exams.","url":"https://www.cs.cmu.edu/~glai1/data/race/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1704.04683","metric":"percent","stars":"","top_model":"Orion-14B-Base","top_percent":91.3,"top_model_id":"orion-14b-base","top_generation":"Orion","top_model_base":"Orion 14B","top_model_family":"Orion","top_company":"orionstarai","top_open_source":1,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":91.3},{"place":2,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":90.3},{"place":3,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":84.1},{"place":4,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":83.3},{"place":5,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":67.2},{"place":6,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":58.9},{"place":7,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":57.9},{"place":8,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":56.8},{"place":9,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":56.7},{"place":10,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":56},{"place":11,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":54.3},{"place":12,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":52.7},{"place":13,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":52.6},{"place":14,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":51.3},{"place":15,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":50.8},{"place":16,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":50.7},{"place":17,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":50.6},{"place":18,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":50.3},{"place":19,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":47},{"place":20,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":46.5},{"place":21,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":46.4},{"place":22,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":45.8}]},{"id":"race-middle","name":"RACE-Middle","topic":"Reading comprehension","description":"RACE reading-comprehension questions from Chinese middle-school English exams.","url":"https://www.cs.cmu.edu/~glai1/data/race/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1704.04683","metric":"percent","stars":"","top_model":"GPT-4","top_percent":93.7,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":93.7},{"place":2,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":93.2},{"place":3,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":93},{"place":4,"model":"xverse-65b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":90.7},{"place":5,"model":"xverse-65b","company":"xverse","family":"XVERSE","version":"XVERSE","score":90.6},{"place":6,"model":"xverse-moe-a36b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":88.4},{"place":7,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":87.6},{"place":8,"model":"falcon-180b","company":"tii","family":"Falcon","version":"Falcon","score":87.6},{"place":9,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":86.4},{"place":10,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":85.7},{"place":11,"model":"gpt-3.5","company":"openai","family":"GPT","version":"GPT-3","score":85.6},{"place":12,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":84.6},{"place":13,"model":"xverse-13b-2","company":"xverse","family":"XVERSE","version":"XVERSE","score":82.4},{"place":14,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":81.5},{"place":15,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":80.2},{"place":16,"model":"xverse-7b","company":"xverse","family":"XVERSE","version":"XVERSE","score":79},{"place":17,"model":"xverse-moe-a4.2b","company":"xverse","family":"XVERSE","version":"XVERSE-MoE","score":75.4},{"place":18,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":74.2},{"place":19,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":74.2},{"place":20,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":73.3},{"place":21,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":73.3},{"place":22,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":73.1},{"place":23,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":70.9},{"place":24,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":70.1},{"place":25,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":69.9},{"place":26,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":68.9},{"place":27,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":68.1},{"place":28,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":67.9},{"place":29,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":67.5},{"place":30,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":67.1},{"place":31,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":66.1},{"place":32,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":65.2},{"place":33,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":64.8},{"place":34,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":63.4},{"place":35,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":63.2},{"place":36,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":63},{"place":37,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":61.9},{"place":38,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":61.6},{"place":39,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":60.7},{"place":40,"model":"dbrx-instruct-preview","company":"databricks","family":"DBRX","version":"DBRX","score":55.9}]},{"id":"ragtruth","name":"RAGTruth","topic":"Hallucination detection","description":"Response-level hallucination detection for RAG answers; F1 on the hallucinated class.","url":"https://github.com/ParticleMedia/RAGTruth","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"pplx-decider-v1-27b","top_percent":88.8,"top_model_id":"pplx-decider-v1-27b","top_generation":"v1","top_model_base":"pplx-decider","top_model_family":"pplx-decider","top_company":"perplexity","top_open_source":1,"lower_is_better":false,"bench_models":47,"total_models":3854,"placements":[{"place":1,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":88.8},{"place":2,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":84.4},{"place":3,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":84.1},{"place":4,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":83.9},{"place":5,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":82.5},{"place":6,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":82.1},{"place":7,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":81.4},{"place":8,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":80.9},{"place":9,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":79.4},{"place":10,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":77.88},{"place":11,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":77.6},{"place":12,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":77.59},{"place":13,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":77.17},{"place":14,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76.97},{"place":15,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":76.5},{"place":16,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":76.5},{"place":17,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":76.3},{"place":18,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":76.2},{"place":19,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.6},{"place":20,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":75.1},{"place":21,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.08},{"place":22,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":71.9},{"place":23,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.75},{"place":24,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":71.5},{"place":25,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.4},{"place":26,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":70.4},{"place":27,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":68},{"place":28,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":66.2},{"place":29,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":65.1},{"place":30,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":64.1},{"place":31,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":53.3},{"place":32,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":50.3},{"place":33,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":48.8},{"place":34,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":46.2},{"place":35,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":42},{"place":36,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":35.7},{"place":37,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":35.7},{"place":38,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":35.6},{"place":39,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":29.7},{"place":40,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":29.7},{"place":41,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":29.5},{"place":42,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":25.3},{"place":43,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":18.2},{"place":44,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":10.2},{"place":45,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":4.5},{"place":46,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":2.3},{"place":47,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":1}]},{"id":"random-complex-tasks","name":"Random Complex Tasks","topic":"Agentic tasks (random)","description":"Randomly constructed complex task environments for agent generalization.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LongCat-Flash-Thinking-2601","top_percent":35.8,"top_model_id":"longcat-flash-thinking-2601","top_generation":"LongCat-Flash","top_model_base":"LongCat-Flash","top_model_family":"LongCat","top_company":"meituan","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":35.8},{"place":2,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":32.7},{"place":3,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32.6},{"place":4,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":32.5},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":32.5},{"place":6,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":29.7},{"place":7,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":25.3},{"place":8,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":17.2}]},{"id":"real5-omnidocbench","name":"Real5-OmniDocBench","topic":"Document parsing (real-world distortions)","description":"OmniDocBench v1.5 pages re-captured under five real-world conditions (scanning, warping, screen photography, illumination, skew); Overall score.","url":"https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2601.21957","metric":"percent","stars":"","top_model":"OvisOCR3","top_percent":93.63,"top_model_id":"ovisocr3","top_generation":"OvisOCR3","top_model_base":"OvisOCR3","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"ovisocr3","company":"alibaba","family":"Ovis","version":"OvisOCR3","score":93.63},{"place":2,"model":"paddleocr-vl-1.6","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.6","score":93.19},{"place":3,"model":"xiaomi-ocr-0","company":"xiaomi","family":"Xiaomi-OCR","version":"Xiaomi-OCR-0","score":92.73},{"place":4,"model":"ovisocr2","company":"alibaba","family":"Ovis","version":"OvisOCR2","score":92.29},{"place":5,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":92.05},{"place":6,"model":"glm-ocr","company":"zai","family":"GLM","version":"GLM OCR","score":90.32},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.24},{"place":8,"model":"monkeyocrv2-b-parsing","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCRv2","score":89.22},{"place":9,"model":"mineru2.5-pro","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":88.96},{"place":10,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.904},{"place":11,"model":"hunyuanocr-1.5","company":"tencent","family":"HunyuanOCR","version":"HunyuanOCR 1.5","score":88.53},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.21},{"place":13,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":86.92},{"place":14,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.86},{"place":15,"model":"dots.ocr","company":"rednote","family":"dots","version":"dots","score":86.38},{"place":16,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":85.61},{"place":17,"model":"paddleocr-vl","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR","score":85.54},{"place":18,"model":"nanonets-ocr-s","company":"nanonets","family":"Nanonets OCR","version":"Nanonets OCR","score":84.19},{"place":19,"model":"qwen3.5-ocr","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.48},{"place":20,"model":"monkeyocr-pro-3b","company":"kingsoft","family":"MonkeyOCR","version":"MonkeyOCR Pro","score":79.49},{"place":21,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":78.66},{"place":22,"model":"monkeyocr-3b","company":"monkeyocr","family":"MonkeyOCR","version":"MonkeyOCR","score":78.29},{"place":23,"model":"monkeyocr-pro-1.2b","company":"monkeyocr","family":"MonkeyOCR","version":"MonkeyOCR","score":77.15},{"place":24,"model":"mineru2-vlm","company":"opendatalab","family":"MinerU","version":"MinerU2","score":76.95},{"place":25,"model":"deepseek-ocr","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR","score":73.99},{"place":26,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":73.01},{"place":27,"model":"pp-structurev3","company":"paddlepaddle","family":"PP-Structure","version":"PP-Structure V3","score":64.45},{"place":28,"model":"dolphin","company":"bytedance","family":"Dolphin","version":"Dolphin","score":61.78},{"place":29,"model":"dolphin-1.5","company":"bytedance","family":"Dolphin","version":"Dolphin","score":61.48},{"place":30,"model":"marker-1.8.2","company":"datalab","family":"Marker","version":"Marker 1.8","score":60.1}]},{"id":"realbench","name":"Realbench","topic":"Web browsing","description":"Real-world browsing and QA benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":49.1,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":49.1},{"place":2,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":46},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":39.3},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":38.4},{"place":5,"model":"gpt-03-cua","company":"openai","family":"o3","version":"o3","score":34.8}]},{"id":"realkie-fcc-verified","name":"RealKIE-FCC Verified","topic":"Key information extraction","description":"Human-verified version of the RealKIE FCC document key-information-extraction benchmark (ALNS).","url":"https://huggingface.co/datasets/amazon-agi/RealKIE-FCC-Verified","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro Preview","top_percent":71.7,"top_model_id":"gemini-3-pro-preview","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro Preview","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":71.7},{"place":2,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":67},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.4},{"place":4,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":62.1},{"place":5,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":59.8},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.9},{"place":7,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":54.6},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":53.6},{"place":9,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":53.1},{"place":10,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":52.2},{"place":11,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":51.9},{"place":12,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":50.1},{"place":13,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":49.7},{"place":14,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":40.4}]},{"id":"realworldqa","name":"RealWorldQA","topic":"Real-world visual QA","description":"Visual question answering with real-world images and scenarios.","url":"https://realworldqa.github.io/","leaderboard":"","github":"https://github.com/ZhuoyuWei/RealWorldQAPlatform","paper":"https://arxiv.org/abs/2410.14332","metric":"percent","stars":"","top_model":"Qwen3.8-Flash-Next","top_percent":88.5,"top_model_id":"qwen3.8-flash-next","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Flash Next","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":228,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":88.5},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":88},{"place":3,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":87.7},{"place":4,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":86.9},{"place":5,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":86.7},{"place":6,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":86.3},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85.9},{"place":8,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":85.9},{"place":9,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.4},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.4},{"place":11,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":85.3},{"place":12,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":85.1},{"place":13,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.1},{"place":14,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.1},{"place":15,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":84.1},{"place":16,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.9},{"place":17,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":83.8},{"place":18,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.7},{"place":19,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.7},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.5},{"place":21,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":83.3},{"place":22,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":83.3},{"place":23,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":82.8},{"place":24,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":82.5},{"place":25,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":82.2},{"place":26,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.3},{"place":27,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.3},{"place":28,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":81},{"place":29,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":80.8},{"place":30,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.3},{"place":31,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.5},{"place":32,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":79.1},{"place":33,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":79.08},{"place":34,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79},{"place":35,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":79},{"place":36,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79},{"place":37,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":78.95},{"place":38,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":78.7},{"place":39,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":78.69},{"place":40,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.43},{"place":41,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":78},{"place":42,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":77.8},{"place":43,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":77.8},{"place":44,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":77.6},{"place":45,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":77.5},{"place":46,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.4},{"place":47,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.4},{"place":48,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":77.4},{"place":49,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":77.3},{"place":50,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":77},{"place":51,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77},{"place":52,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.99},{"place":53,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":76.99},{"place":54,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":76.73},{"place":55,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":76.7},{"place":56,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":76.6},{"place":57,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.34},{"place":58,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.2},{"place":59,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":76.1},{"place":60,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":75.9},{"place":61,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":75.8},{"place":62,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":75.7},{"place":63,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":75.6},{"place":64,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":75.4},{"place":65,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":75.4},{"place":66,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":75.4},{"place":67,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":75.4},{"place":68,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":75.2},{"place":69,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":75},{"place":70,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":74.6},{"place":71,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":74.5},{"place":72,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.5},{"place":73,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.5},{"place":74,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":74.44},{"place":75,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.2},{"place":76,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":73.9},{"place":77,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":73.9},{"place":78,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":73.8},{"place":79,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.7},{"place":80,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":73.6},{"place":81,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":73.6},{"place":82,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":73.6},{"place":83,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":73.5},{"place":84,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":73.5},{"place":85,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":73.3},{"place":86,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.2},{"place":87,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":73.1},{"place":88,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":72.9},{"place":89,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":72.8},{"place":90,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":72.7},{"place":91,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":72.4},{"place":92,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.3},{"place":93,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":72.3},{"place":94,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.2},{"place":95,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.2},{"place":96,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":72.2},{"place":97,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":72.1},{"place":98,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":72},{"place":99,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":71.9},{"place":100,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":71.8},{"place":101,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":71.8},{"place":102,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":71.76},{"place":103,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.5},{"place":104,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.4},{"place":105,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":71.37},{"place":106,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":71.2},{"place":107,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":71.2},{"place":108,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":71.1},{"place":109,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":71.1},{"place":110,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.9},{"place":111,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":70.7},{"place":112,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":70.7},{"place":113,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":70.7},{"place":114,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":70.6},{"place":115,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.6},{"place":116,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.5},{"place":117,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":70.5},{"place":118,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":70.4},{"place":119,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.3},{"place":120,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":70.3},{"place":121,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":70.2},{"place":122,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":70.1},{"place":123,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":70.1},{"place":124,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":70.1},{"place":125,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":70.1},{"place":126,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":69.9},{"place":127,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":69.8},{"place":128,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":69.7},{"place":129,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":69.7},{"place":130,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":69.67},{"place":131,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.5},{"place":132,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":69.41},{"place":133,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":69.4},{"place":134,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.3},{"place":135,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":69.3},{"place":136,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":69},{"place":137,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69},{"place":138,"model":"grok-1.5v","company":"xai","family":"Grok","version":"Grok 1.5","score":68.7},{"place":139,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":68.6},{"place":140,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":68.5},{"place":141,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":68.4},{"place":142,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":68.3},{"place":143,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":68.1},{"place":144,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.1},{"place":145,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":68},{"place":146,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":68},{"place":147,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":67.8},{"place":148,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":67.8},{"place":149,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":67.8},{"place":150,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":67.7},{"place":151,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":67.5},{"place":152,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":67.5},{"place":153,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":67.5},{"place":154,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":67.5},{"place":155,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":67.5},{"place":156,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":67.5},{"place":157,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":67.5},{"place":158,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":67.45},{"place":159,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":67.3},{"place":160,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":67.3},{"place":161,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":67.2},{"place":162,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.1},{"place":163,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":67.1},{"place":164,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":67.1},{"place":165,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":67.1},{"place":166,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":66.93},{"place":167,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":66.7},{"place":168,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":66.3},{"place":169,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":66.3},{"place":170,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":66.1},{"place":171,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":66},{"place":172,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":66},{"place":173,"model":"lfm2-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":65.75},{"place":174,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":65.4},{"place":175,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":65.4},{"place":176,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":65.4},{"place":177,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":65.23},{"place":178,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":65.1},{"place":179,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":65.1},{"place":180,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.1},{"place":181,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":65},{"place":182,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":65},{"place":183,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":64.84},{"place":184,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.6},{"place":185,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":64.4},{"place":186,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":64.4},{"place":187,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":64.3},{"place":188,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.3},{"place":189,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.3},{"place":190,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":64.2},{"place":191,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":64.2},{"place":192,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":64.2},{"place":193,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":64.2},{"place":194,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":64.1},{"place":195,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":64.1},{"place":196,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":64.1},{"place":197,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.9},{"place":198,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":63.5},{"place":199,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.4},{"place":200,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":63.2},{"place":201,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":63},{"place":202,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":62.9},{"place":203,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":62.9},{"place":204,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":62.9},{"place":205,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":62.6},{"place":206,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":62.6},{"place":207,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":62.6},{"place":208,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":62.5},{"place":209,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":62.2},{"place":210,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":62},{"place":211,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.8},{"place":212,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":61.6},{"place":213,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":61.56},{"place":214,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":61.4},{"place":215,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":61.4},{"place":216,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":61.2},{"place":217,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":61.2},{"place":218,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.1},{"place":219,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":60.8},{"place":220,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":60.78},{"place":221,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":60.7},{"place":222,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":60.7},{"place":223,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":60.7},{"place":224,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":60.7},{"place":225,"model":"blip-3-4b","company":"salesforce","family":"BLIP","version":"BLIP-3","score":60.5},{"place":226,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":60.4},{"place":227,"model":"blip-3o-4b","company":"salesforce","family":"BLIP","version":"BLIP-3O","score":60.4},{"place":228,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":60.4},{"place":229,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":60.4},{"place":230,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":60.3},{"place":231,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":60.1},{"place":232,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":60.1},{"place":233,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":60.1},{"place":234,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":60},{"place":235,"model":"llava-next-llama3","company":"llava","family":"LLaVA","version":"LLaVA-Next-Llama3","score":60},{"place":236,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":60},{"place":237,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":59.9},{"place":238,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":59.4},{"place":239,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":59.4},{"place":240,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":59.08},{"place":241,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":59},{"place":242,"model":"phi-3-vision-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":58.8},{"place":243,"model":"bunny-llama3-8b","company":"baai","family":"Bunny","version":"Bunny-Llama3","score":58.8},{"place":244,"model":"lfm2.5-vl-450m","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":58.43},{"place":245,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":58.3},{"place":246,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":58.3},{"place":247,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":58},{"place":248,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":57.5},{"place":249,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":57.5},{"place":250,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":57.4},{"place":251,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":57.3},{"place":252,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":57.25},{"place":253,"model":"internvl3.5-1b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57.12},{"place":254,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":56.9},{"place":255,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":56.7},{"place":256,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":56.4},{"place":257,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":56.2},{"place":258,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":56.1},{"place":259,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":55.8},{"place":260,"model":"llava-onevision-0.5b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":55.6},{"place":261,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":55.3},{"place":262,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":55.2},{"place":263,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":54.8},{"place":264,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":54.8},{"place":265,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":54.2},{"place":266,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":53.6},{"place":267,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":53.6},{"place":268,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":53.5},{"place":269,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":53.3},{"place":270,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":52.4},{"place":271,"model":"lfm2-vl-450m","company":"liquidai","family":"LFM","version":"LFM2-VL","score":52.03},{"place":272,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":51.9},{"place":273,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":51.2},{"place":274,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":51.2},{"place":275,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.7},{"place":276,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":50.3},{"place":277,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":49.9},{"place":278,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":49.8},{"place":279,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":49.7},{"place":280,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":49.3},{"place":281,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":48.4},{"place":282,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":46.93},{"place":283,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":46.1},{"place":284,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":45.5},{"place":285,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":42.4},{"place":286,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":28.5},{"place":287,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":27.2}]},{"id":"reasonseg-val","name":"ReasonSeg (val)","topic":"Reasoning segmentation","description":"ReasonSeg val reasoning segmentation, gIoU.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":71.2,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":71.2},{"place":2,"model":"lisa-13b","company":"cuhk","family":"LISA","version":"LISA","score":65},{"place":3,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":60.9},{"place":4,"model":"unipixel-7b","company":"polyu","family":"UniPixel","version":"UniPixel","score":60.5},{"place":5,"model":"gsva-7b","company":"tsinghua","family":"GSVA","version":"GSVA","score":50.5}]},{"id":"recruit-bench","name":"Recruit-Bench","topic":"Recruitment / HR tasks","description":"Benchmark of recruiting-domain tasks (resume screening, job matching, candidate communication) used by Nanbeige.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 12B IT","top_percent":69.4,"top_model_id":"gemma-4-12b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 12B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.4},{"place":2,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":63.3},{"place":3,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59},{"place":4,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.9},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.7}]},{"id":"ref-l4-rod-f1","name":"Ref-L4 Referring Detection (F1)","topic":"Referring expressions","description":"Ref-L4 referring object detection, F1 mean over IoU 0.5:0.95.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":78.1,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":78.1},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":75.1},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":74.3},{"place":4,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.4},{"place":5,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72},{"place":6,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":65.2}]},{"id":"ref-l4-test","name":"Ref-L4 (test)","topic":"Referring expressions","description":"Ref-L4 referring expression comprehension on the test split.","url":"https://huggingface.co/datasets/JierunChen/Ref-L4","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-4.6V","top_percent":88.9,"top_model_id":"glm-4.6v","top_generation":"GLM 4.6V","top_model_base":"GLM 4.6V","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":88.9},{"place":2,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":87.7}]},{"id":"ref-zom-ciou","name":"Ref-ZOM (cIoU)","topic":"Referring segmentation","description":"Ref-ZOM zero/one/many-target referring segmentation, cIoU.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-2B","top_percent":73.4,"top_model_id":"wevisone-vl-2b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-2B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":73.4},{"place":2,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":72.2},{"place":3,"model":"gsva-7b","company":"tsinghua","family":"GSVA","version":"GSVA","score":66.6},{"place":4,"model":"unipixel-7b","company":"polyu","family":"UniPixel","version":"UniPixel","score":62.9},{"place":5,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":61}]},{"id":"ref-zom-rejection","name":"Ref-ZOM (Rejection)","topic":"Referring segmentation","description":"Ref-ZOM rejection rate on non-existent referents.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":86,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":86},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":62.4},{"place":3,"model":"gsva-7b","company":"tsinghua","family":"GSVA","version":"GSVA","score":41.9},{"place":4,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":1.3},{"place":5,"model":"unipixel-7b","company":"polyu","family":"UniPixel","version":"UniPixel","score":0.3}]},{"id":"refcoco","name":"RefCOCO","topic":"Referring expressions","description":"RefCOCO average accuracy at IoU 0.5 (val).","url":"https://huggingface.co/datasets/JierunChen/Ref-L4","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek-VL2","top_percent":95.1,"top_model_id":"deepseek-vl2","top_generation":"DeepSeek-VL2","top_model_base":"DeepSeek-VL2","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":97,"total_models":3854,"placements":[{"place":1,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":95.1},{"place":2,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":95},{"place":3,"model":"egm-8b","company":"nvidia","family":"EGM","version":"EGM","score":93.9},{"place":4,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":93.9},{"place":5,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":93.7},{"place":6,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":93.5},{"place":7,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":93.4},{"place":8,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":93.2},{"place":9,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":93.2},{"place":10,"model":"ferret-v2-7b","company":"apple","family":"Ferret","version":"Ferret-v2","score":92.8},{"place":11,"model":"cogvlm-grounding-generalist","company":"zai","family":"CogVLM","version":"CogVLM","score":92.8},{"place":12,"model":"cogvlm-grounding-generalist","company":"zai","family":"CogVLM","version":"CogVLM","score":92.76},{"place":13,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":92.6},{"place":14,"model":"ferret-v2-13b","company":"apple","family":"Ferret","version":"Ferret-v2","score":92.6},{"place":15,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.5},{"place":16,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":92.4},{"place":17,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.4},{"place":18,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.3},{"place":19,"model":"internvl2-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":92.2},{"place":20,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":92.2},{"place":21,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92},{"place":22,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":91.9},{"place":23,"model":"texthawk2","company":"huawei","family":"TextHawk","version":"TextHawk2","score":91.9},{"place":24,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":91.7},{"place":25,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":91.7},{"place":26,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":91.3},{"place":27,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":91.3},{"place":28,"model":"moondream-9b-a2b","company":"moondream","family":"Moondream","version":"Moondream 3","score":91.1},{"place":29,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.1},{"place":30,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91},{"place":31,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90.97},{"place":32,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":90.93},{"place":33,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90.91},{"place":34,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.9},{"place":35,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":90.6},{"place":36,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":90.45},{"place":37,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.4},{"place":38,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":90.3},{"place":39,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":90.3},{"place":40,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":90.3},{"place":41,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":90.1},{"place":42,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.7},{"place":43,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.7},{"place":44,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":89.7},{"place":45,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":89.6},{"place":46,"model":"ferret-13b","company":"apple","family":"Ferret","version":"Ferret","score":89.48},{"place":47,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":89.4},{"place":48,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":89.36},{"place":49,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.3},{"place":50,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":89.2},{"place":51,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.1},{"place":52,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":89.1},{"place":53,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":88.9},{"place":54,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":88.8},{"place":55,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":88.77},{"place":56,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":88.6},{"place":57,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":88.55},{"place":58,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":88.47},{"place":59,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":88.3},{"place":60,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":88.2},{"place":61,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.1},{"place":62,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":87.9},{"place":63,"model":"shikra-13b","company":"sensetime","family":"Shikra","version":"Shikra","score":87.83},{"place":64,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.8},{"place":65,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.7},{"place":66,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":87.6},{"place":67,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.48},{"place":68,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":87.43},{"place":69,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87.1},{"place":70,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":87.1},{"place":71,"model":"shikra-7b","company":"sensetime","family":"Shikra","version":"Shikra","score":87.01},{"place":72,"model":"shikra-7b","company":"sensetime","family":"Shikra","version":"Shikra","score":87},{"place":73,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":86.7},{"place":74,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.6},{"place":75,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":86},{"place":76,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":85.92},{"place":77,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":85.7},{"place":78,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":85.6},{"place":79,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":85.3},{"place":80,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":84.85},{"place":81,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.8},{"place":82,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.8},{"place":83,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":84.7},{"place":84,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":84.3},{"place":85,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":84.1},{"place":86,"model":"interfaze-1.1-lite","company":"interfaze","family":"Interfaze","version":"Interfaze 1.1","score":83.8},{"place":87,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":83.6},{"place":88,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":82.9},{"place":89,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":82.3},{"place":90,"model":"interfaze","company":"interfaze","family":"Interfaze","version":"Interfaze 1","score":82.1},{"place":91,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":81.47},{"place":92,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.1},{"place":93,"model":"dots.mocr","company":"rednote","family":"dots","version":"dots","score":80.03},{"place":94,"model":"ofa-large","company":"alibaba","family":"OFA","version":"OFA","score":80},{"place":95,"model":"ofa-large","company":"alibaba","family":"OFA","version":"OFA","score":79.96},{"place":96,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.3},{"place":97,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.5},{"place":98,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.8},{"place":99,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.2},{"place":100,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.8},{"place":101,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.6},{"place":102,"model":"north-micro-vision-instruct","company":"cohere","family":"North","version":"North Micro Vision","score":73.2},{"place":103,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.1},{"place":104,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":68.22},{"place":105,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":67.3},{"place":106,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":66.8},{"place":107,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.5},{"place":108,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":58.1},{"place":109,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":57.1},{"place":110,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.9},{"place":111,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":45.1},{"place":112,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":33.6},{"place":113,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":31.7},{"place":114,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.4},{"place":115,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":30.1},{"place":116,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":20.2},{"place":117,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.4},{"place":118,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":2.4},{"place":119,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":1.8}]},{"id":"refcoco-testa-ciou","name":"RefCOCO testA Segmentation (cIoU)","topic":"Referring segmentation","description":"RefCOCO testA referring segmentation, cIoU.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":84.5,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":84.5},{"place":2,"model":"unipixel-7b","company":"polyu","family":"UniPixel","version":"UniPixel","score":83},{"place":3,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":82.9},{"place":4,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":82},{"place":5,"model":"gsva-7b","company":"tsinghua","family":"GSVA","version":"GSVA","score":78.9},{"place":6,"model":"lisa-13b","company":"cuhk","family":"LISA","version":"LISA","score":78.8}]},{"id":"refcocog","name":"RefCOCOg","topic":"Referring expressions","description":"RefCOCOg average accuracy at IoU 0.5 (val).","url":"https://huggingface.co/datasets/JierunChen/Ref-L4","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek-VL2","top_percent":92.8,"top_model_id":"deepseek-vl2","top_generation":"DeepSeek-VL2","top_model_base":"DeepSeek-VL2","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":92.8},{"place":2,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":92.7},{"place":3,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":92.6},{"place":4,"model":"egm-8b","company":"nvidia","family":"EGM","version":"EGM","score":90.8},{"place":5,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.5},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.4},{"place":7,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":89.9},{"place":8,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":89.9},{"place":9,"model":"cogvlm-grounding-generalist","company":"zai","family":"CogVLM","version":"CogVLM","score":89.8},{"place":10,"model":"cogvlm-grounding-generalist","company":"zai","family":"CogVLM","version":"CogVLM","score":89.75},{"place":11,"model":"internvl2-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":89.5},{"place":12,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":89.5},{"place":13,"model":"ferret-v2-7b","company":"apple","family":"Ferret","version":"Ferret-v2","score":89.4},{"place":14,"model":"ferret-v2-13b","company":"apple","family":"Ferret","version":"Ferret-v2","score":89.4},{"place":15,"model":"moondream-9b-a2b","company":"moondream","family":"Moondream","version":"Moondream 3","score":88.6},{"place":16,"model":"texthawk2","company":"huawei","family":"TextHawk","version":"TextHawk2","score":88.2},{"place":17,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.8},{"place":18,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":87.3},{"place":19,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":87.3},{"place":20,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":86.7},{"place":21,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":86.3},{"place":22,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":85.96},{"place":23,"model":"ferret-13b","company":"apple","family":"Ferret","version":"Ferret","score":85.83},{"place":24,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":85.6},{"place":25,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":85.58},{"place":26,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":82.7},{"place":27,"model":"shikra-13b","company":"sensetime","family":"Shikra","version":"Shikra","score":82.64},{"place":28,"model":"shikra-7b","company":"sensetime","family":"Shikra","version":"Shikra","score":82.3},{"place":29,"model":"shikra-7b","company":"sensetime","family":"Shikra","version":"Shikra","score":82.27},{"place":30,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":81.2},{"place":31,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":80.2},{"place":32,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":77.6},{"place":33,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.1},{"place":34,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":73.8},{"place":35,"model":"ofa-large","company":"alibaba","family":"OFA","version":"OFA","score":67.6},{"place":36,"model":"ofa-large","company":"alibaba","family":"OFA","version":"OFA","score":67.57},{"place":37,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":49.8},{"place":38,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":32},{"place":39,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":26.2},{"place":40,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":19.8}]},{"id":"refcocog-rod-f1","name":"RefCOCOg Referring Detection (F1)","topic":"Referring expressions","description":"RefCOCOg test referring object detection (multi-box), F1 mean over IoU 0.5:0.95.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":81.8,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":81.8},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":78.2},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":77.6},{"place":4,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.9},{"place":5,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.6},{"place":6,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":74.3}]},{"id":"refcocog-rod-rejection","name":"RefCOCOg Referring Detection (Rejection)","topic":"Referring expressions","description":"Rejection rate on non-existent referents for RefCOCOg referring detection.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":67.4,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":67.4},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":50.2},{"place":3,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":22.5},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15.2},{"place":5,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":0.6},{"place":6,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":0.5}]},{"id":"refcocog-test-ciou","name":"RefCOCOg test Segmentation (cIoU)","topic":"Referring segmentation","description":"RefCOCOg test referring segmentation, cIoU.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":77.8,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":77.8},{"place":2,"model":"unipixel-7b","company":"polyu","family":"UniPixel","version":"UniPixel","score":77.1},{"place":3,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":76.6},{"place":4,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":74.9},{"place":5,"model":"gsva-7b","company":"tsinghua","family":"GSVA","version":"GSVA","score":73.3},{"place":6,"model":"lisa-13b","company":"cuhk","family":"LISA","version":"LISA","score":70.5}]},{"id":"refcocoplus","name":"RefCOCO+","topic":"Referring expressions","description":"RefCOCO+ accuracy at IoU 0.5 on the val split.","url":"https://huggingface.co/datasets/JierunChen/Ref-L4","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek-VL2","top_percent":91.2,"top_model_id":"deepseek-vl2","top_generation":"DeepSeek-VL2","top_model_base":"DeepSeek-VL2","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":33,"total_models":3854,"placements":[{"place":1,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":91.2},{"place":2,"model":"egm-8b","company":"nvidia","family":"EGM","version":"EGM","score":90.5},{"place":3,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":90.4},{"place":4,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":90.1},{"place":5,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":90.1},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.5},{"place":7,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":89.4},{"place":8,"model":"internvl2-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":88.8},{"place":9,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":88.8},{"place":10,"model":"cogvlm-grounding-generalist","company":"zai","family":"CogVLM","version":"CogVLM","score":88.7},{"place":11,"model":"cogvlm-grounding-generalist","company":"zai","family":"CogVLM","version":"CogVLM","score":88.68},{"place":12,"model":"ferret-v2-7b","company":"apple","family":"Ferret","version":"Ferret-v2","score":87.4},{"place":13,"model":"ferret-v2-13b","company":"apple","family":"Ferret","version":"Ferret-v2","score":87.4},{"place":14,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.4},{"place":15,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.2},{"place":16,"model":"texthawk2","company":"huawei","family":"TextHawk","version":"TextHawk2","score":86.2},{"place":17,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":85.8},{"place":18,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":85.8},{"place":19,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":85.2},{"place":20,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":83.12},{"place":21,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":83.1},{"place":22,"model":"shikra-13b","company":"sensetime","family":"Shikra","version":"Shikra","score":82.89},{"place":23,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":82.82},{"place":24,"model":"ferret-13b","company":"apple","family":"Ferret","version":"Ferret","score":82.81},{"place":25,"model":"moondream-9b-a2b","company":"moondream","family":"Moondream","version":"Moondream 3","score":81.8},{"place":26,"model":"shikra-7b","company":"sensetime","family":"Shikra","version":"Shikra","score":81.6},{"place":27,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":79.8},{"place":28,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":79},{"place":29,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":76},{"place":30,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":75.9},{"place":31,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":73.5},{"place":32,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.2},{"place":33,"model":"ofa-large","company":"alibaba","family":"OFA","version":"OFA","score":68.3},{"place":34,"model":"ofa-large","company":"alibaba","family":"OFA","version":"OFA","score":68.29},{"place":35,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":46.3},{"place":36,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":23.4}]},{"id":"refcocoplus-testa-ciou","name":"RefCOCO+ testA Segmentation (cIoU)","topic":"Referring segmentation","description":"RefCOCO+ testA referring segmentation, cIoU.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":81.1,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":81.1},{"place":2,"model":"unipixel-7b","company":"polyu","family":"UniPixel","version":"UniPixel","score":80.1},{"place":3,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":79.6},{"place":4,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":79},{"place":5,"model":"lisa-13b","company":"cuhk","family":"LISA","version":"LISA","score":70.2},{"place":6,"model":"gsva-7b","company":"tsinghua","family":"GSVA","version":"GSVA","score":69.6}]},{"id":"refspatialbench","name":"RefSpatialBench","topic":"Spatial reasoning","description":"Reference spatial understanding benchmark covering spatial grounding tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":80.14,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":71,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":80.14},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":78},{"place":3,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":76.4},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.6},{"place":5,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":72.1},{"place":6,"model":"ace-brain-0.6-9b","company":"ace-robotics","family":"ACE-Brain","version":"ACE-Brain-0.6","score":71.84},{"place":7,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":71.1},{"place":8,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":70},{"place":9,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.9},{"place":10,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.9},{"place":11,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.3},{"place":12,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.7},{"place":13,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":67.5},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65.5},{"place":15,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64.3},{"place":16,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":63.9},{"place":17,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.5},{"place":18,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":63.2},{"place":19,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.4},{"place":20,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":60.29},{"place":21,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":59.9},{"place":22,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":59.2},{"place":23,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":59.2},{"place":24,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":58.8},{"place":25,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.5},{"place":26,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.3},{"place":27,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":56},{"place":28,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":55.2},{"place":29,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.6},{"place":30,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.51},{"place":31,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":54.51},{"place":32,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.2},{"place":33,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.2},{"place":34,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":54},{"place":35,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":53.4},{"place":36,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.4},{"place":37,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":53.3},{"place":38,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.1},{"place":39,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":53.1},{"place":40,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":52.8},{"place":41,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":52.7},{"place":42,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":52.5},{"place":43,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":52.5},{"place":44,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":51.81},{"place":45,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":51.56},{"place":46,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":50.9},{"place":47,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":50.78},{"place":48,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.5},{"place":49,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":49.5},{"place":50,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":48.5},{"place":51,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":48},{"place":52,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.5},{"place":53,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":47.4},{"place":54,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.6},{"place":55,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":45.8},{"place":56,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.3},{"place":57,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.3},{"place":58,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.6},{"place":59,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":41.8},{"place":60,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":40},{"place":61,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":37.6},{"place":62,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":36.5},{"place":63,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":35},{"place":64,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.6},{"place":65,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":33.1},{"place":66,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.9},{"place":67,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":32.5},{"place":68,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.3},{"place":69,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.9},{"place":70,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.9},{"place":71,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":28.2},{"place":72,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":27.7},{"place":73,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":26.4},{"place":74,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":23.8},{"place":75,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":23.5},{"place":76,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":23.5},{"place":77,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":23},{"place":78,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":22.3},{"place":79,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":21.7},{"place":80,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":21.5},{"place":81,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":15.1},{"place":82,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":12.6},{"place":83,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":12.3},{"place":84,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":11.2},{"place":85,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":9},{"place":86,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.7},{"place":87,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":4.3},{"place":88,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":3},{"place":89,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":2.5},{"place":90,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.2},{"place":91,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":2.17},{"place":92,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":0.4}]},{"id":"refusalbench","name":"RefusalBench","topic":"Safety / refusal","description":"Safety-oriented refusal and policy adherence benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Hermes 4.3 36B Pyche","top_percent":72.29,"top_model_id":"hermes-4.3-36b-pyche","top_generation":"Hermes 4.3","top_model_base":"Hermes 4.3 36B Pyche","top_model_family":"Hermes","top_company":"nousresearch","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"hermes-4.3-36b-pyche","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":72.29},{"place":2,"model":"hermes-4.3-36b","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":66.67},{"place":3,"model":"hermes-4-70b","company":"nousresearch","family":"Hermes","version":"Hermes 4","score":59.5},{"place":4,"model":"hermes-4.3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":59.2}]},{"id":"relytoolbench","name":"RelyToolBench","topic":"Tool hallucination","description":"Benchmark for tool-use reliability and tool hallucination (ToolHallucination).","url":"","leaderboard":"","github":"https://github.com/X-LANCE/ToolHallucination","paper":"","metric":"percent","stars":"","top_model":"Nemotron-3.5-Bolt-E4B-4GB","top_percent":69.29,"top_model_id":"nemotron-3.5-bolt-e4b-4gb","top_generation":"Nemotron 3.5","top_model_base":"Nemotron-3.5 Bolt E4B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":69.29},{"place":2,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":67.15},{"place":3,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":63.16},{"place":4,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.6},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.35},{"place":6,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":41.2},{"place":7,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.97},{"place":8,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.34}]},{"id":"remi","name":"ReMI","topic":"Multimodal reasoning","description":"Reasoning over multimodal inputs (ReMI).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Step3-VL-10B","top_percent":67.29,"top_model_id":"step3-vl-10b","top_generation":"Step3-VL","top_model_base":"Step3-VL 10B","top_model_family":"Step","top_company":"stepfun","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":67.29},{"place":2,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":63.13},{"place":3,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":60.75},{"place":4,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.17},{"place":5,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":52.65}]},{"id":"repobench","name":"RepoBench","topic":"Code understanding","description":"Repository-level code comprehension and reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.5","top_percent":83.82,"top_model_id":"claude-sonnet-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Sonnet 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.82},{"place":2,"model":"gpt-5-codex-medium","company":"openai","family":"GPT","version":"GPT-5","score":67.65},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.35},{"place":4,"model":"gpt-5-codex-high","company":"openai","family":"GPT","version":"GPT-5","score":66.18},{"place":5,"model":"gpt-5-codex-low","company":"openai","family":"GPT","version":"GPT-5","score":64.71},{"place":6,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":64.71},{"place":7,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":63.24},{"place":8,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":61.47},{"place":9,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":61.18},{"place":10,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":60.29},{"place":11,"model":"deepseek-v3.2-exp-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":59.41},{"place":12,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":59.12},{"place":13,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":34},{"place":14,"model":"deepseek-coder-33b","company":"deepseek","family":"DeepSeek Coder","version":"DeepSeek Coder","score":28.4},{"place":15,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":18.4},{"place":16,"model":"codellama-70b","company":"meta","family":"CodeLlama","version":"CodeLlama","score":11.4}]},{"id":"researchrubrics","name":"ResearchRubrics","topic":"Research evaluation","description":"Benchmark evaluating model ability to conduct research and synthesize findings.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":76.2,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":27,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":76.2},{"place":2,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":73.9},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.8},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":73.5},{"place":5,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":71.7},{"place":6,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":71.1},{"place":7,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":68.3},{"place":8,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":67.9},{"place":9,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":66.2},{"place":10,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":65.3},{"place":11,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":64},{"place":12,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":63.6},{"place":13,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":63},{"place":14,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":62},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":61.5},{"place":16,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":60.2},{"place":17,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":59.5},{"place":18,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":59.2},{"place":19,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":56.2},{"place":20,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":55.8},{"place":21,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":54.3},{"place":22,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":50.8},{"place":23,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":50.7},{"place":24,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":47.1},{"place":25,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":44.8},{"place":26,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.2},{"place":27,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":36.9},{"place":28,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.1}]},{"id":"rewardbench","name":"RewardBench","topic":"Reward modeling","description":"Preference/reward model evaluation benchmark.","url":"","leaderboard":"https://huggingface.co/spaces/allenai/reward-bench","github":"","paper":"","metric":"percent","stars":"","top_model":"INF-ORM-Llama3.1-70B","top_percent":95.1,"top_model_id":"inf-orm-llama3.1-70b","top_generation":"INF-ORM-Llama3.1-70B","top_model_base":"INF-ORM-Llama3.1-70B","top_model_family":"INF","top_company":"infly","top_open_source":1,"lower_is_better":false,"bench_models":175,"total_models":3854,"placements":[{"place":1,"model":"inf-orm-llama3.1-70b","company":"infly","family":"INF","version":"INF-ORM-Llama3.1-70B","score":95.1},{"place":2,"model":"ldl-reward-gemma-2-27b-v0.1","company":"shikaichen","family":"LDL","version":"LDL-Reward-Gemma-2-27B-v0.1","score":95},{"place":3,"model":"qrm-gemma-2-27b","company":"nicolinho","family":"QRM","version":"QRM-Gemma-2-27B","score":94.4},{"place":4,"model":"skywork-reward-gemma-2-27b-v0.2","company":"skywork","family":"Skywork","version":"Skywork-Reward-Gemma-2-27B-v0.2","score":94.3},{"place":5,"model":"llama-3.1-nemotron-70b-reward","company":"nvidia","family":"Llama","version":"Llama-3.1-Nemotron-70B-Reward","score":94.1},{"place":6,"model":"skywork-reward-gemma-2-27b","company":"skywork","family":"Skywork","version":"Skywork-Reward-Gemma-2-27B","score":93.8},{"place":7,"model":"texteval-llama3.1-70b","company":"sf-foundation","family":"TextEval","version":"TextEval-Llama3.1-70B","score":93.5},{"place":8,"model":"metametrics-rm-v1.0","company":"meta-metrics","family":"MetaMetrics","version":"MetaMetrics-RM-v1.0","score":93.4},{"place":9,"model":"skywork-critic-llama-3.1-70b","company":"skywork","family":"Skywork","version":"Skywork-Critic-Llama-3.1-70B","score":93.3},{"place":10,"model":"qrm-llama3.1-8b-v2","company":"nicolinho","family":"QRM","version":"QRM-Llama3.1-8B-v2","score":93.1},{"place":11,"model":"skywork-reward-llama-3.1-8b-v0.2","company":"skywork","family":"Skywork","version":"Skywork-Reward-Llama-3.1-8B-v0.2","score":93.1},{"place":12,"model":"qrm-llama3.1-8b","company":"nicolinho","family":"QRM","version":"QRM-Llama3.1-8B","score":93.1},{"place":13,"model":"urm-llama-3.1-8b","company":"lxzgordon","family":"URM","version":"URM-LLaMa-3.1-8B","score":92.9},{"place":14,"model":"sfr-llama-3.1-70b-judge-r","company":"salesforce","family":"SFR","version":"SFR-LLaMa-3.1-70B-Judge-r","score":92.7},{"place":15,"model":"rise-judge-qwen2.5-32b","company":"r-i-s-e","family":"RISE","version":"RISE-Judge-Qwen2.5-32B","score":92.7},{"place":16,"model":"skywork-reward-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-Reward-Llama-3.1-8B","score":92.5},{"place":17,"model":"selene-1","company":"atla","family":"Selene","version":"Selene","score":92.4},{"place":18,"model":"gpm-llama-3.1-8b","company":"general-preference","family":"GPM","version":"GPM-Llama-3.1-8B","score":92.2},{"place":19,"model":"nemotron-4-340b-reward","company":"nvidia","family":"Nemotron","version":"Nemotron-4-340B-Reward","score":92},{"place":20,"model":"qwen2.5-rm-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":91.59},{"place":21,"model":"grm-llama3-8b-rewardmodel-ft","company":"ray2333","family":"GRM","version":"GRM-Llama3-8B-rewardmodel-ft","score":91.5},{"place":22,"model":"qrm-llama3-8b","company":"nicolinho","family":"QRM","version":"QRM-Llama3-8B","score":91.1},{"place":23,"model":"texteval-offsetbias-12b","company":"sf-foundation","family":"TextEval","version":"TextEval-OffsetBias-12B","score":91},{"place":24,"model":"grm-llama3.2-3b-rewardmodel-ft","company":"ray2333","family":"GRM","version":"GRM-llama3.2-3B-rewardmodel-ft","score":90.9},{"place":25,"model":"sfr-nemo-12b-judge-r","company":"salesforce","family":"SFR","version":"SFR-nemo-12B-Judge-r","score":90.3},{"place":26,"model":"internlm2-20b-reward","company":"internlm","family":"internlm2","version":"internlm2-20b-reward","score":90.2},{"place":27,"model":"llama-3.1-70b-instruct-rm-rb2","company":"allenai","family":"Llama","version":"Llama-3.1-70B-Instruct-RM-RB2","score":90.2},{"place":28,"model":"skywork-vl-reward-7b","company":"skywork","family":"Skywork","version":"Skywork-VL-Reward-7B","score":90.1},{"place":29,"model":"self-taught-evaluator-llama3.1-70b","company":"facebook","family":"Self","version":"Self-taught-evaluator-llama3.1-70B","score":90},{"place":30,"model":"urm-llama-3-8b","company":"lxzgordon","family":"URM","version":"URM-LLaMa-3-8B","score":89.9},{"place":31,"model":"llama-3-offsetbias-rm-8b","company":"ncsoft","family":"Llama","version":"Llama-3-OffsetBias-RM-8B","score":89.4},{"place":32,"model":"selene-1-mini-llama-3.1-8b","company":"atlaai","family":"Selene","version":"Selene-1-Mini-Llama-3.1-8B","score":89.1},{"place":33,"model":"skywork-critic-llama-3.1-8b","company":"skywork","family":"Skywork","version":"Skywork-Critic-Llama-3.1-8B","score":89},{"place":34,"model":"llama-3.1-8b-instruct-rm-rb2","company":"allenai","family":"Llama","version":"Llama-3.1-8B-Instruct-RM-RB2","score":88.9},{"place":35,"model":"llama-3.1-tulu-3-70b-sft-rm-rb2","company":"allenai","family":"Llama","version":"Llama-3.1-Tulu-3-70B-SFT-RM-RB2","score":88.9},{"place":36,"model":"llama3-70b-steerlm-rm","company":"nvidia","family":"Llama3","version":"Llama3-70B-SteerLM-RM","score":88.8},{"place":37,"model":"sfr-llama-3.1-8b-judge-r","company":"salesforce","family":"SFR","version":"SFR-LLaMa-3.1-8B-Judge-r","score":88.7},{"place":38,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":88.7},{"place":39,"model":"self-taught-llama-3-70b","company":"facebook","family":"Self","version":"Self-taught-Llama-3-70B","score":88.6},{"place":40,"model":"armorm-llama3-8b-v0.1","company":"rlhflow","family":"ArmoRM","version":"ArmoRM-Llama3-8B-v0.1","score":88.6},{"place":41,"model":"grm-gemma2-2b-rewardmodel-ft","company":"ray2333","family":"GRM","version":"GRM-gemma2-2B-rewardmodel-ft","score":88.4},{"place":42,"model":"athene-rm-70b","company":"nexusflow","family":"Athene","version":"Athene","score":88.32},{"place":43,"model":"gemini-1.5-pro-api-0514","company":"google","family":"Gemini","version":"Gemini 1.5","score":88.2},{"place":44,"model":"rise-judge-qwen2.5-7b","company":"r-i-s-e","family":"RISE","version":"RISE-Judge-Qwen2.5-7B","score":88.2},{"place":45,"model":"cohere-rm-may-2024","company":"cohere","family":"Cohere RM","version":"Cohere RM","score":88.2},{"place":46,"model":"flame-1.0-24b-july-2024","company":"google","family":"FLAMe","version":"FLAMe","score":87.8},{"place":47,"model":"internlm2-7b-reward","company":"internlm","family":"internlm2","version":"internlm2-7b-reward","score":87.6},{"place":48,"model":"con-j-qwen2-7b","company":"ziyiye","family":"Con","version":"Con-J-Qwen2-7B","score":87.1},{"place":49,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":87},{"place":50,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":86.8},{"place":51,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":86.7},{"place":52,"model":"pair-preference-model-llama3-8b","company":"rlhflow","family":"pair","version":"pair-preference-model-LLaMA3-8B","score":85.7},{"place":53,"model":"llama-3.1-tulu-3-8b-sft-rm-rb2","company":"allenai","family":"Llama","version":"Llama-3.1-Tulu-3-8B-SFT-RM-RB2","score":85.5},{"place":54,"model":"grm-llama3-8b-sftreg","company":"ray2333","family":"GRM","version":"GRM-llama3-8B-sftreg","score":85.4},{"place":55,"model":"compassjudger-1-32b-instruct","company":"opencompass","family":"CompassJudger","version":"CompassJudger-1-32B-Instruct","score":85.2},{"place":56,"model":"cohere-rm-march-2024","company":"cohere","family":"Cohere RM","version":"Cohere RM","score":85.1},{"place":57,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":84.7},{"place":58,"model":"grm-llama3-8b-distill","company":"ray2333","family":"GRM","version":"GRM-llama3-8B-distill","score":84.6},{"place":59,"model":"llama-3.1-8b-base-rm-rb2","company":"allenai","family":"Llama","version":"Llama-3.1-8B-Base-RM-RB2","score":84.6},{"place":60,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":84.6},{"place":61,"model":"grm-gemma-2b-rewardmodel-ft","company":"ray2333","family":"GRM","version":"GRM-Gemma-2B-rewardmodel-ft","score":84.5},{"place":62,"model":"gpt-4-0125-preview","company":"openai","family":"GPT","version":"GPT-4","score":84.3},{"place":63,"model":"llama-3.1-tulu-3-8b-dpo-rm-rb2","company":"allenai","family":"Llama","version":"Llama-3.1-Tulu-3-8B-DPO-RM-RB2","score":84.3},{"place":64,"model":"reflection-llama-3.1-70b","company":"mattshumer","family":"Reflection","version":"Reflection","score":84.2},{"place":65,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":84.2},{"place":66,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84.1},{"place":67,"model":"compassjudger-1-14b-instruct","company":"opencompass","family":"CompassJudger","version":"CompassJudger-1-14B-Instruct","score":84.1},{"place":68,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":84.1},{"place":69,"model":"llama-3-offsetbias-8b","company":"ncsoft","family":"Llama","version":"Llama-3-OffsetBias-8B","score":84},{"place":70,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":84},{"place":71,"model":"llama-3.1-tulu-3-8b-rl-rm-rb2","company":"allenai","family":"Llama","version":"Llama-3.1-Tulu-3-8B-RL-RM-RB2","score":83.7},{"place":72,"model":"fsfairx-llama3-rm-v0.1","company":"sfairxc","family":"FsfairX","version":"FsfairX-LLaMA3-RM-v0.1","score":83.4},{"place":73,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":83.3},{"place":74,"model":"compassjudger-1-7b-instruct","company":"opencompass","family":"CompassJudger","version":"CompassJudger-1-7B-Instruct","score":83.2},{"place":75,"model":"internlm2-1-8b-reward","company":"internlm","family":"internlm2","version":"internlm2-1_8b-reward","score":82.2},{"place":76,"model":"btrm-qwen2-7b-0613","company":"cir-ams","family":"BTRM","version":"BTRM_Qwen2_7b_0613","score":81.7},{"place":77,"model":"eurus-rm-7b","company":"openbmb","family":"Eurus","version":"Eurus-RM-7b","score":81.6},{"place":78,"model":"starling-rm-34b","company":"nexusflow","family":"Starling","version":"Starling-RM-34B","score":81.3},{"place":79,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":80.9},{"place":80,"model":"gemini-1.5-flash-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":80.5},{"place":81,"model":"gemma-2b-rewardmodel-ft","company":"ray2333","family":"Gemma","version":"Gemma-2B-rewardmodel-ft","score":80.5},{"place":82,"model":"tulu-v2.5-13b-preference-mix-rm","company":"allenai","family":"tulu","version":"tulu-v2.5-13b-preference-mix-rm","score":80.3},{"place":83,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":80.1},{"place":84,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":80.1},{"place":85,"model":"rm-mistral-7b","company":"weqweasdas","family":"RM","version":"RM-Mistral-7B","score":79.8},{"place":86,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.5},{"place":87,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":78.5},{"place":88,"model":"mistral-rm-for-raft-gshf-v0","company":"hendrydong","family":"Mistral","version":"Mistral-RM-for-RAFT-GSHF-v0","score":78.5},{"place":89,"model":"reward-model-mistral-7b-instruct-unified-feedback","company":"ray2333","family":"reward","version":"reward-model-Mistral-7B-instruct-Unified-Feedback","score":76.6},{"place":90,"model":"mmpo-gemma-7b-gamma1.1-epoch3","company":"ahjeong","family":"MMPO","version":"MMPO_Gemma_7b_gamma1.1_epoch3","score":76.5},{"place":91,"model":"stablelm-2-12b-chat","company":"stabilityai","family":"stablelm","version":"stablelm-2-12b-chat","score":76.4},{"place":92,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":76.3},{"place":93,"model":"tulu-2-dpo-70b","company":"ai2","family":"Tulu","version":"Tulu 2 DPO 70B","score":76.2},{"place":94,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":76},{"place":95,"model":"mmpo-gemma-7b","company":"ahjeong","family":"MMPO","version":"MMPO_Gemma_7b","score":75.9},{"place":96,"model":"llama-3-tulu-2-dpo-70b","company":"allenai","family":"llama","version":"llama-3-tulu-2-dpo-70b","score":75},{"place":97,"model":"nous-hermes-2-mistral-7b-dpo","company":"nousresearch","family":"Nous","version":"Nous-Hermes-2-Mistral-7B-DPO","score":74.8},{"place":98,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":74.6},{"place":99,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":74.5},{"place":100,"model":"prometheus-8x7b-v2.0","company":"prometheus-eval","family":"prometheus","version":"prometheus-8x7b-v2.0","score":74.5},{"place":101,"model":"grm-gemma-2b-sftreg","company":"ray2333","family":"GRM","version":"GRM-Gemma-2B-sftreg","score":74.5},{"place":102,"model":"gpm-gemma-2b","company":"general-preference","family":"GPM","version":"GPM-Gemma-2B","score":74.5},{"place":103,"model":"matter-0.1-7b-boost-dpo-preview","company":"0-hero","family":"Matter","version":"Matter-0.1-7B-boost-DPO-preview","score":74.5},{"place":104,"model":"tulu-v2.5-70b-uf-rm","company":"allenai","family":"tulu","version":"tulu-v2.5-70b-uf-rm","score":74},{"place":105,"model":"zephyr-7b-alpha","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Alpha","score":73.9},{"place":106,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":73.9},{"place":107,"model":"tulu-2-dpo-13b","company":"allenai","family":"tulu","version":"tulu-2-dpo-13b","score":73.7},{"place":108,"model":"compassjudger-1-1.5b-instruct","company":"opencompass","family":"CompassJudger","version":"CompassJudger-1-1.5B-Instruct","score":73.4},{"place":109,"model":"llama-3-tulu-2-8b-uf-mean-rm","company":"allenai","family":"llama","version":"llama-3-tulu-2-8b-uf-mean-rm","score":73.4},{"place":110,"model":"starchat2-15b-v0.1","company":"huggingface","family":"starchat2-15b-v0.1","version":"starchat2-15b-v0.1","score":73.2},{"place":111,"model":"gemma-2b-rewardmodel-baseline","company":"ray2333","family":"Gemma","version":"Gemma-2B-rewardmodel-baseline","score":72.9},{"place":112,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":72.9},{"place":113,"model":"zephyr-7b-beta","company":"huggingface","family":"Zephyr","version":"Zephyr 7B Beta","score":72.8},{"place":114,"model":"llama-3-tulu-2-dpo-8b","company":"allenai","family":"llama","version":"llama-3-tulu-2-dpo-8b","score":72.7},{"place":115,"model":"matter-0.1-7b-dpo-preview","company":"0-hero","family":"Matter","version":"Matter-0.1-7B-DPO-preview","score":72.5},{"place":116,"model":"bagel-dpo-34b-v0.5","company":"jondurbin","family":"bagel","version":"bagel-dpo-34b-v0.5","score":72.2},{"place":117,"model":"tulu-2-dpo-7b","company":"allenai","family":"tulu","version":"tulu-2-dpo-7b","score":72.1},{"place":118,"model":"prometheus-7b-v2.0","company":"prometheus-eval","family":"prometheus","version":"prometheus-7b-v2.0","score":72},{"place":119,"model":"stablelm-zephyr-3b","company":"stabilityai","family":"stablelm","version":"stablelm-zephyr-3b","score":71.5},{"place":120,"model":"nous-hermes-2-mixtral-8x7b-dpo","company":"nousresearch","family":"Nous Hermes","version":"Nous Hermes 2","score":71.4},{"place":121,"model":"starling-rm-7b-alpha","company":"berkeley-nest","family":"Starling","version":"Starling-RM-7B-alpha","score":71.1},{"place":122,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":70.6},{"place":123,"model":"llama-3-tulu-2-70b-uf-mean-rm","company":"allenai","family":"llama","version":"llama-3-tulu-2-70b-uf-mean-rm","score":70.2},{"place":124,"model":"rm-gemma-7b","company":"weqweasdas","family":"RM","version":"RM-Gemma-7B","score":69.7},{"place":125,"model":"rm-gemma-7b-4096","company":"weqweasdas","family":"RM","version":"RM-Gemma-7B-4096","score":69.2},{"place":126,"model":"ultrarm-13b","company":"openbmb","family":"UltraRM","version":"UltraRM-13b","score":69},{"place":127,"model":"oasst-rm-2.1-pythia-1.4b-epoch-2.5","company":"openassistant","family":"oasst","version":"oasst-rm-2.1-pythia-1.4b-epoch-2.5","score":69},{"place":128,"model":"eurus-7b-kto","company":"openbmb","family":"Eurus","version":"Eurus-7b-kto","score":69},{"place":129,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":68.6},{"place":130,"model":"llama3-iterative-dpo-final","company":"rlhflow","family":"LLaMA3","version":"LLaMA3-iterative-DPO-final","score":67.8},{"place":131,"model":"zephyr-7b-gemma-v0.1","company":"huggingfaceh4","family":"zephyr","version":"zephyr-7b-gemma-v0.1","score":67.6},{"place":132,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":67.5},{"place":133,"model":"minicpm-2b-dpo-fp32","company":"openbmb","family":"MiniCPM","version":"MiniCPM-2B-dpo-fp32","score":67.3},{"place":134,"model":"better-pairrm","company":"mightbe","family":"Better","version":"Better-PairRM","score":67.3},{"place":135,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":67.3},{"place":136,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":67.2},{"place":137,"model":"qwen1.5-moe-a2.7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.4},{"place":138,"model":"rewardmodel-mistral-7b-for-dpa-v1","company":"rlhflow","family":"RewardModel","version":"RewardModel-Mistral-7B-for-DPA-v1","score":66.3},{"place":139,"model":"stablelm-2-zephyr-1.6b","company":"stabilityai","family":"StableLM","version":"StableLM 2","score":65.7},{"place":140,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":65.7},{"place":141,"model":"rm-gemma-2b","company":"weqweasdas","family":"RM","version":"RM-Gemma-2B","score":65.5},{"place":142,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":65.3},{"place":143,"model":"tulu-v2.5-70b-preference-mix-rm","company":"allenai","family":"tulu","version":"tulu-v2.5-70b-preference-mix-rm","score":65.2},{"place":144,"model":"faro-yi-9b-dpo","company":"wenbopan","family":"Faro","version":"Faro-Yi-9B-DPO","score":64.6},{"place":145,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":64.5},{"place":146,"model":"ziya-llama-7b-reward","company":"idea-ccnl","family":"Ziya","version":"Ziya-LLaMA-7B-Reward","score":63.8},{"place":147,"model":"beaver-7b-v2.0-reward","company":"pku-alignment","family":"beaver","version":"beaver-7b-v2.0-reward","score":63.7},{"place":148,"model":"stable-code-instruct-3b","company":"stabilityai","family":"stable","version":"stable-code-instruct-3b","score":62.2},{"place":149,"model":"oasst-rm-2-pythia-6.9b-epoch-1","company":"openassistant","family":"oasst","version":"oasst-rm-2-pythia-6.9b-epoch-1","score":61.5},{"place":150,"model":"reward-model-deberta-v3-large-v2","company":"openassistant","family":"reward","version":"reward-model-deberta-v3-large-v2","score":61.3},{"place":151,"model":"pairrm-hf","company":"llm-blender","family":"PairRM","version":"PairRM-hf","score":60.9},{"place":152,"model":"beaver-7b-v2.0-cost","company":"pku-alignment","family":"beaver","version":"beaver-7b-v2.0-cost","score":59.6},{"place":153,"model":"archangel-sft-kto-llama13b","company":"contextualai","family":"archangel","version":"archangel_sft-kto_llama13b","score":59.5},{"place":154,"model":"archangel-sft-kto-llama30b","company":"contextualai","family":"archangel","version":"archangel_sft-kto_llama30b","score":59},{"place":155,"model":"qwen1.5-1.8b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":58.9},{"place":156,"model":"beaver-7b-v1.0-cost","company":"pku-alignment","family":"beaver","version":"beaver-7b-v1.0-cost","score":58},{"place":157,"model":"archangel-sft-dpo-llama30b","company":"contextualai","family":"archangel","version":"archangel_sft-dpo_llama30b","score":56.2},{"place":158,"model":"archangel-sft-kto-pythia1-4b","company":"contextualai","family":"archangel","version":"archangel_sft-kto_pythia1-4b","score":55.8},{"place":159,"model":"archangel-sft-kto-pythia6-9b","company":"contextualai","family":"archangel","version":"archangel_sft-kto_pythia6-9b","score":55.6},{"place":160,"model":"archangel-sft-kto-pythia2-8b","company":"contextualai","family":"archangel","version":"archangel_sft-kto_pythia2-8b","score":55},{"place":161,"model":"qwen1.5-4b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":54.8},{"place":162,"model":"archangel-sft-dpo-llama13b","company":"contextualai","family":"archangel","version":"archangel_sft-dpo_llama13b","score":54},{"place":163,"model":"archangel-sft-kto-llama7b","company":"contextualai","family":"archangel","version":"archangel_sft-kto_llama7b","score":53.9},{"place":164,"model":"archangel-sft-dpo-llama7b","company":"contextualai","family":"archangel","version":"archangel_sft-dpo_llama7b","score":53},{"place":165,"model":"qwen1.5-0.5b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":53},{"place":166,"model":"archangel-sft-dpo-pythia2-8b","company":"contextualai","family":"archangel","version":"archangel_sft-dpo_pythia2-8b","score":52.9},{"place":167,"model":"archangel-sft-dpo-pythia6-9b","company":"contextualai","family":"archangel","version":"archangel_sft-dpo_pythia6-9b","score":52.6},{"place":168,"model":"archangel-sft-dpo-pythia1-4b","company":"contextualai","family":"archangel","version":"archangel_sft-dpo_pythia1-4b","score":52.3},{"place":169,"model":"steamshp-flan-t5-xl","company":"stanfordnlp","family":"SteamSHP","version":"SteamSHP-flan-t5-xl","score":51.3},{"place":170,"model":"smoltulu-1.7b-rm","company":"sultanr","family":"SmolTulu","version":"SmolTulu-1.7b-RM","score":50.9},{"place":171,"model":"archangel-sft-kto-pythia12-0b","company":"contextualai","family":"archangel","version":"archangel_sft-kto_pythia12-0b","score":50.5},{"place":172,"model":"hh-rlhf-rm-open-llama-3b","company":"weqweasdas","family":"hh","version":"hh_rlhf_rm_open_llama_3b","score":50.3},{"place":173,"model":"archangel-sft-dpo-pythia12-0b","company":"contextualai","family":"archangel","version":"archangel_sft-dpo_pythia12-0b","score":50.1},{"place":174,"model":"steamshp-flan-t5-large","company":"stanfordnlp","family":"SteamSHP","version":"SteamSHP-flan-t5-large","score":49.6},{"place":175,"model":"tulu-v2.5-13b-uf-rm","company":"allenai","family":"tulu","version":"tulu-v2.5-13b-uf-rm","score":48.1},{"place":176,"model":"beaver-7b-v1.0-reward","company":"pku-alignment","family":"beaver","version":"beaver-7b-v1.0-reward","score":47.3}]},{"id":"riemannbench","name":"RiemannBench","topic":"Research math","description":"Research-level mathematics benchmark (reported in Anthropic Fable 5/Mythos 5 system card).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":76,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":76},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":72},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":69.6},{"place":4,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":65.6},{"place":5,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":55},{"place":6,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":43},{"place":7,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":34}]},{"id":"roboafford","name":"RoboAfford","topic":"Embodied reasoning","description":"Robotic affordance (object & spatial) grounding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ACE-Brain-0.6-9B","top_percent":88.14,"top_model_id":"ace-brain-0.6-9b","top_generation":"ACE-Brain-0.6","top_model_base":"ACE-Brain-0.6 9B","top_model_family":"ACE-Brain","top_company":"ace-robotics","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"ace-brain-0.6-9b","company":"ace-robotics","family":"ACE-Brain","version":"ACE-Brain-0.6","score":88.14},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":84.94},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":84.6},{"place":4,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":83.4},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":82.3},{"place":6,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":81.1},{"place":7,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":80.4},{"place":8,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":76.9},{"place":9,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":75.9},{"place":10,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":75.8},{"place":11,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":75.1},{"place":12,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":74},{"place":13,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":71.8},{"place":14,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":71.8},{"place":15,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":71.7},{"place":16,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":71.48},{"place":17,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":71.45},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":68.04},{"place":19,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.8}]},{"id":"roborefit","name":"RoboRefIt","topic":"Embodied reasoning","description":"Referring-expression grounding in cluttered robotic scenes.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"PhysBrain1.5-8B","top_percent":89.6,"top_model_id":"physbrain1.5-8b","top_generation":"PhysBrain 1.5","top_model_base":"PhysBrain 1.5 8B","top_model_family":"PhysBrain","top_company":"deepcybo","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":89.6},{"place":2,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":86.8},{"place":3,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":86.2},{"place":4,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":86.1},{"place":5,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":85.9},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":85.1},{"place":7,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":84.6},{"place":8,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.5},{"place":9,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":82.8},{"place":10,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":82.5},{"place":11,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":81.9},{"place":12,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.3},{"place":13,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":75.5}]},{"id":"robospatialhome","name":"RoboSpatialHome","topic":"Embodied spatial understanding","description":"RoboSpatialHome benchmark for embodied spatial reasoning in domestic environments.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":80.94,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":80.94},{"place":2,"model":"ace-brain-0.6-9b","company":"ace-robotics","family":"ACE-Brain","version":"ACE-Brain-0.6","score":76.56},{"place":3,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.9},{"place":4,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":73.9},{"place":5,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":73.7},{"place":6,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":73.3},{"place":7,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":73.1},{"place":8,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":72.4},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":72},{"place":10,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":72},{"place":11,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":71.2},{"place":12,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":71},{"place":13,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":70.9},{"place":14,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":70.4},{"place":15,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":70.2},{"place":16,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":70},{"place":17,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":69.7},{"place":18,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":69.55},{"place":19,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":69.4},{"place":20,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.7},{"place":21,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":67.3},{"place":22,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.9},{"place":23,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":66.4},{"place":24,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":65.9},{"place":25,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":65.7},{"place":26,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":65},{"place":27,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.6},{"place":28,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.34},{"place":29,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.2},{"place":30,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.9},{"place":31,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":62.3},{"place":32,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":61.8},{"place":33,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.7},{"place":34,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":60.1},{"place":35,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":59.19},{"place":36,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":59},{"place":37,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.2},{"place":38,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":57.5},{"place":39,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":57.4},{"place":40,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56},{"place":41,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":56},{"place":42,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":55.7},{"place":43,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":55.4},{"place":44,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.4},{"place":45,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.7},{"place":46,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":54.2},{"place":47,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.1},{"place":48,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":53.5},{"place":49,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":52.86},{"place":50,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":49.43},{"place":51,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.1},{"place":52,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.5},{"place":53,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.3},{"place":54,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":44.8},{"place":55,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":44.6},{"place":56,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":44.6},{"place":57,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":43.78},{"place":58,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":41.2},{"place":59,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":40.9}]},{"id":"robotgrounding-inhouse","name":"RobotGrounding (in-house)","topic":"Embodied grounding","description":"ACE Robotics in-house robot grounding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ACE-Brain-0.6-9B","top_percent":93.42,"top_model_id":"ace-brain-0.6-9b","top_generation":"ACE-Brain-0.6","top_model_base":"ACE-Brain-0.6 9B","top_model_family":"ACE-Brain","top_company":"ace-robotics","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"ace-brain-0.6-9b","company":"ace-robotics","family":"ACE-Brain","version":"ACE-Brain-0.6","score":93.42},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":91.1},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":90.89},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":85.18},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":83.96},{"place":6,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":78.51}]},{"id":"robovqa","name":"RoboVQA","topic":"Embodied reasoning","description":"Robotics video question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"PhysBrain1.5-2B","top_percent":62.9,"top_model_id":"physbrain1.5-2b","top_generation":"PhysBrain 1.5","top_model_base":"PhysBrain 1.5 2B","top_model_family":"PhysBrain","top_company":"deepcybo","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":62.9},{"place":2,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":61.5},{"place":3,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":60.9},{"place":4,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":60.8},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.5},{"place":6,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":55.5},{"place":7,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":51.5},{"place":8,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":48.4},{"place":9,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":44.7},{"place":10,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":41.7},{"place":11,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":41.2},{"place":12,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":37},{"place":13,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":36}]},{"id":"rolebench","name":"RoleBench","topic":"Role-playing","description":"Role-playing benchmark from RoleLLM measuring character speaking style and role-specific knowledge.","url":"","leaderboard":"","github":"https://github.com/InteractiveNLP-Team/RoleLLM-public","paper":"","metric":"percent","stars":"","top_model":"Nemotron-3.5-Bolt-E4B-4GB","top_percent":71.21,"top_model_id":"nemotron-3.5-bolt-e4b-4gb","top_generation":"Nemotron 3.5","top_model_base":"Nemotron-3.5 Bolt E4B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.21},{"place":2,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.05},{"place":3,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":60.51},{"place":4,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.66},{"place":5,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.35},{"place":6,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":49.95},{"place":7,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":12.02},{"place":8,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":10.86}]},{"id":"rolemrc","name":"RoleMRC","topic":"Role-playing","description":"Role-playing and instruction-following benchmark built from machine reading comprehension.","url":"","leaderboard":"","github":"https://github.com/LuJunru/RoleMRC","paper":"","metric":"percent","stars":"","top_model":"Nemotron-3.5-Bolt-E4B","top_percent":80.63,"top_model_id":"nemotron-3.5-bolt-e4b","top_generation":"Nemotron 3.5","top_model_base":"Nemotron-3.5 Bolt E4B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":80.63},{"place":2,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":79.12},{"place":3,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":75.24},{"place":4,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.62},{"place":5,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.81},{"place":6,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.61},{"place":7,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":47},{"place":8,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":45.84}]},{"id":"roo-code-evals","name":"Roo Code Evals","topic":"Code assistant eval","description":"Community-maintained coding evals and leaderboard by Roo Code.","url":"https://roocode.com/evals","leaderboard":"https://roocode.com/evals","github":"https://github.com/RooCodeInc/Roo-Code-Evals","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":100,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":40,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":100},{"place":2,"model":"gpt-5.2-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":100},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":100},{"place":4,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":100},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":100},{"place":6,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":99},{"place":7,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":98},{"place":8,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":98},{"place":9,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":98},{"place":10,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":97},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":96},{"place":12,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":95},{"place":13,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":95},{"place":14,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":95},{"place":15,"model":"kimi-k2-instruct-0905-groq","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":94},{"place":16,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":94},{"place":17,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":91},{"place":18,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":90},{"place":19,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":90},{"place":20,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":90},{"place":21,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":90},{"place":22,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":89},{"place":23,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89},{"place":24,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":89},{"place":25,"model":"sonoma-sky","company":"","family":"Sonoma","version":"Sonoma","score":86},{"place":26,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":86},{"place":27,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":86},{"place":28,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":85},{"place":29,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":84},{"place":30,"model":"kimi-k2-instruct-0711","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":83},{"place":31,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":83},{"place":32,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":79},{"place":33,"model":"sonoma-dusk","company":"","family":"Sonoma","version":"Sonoma","score":78},{"place":34,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":78},{"place":35,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":77},{"place":36,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":75},{"place":37,"model":"qwen3-next","company":"qwen","family":"Qwen","version":"Qwen3","score":73},{"place":38,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":72},{"place":39,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":54},{"place":40,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":52}]},{"id":"routerbench-decision","name":"RouterBench (decision)","topic":"Model routing","description":"Choose which LLM to route a query to; selected quality (quality objective). Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/withmartian/routerbench","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"score","stars":"","top_model":"Kev 9B","top_percent":80,"top_model_id":"kev-9b","top_generation":"Kev","top_model_base":"Kev","top_model_family":"Kev","top_company":"jaredpalmer","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":80},{"place":2,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":79.9},{"place":3,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":79.9},{"place":4,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":79.9},{"place":5,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":79.9},{"place":6,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":79.9},{"place":7,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":79.9},{"place":8,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":79.9},{"place":9,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":79.8},{"place":10,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":79.8},{"place":11,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":79.8},{"place":12,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":79.8},{"place":13,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":79.8},{"place":14,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":79.7},{"place":15,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":79.7},{"place":16,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":79.6},{"place":17,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":79.5},{"place":18,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":79.5},{"place":19,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":79.3},{"place":20,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":79},{"place":21,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":79},{"place":22,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":78.9},{"place":23,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":78.7},{"place":24,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":78.3},{"place":25,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":77.8},{"place":26,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":77.8},{"place":27,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":76.5},{"place":28,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":76.5},{"place":29,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":74.5},{"place":30,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":73.4},{"place":31,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":71.2},{"place":32,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":67.8},{"place":33,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":59.8},{"place":34,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":59.4},{"place":35,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":58.7},{"place":36,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":57.1},{"place":37,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":56.6},{"place":38,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":51.6}]},{"id":"ruler-100-1m","name":"RULER-100 @1M","topic":"Long-context eval","description":"RULER-100 evaluation at a 1M context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","top_percent":86.3,"top_model_id":"nvidia-nemotron-3-nano-30b-a3b-bf16","top_generation":"Nemotron 3","top_model_base":"Nemotron-3 Nano 30B A3B BF16","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.3},{"place":2,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.5}]},{"id":"ruler-100-256k","name":"RULER-100 @256k","topic":"Long-context eval","description":"RULER-100 evaluation at a 256k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","top_percent":92.9,"top_model_id":"nvidia-nemotron-3-nano-30b-a3b-bf16","top_generation":"Nemotron 3","top_model_base":"Nemotron-3 Nano 30B A3B BF16","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.9},{"place":2,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.4}]},{"id":"ruler-100-512k","name":"RULER-100 @512k","topic":"Long-context eval","description":"RULER-100 evaluation at a 512k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","top_percent":91.3,"top_model_id":"nvidia-nemotron-3-nano-30b-a3b-bf16","top_generation":"Nemotron 3","top_model_base":"Nemotron-3 Nano 30B A3B BF16","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.3},{"place":2,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84}]},{"id":"ruler-128k","name":"Ruler 128k","topic":"Long-context eval","description":"RULER benchmark at 128k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Qwen3-Next-80B-A3B-Instruct","top_percent":96,"top_model_id":"qwen3-next-80b-a3b-instruct","top_generation":"Qwen3 Next","top_model_base":"Qwen3 Next 80B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":44,"total_models":3854,"placements":[{"place":1,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":96},{"place":2,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":95.6},{"place":3,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":95.4},{"place":4,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":93.9},{"place":5,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.49},{"place":6,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":91.88},{"place":7,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.1},{"place":8,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":90.2},{"place":9,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.66},{"place":10,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":89.4},{"place":11,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":89.37},{"place":12,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.1},{"place":13,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89},{"place":14,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":88.61},{"place":15,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":88.4},{"place":16,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":84.5},{"place":17,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":83.1},{"place":18,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.92},{"place":19,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82},{"place":20,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":81.38},{"place":21,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":81.2},{"place":22,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":78.9},{"place":23,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":78.1},{"place":24,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":77.4},{"place":25,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":77},{"place":26,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":76.9},{"place":27,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.1},{"place":28,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.74},{"place":29,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":71.41},{"place":30,"model":"llama3-3.2b","company":"meta","family":"Llama","version":"Llama 3","score":71.3},{"place":31,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":68.8},{"place":32,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":68.01},{"place":33,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.6},{"place":34,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":65.8},{"place":35,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":63.62},{"place":36,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":57.6},{"place":37,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":57.56},{"place":38,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":57.1},{"place":39,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":56.12},{"place":40,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":55.77},{"place":41,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":55.3},{"place":42,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":55.1},{"place":43,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":45.09},{"place":44,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":36.33},{"place":45,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":35.1},{"place":46,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":28},{"place":47,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":25.5},{"place":48,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":0}]},{"id":"ruler-16k","name":"Ruler 16k","topic":"Long-context eval","description":"RULER benchmark at 16k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Qwen2.5-72B-Instruct","top_percent":97.7,"top_model_id":"qwen2.5-72b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":97.7},{"place":2,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.9},{"place":3,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.5},{"place":4,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.5},{"place":5,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":95.4},{"place":6,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":95.2},{"place":7,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":93.7},{"place":8,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":92.7},{"place":9,"model":"qwen-2.5-7.6b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":92.2},{"place":10,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":92.2},{"place":11,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":92.1},{"place":12,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":91.6},{"place":13,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":91.28},{"place":14,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":91.28},{"place":15,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":90.73},{"place":16,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":90.73},{"place":17,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.4},{"place":18,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":90.01},{"place":19,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.7},{"place":20,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":85.88},{"place":21,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":85},{"place":22,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":84.2},{"place":23,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":82.8},{"place":24,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":82.1},{"place":25,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":72},{"place":26,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":27,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":0},{"place":28,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":0}]},{"id":"ruler-1m","name":"Ruler 1M","topic":"Long-context eval","description":"RULER benchmark at 1M context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Kimi-Linear-Instruct","top_percent":94.8,"top_model_id":"kimi-linear-instruct","top_generation":"Kimi Linear","top_model_base":"Kimi Linear","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":94.8},{"place":2,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":94.7},{"place":3,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":94.2},{"place":4,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":93.9},{"place":5,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.2},{"place":6,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.75},{"place":7,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.33},{"place":8,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.1},{"place":9,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.7},{"place":10,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.3},{"place":11,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":86.3},{"place":12,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":84.5},{"place":13,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":80.3},{"place":14,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":77.5},{"place":15,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":76.83},{"place":16,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":74.39},{"place":17,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":72.93},{"place":18,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":72.8},{"place":19,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":69.62},{"place":20,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":66.98},{"place":21,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.43},{"place":22,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":51.23},{"place":23,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":22.3}]},{"id":"ruler-256k","name":"Ruler 256k","topic":"Long-context eval","description":"RULER benchmark at 256k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Qwen3.5-122B-A10B","top_percent":96.74,"top_model_id":"qwen3.5-122b-a10b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 122B A10B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":96.74},{"place":2,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":96.7},{"place":3,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":96.3},{"place":4,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":95.1},{"place":5,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.22},{"place":6,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.18},{"place":7,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":85.73},{"place":8,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.03},{"place":9,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.36},{"place":10,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":76.88},{"place":11,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":75.44},{"place":12,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":71.71},{"place":13,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":52.3},{"place":14,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":35.5}]},{"id":"ruler-32k","name":"Ruler 32k","topic":"Long-context eval","description":"RULER benchmark at 32k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Qwen2.5-72B-Instruct","top_percent":96.5,"top_model_id":"qwen2.5-72b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":96.5},{"place":2,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":96},{"place":3,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.5},{"place":4,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":94.8},{"place":5,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":94.8},{"place":6,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":93.4},{"place":7,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":93.2},{"place":8,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.8},{"place":9,"model":"qwen-2.5-7.6b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.2},{"place":10,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":90.2},{"place":11,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":89.9},{"place":12,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":89.6},{"place":13,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":89.4},{"place":14,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":88.63},{"place":15,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":88.63},{"place":16,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.32},{"place":17,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":88.32},{"place":18,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":87.92},{"place":19,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":87.4},{"place":20,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83},{"place":21,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":82},{"place":22,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":81.7},{"place":23,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":81.62},{"place":24,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":78.1},{"place":25,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":77.9},{"place":26,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":76.4},{"place":27,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":69.2},{"place":28,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":69.01},{"place":29,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":67.5},{"place":30,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":58.7},{"place":31,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":57.3},{"place":32,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":55.72},{"place":33,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":0.1},{"place":34,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":35,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":0}]},{"id":"ruler-4k","name":"Ruler 4k","topic":"Long-context eval","description":"RULER benchmark at 4k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Qwen2.5 14B Instruct","top_percent":97.7,"top_model_id":"qwen2.5-14b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 14B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":97.7},{"place":2,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":97.7},{"place":3,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":97.5},{"place":4,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":96.9},{"place":5,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":96.7},{"place":6,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":96.6},{"place":7,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":96.5},{"place":8,"model":"ministral-8b","company":"mistral","family":"Ministral","version":"Ministral","score":96},{"place":9,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":95.5},{"place":10,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":95},{"place":11,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":94.7},{"place":12,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":94.32},{"place":13,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":94.32},{"place":14,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":93.09},{"place":15,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":93.09},{"place":16,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":92.49},{"place":17,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":86.39}]},{"id":"ruler-512k","name":"Ruler 512k","topic":"Long-context eval","description":"RULER benchmark at 512k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Qwen3.5-122B-A10B","top_percent":95.95,"top_model_id":"qwen3.5-122b-a10b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 122B A10B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.95},{"place":2,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":95.7},{"place":3,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":95.67},{"place":4,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":94.2},{"place":5,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":90.9},{"place":6,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":87.1},{"place":7,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":86.9},{"place":8,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":84.54},{"place":9,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.16},{"place":10,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":78.4},{"place":11,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":46.7}]},{"id":"ruler-64k","name":"Ruler 64k","topic":"Long-context eval","description":"RULER benchmark at 64k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Qwen3.5-4B-Q4_K_M","top_percent":95.37,"top_model_id":"qwen3.5-4b-q4-k-m","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":46,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.37},{"place":2,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":95.3},{"place":3,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.15},{"place":4,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":93.79},{"place":5,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":93.3},{"place":6,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":93.17},{"place":7,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":93},{"place":8,"model":"minicpm-sala","company":"openbmb","family":"MiniCPM","version":"MiniCPM SALA","score":92.65},{"place":9,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.51},{"place":10,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":91.31},{"place":11,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.8},{"place":12,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.3},{"place":13,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":90.11},{"place":14,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":89.96},{"place":15,"model":"nemotron-nano-v2-9b","company":"nvidia","family":"Nemotron","version":"Nemotron Nano V2","score":88.77},{"place":16,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":88.4},{"place":17,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":87.6},{"place":18,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":87.5},{"place":19,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.1},{"place":20,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":87},{"place":21,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":86.99},{"place":22,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":86.7},{"place":23,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86.7},{"place":24,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":86.55},{"place":25,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":86.14},{"place":26,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":85.76},{"place":27,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":84.7},{"place":28,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":84.7},{"place":29,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":84.7},{"place":30,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83},{"place":31,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.3},{"place":32,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":81.58},{"place":33,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":80.99},{"place":34,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.53},{"place":35,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":78},{"place":36,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":71},{"place":37,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":70.8},{"place":38,"model":"ministral-3-r-8b","company":"mistral","family":"Ministral","version":"Ministral 3","score":70.66},{"place":39,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":67.8},{"place":40,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":67.52},{"place":41,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":56.5},{"place":42,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":51.1},{"place":43,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":16.12},{"place":44,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0},{"place":45,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":0},{"place":46,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":0}]},{"id":"ruler-8k","name":"Ruler 8k","topic":"Long-context eval","description":"RULER benchmark at 8k context window.","url":"https://github.com/allenai/ruler","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.06654","metric":"percent","stars":"","top_model":"Qwen2.5-72B-Instruct","top_percent":97.2,"top_model_id":"qwen2.5-72b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":97.2},{"place":2,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":97.1},{"place":3,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":96.8},{"place":4,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":96.3},{"place":5,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":95.8},{"place":6,"model":"qwen2.5-turbo","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.7},{"place":7,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.1},{"place":8,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":93.8},{"place":9,"model":"llama-3-8b-instruct-gradient-1048k","company":"gradient","family":"Llama","version":"Llama 3","score":93.8},{"place":10,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":92.9},{"place":11,"model":"glm-4-9b-chat-1m","company":"zai","family":"GLM","version":"GLM-4","score":92.8},{"place":12,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":92.29},{"place":13,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":92.29},{"place":14,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":92.16},{"place":15,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":92.16},{"place":16,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":92.14},{"place":17,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":91.3},{"place":18,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.9},{"place":19,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":90.6},{"place":20,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":90.16},{"place":21,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":89.5},{"place":22,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.1},{"place":23,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":87.4},{"place":24,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":86.2},{"place":25,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":84.8},{"place":26,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":76.8},{"place":27,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":0.2},{"place":28,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":0}]},{"id":"rw-search","name":"RW Search","topic":"Agentic search","description":"Real-world search benchmark evaluating retrieval and reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":85.3,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":85.3},{"place":2,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":82},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":81.3},{"place":4,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":79.5},{"place":5,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":79.3},{"place":6,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":78.8},{"place":7,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":77.3},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.3},{"place":9,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":75.5},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.5},{"place":11,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":74},{"place":12,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":69},{"place":13,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":68.5},{"place":14,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":63},{"place":15,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":20.5}]},{"id":"saas-bench","name":"SaaS-Bench","topic":"Agentic SaaS tasks","description":"Benchmark of agents completing tasks in SaaS application environments (as reported in the Kimi K3 release).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":61.4,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":61.4},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":60.1},{"place":3,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":56.1},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":43.8}]},{"id":"safetybench","name":"SafetyBench","topic":"Safety","description":"Multiple-choice safety evaluation across 7 categories in Chinese and English.","url":"https://github.com/thu-coai/SafetyBench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2309.07045","metric":"percent","stars":"","top_model":"GPT 4 0613","top_percent":89.7,"top_model_id":"gpt-4-0613","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":89.7},{"place":2,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":88.1},{"place":3,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":87.9},{"place":4,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":87.5},{"place":5,"model":"glm-4-0520","company":"zai","family":"GLM","version":"GLM 4","score":87.2}]},{"id":"salad-bench","name":"SALAD-Bench","topic":"Safety alignment","description":"Safety Alignment and Dangerous-behavior benchmark evaluating harmful assistance and refusal consistency.","url":"https://github.com/allenai/salad-bench","leaderboard":"","github":"https://github.com/allenai/salad-bench","paper":"https://arxiv.org/abs/2410.08628","metric":"percent","stars":"","top_model":"Granite-4.1-3B","top_percent":93.95,"top_model_id":"granite-4.1-3b","top_generation":"Granite 4.1","top_model_base":"Granite 4.1 3B","top_model_family":"Granite","top_company":"IBM","top_open_source":1,"lower_is_better":true,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":93.95},{"place":2,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":95.8},{"place":3,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":96.41},{"place":4,"model":"granite-4.0-h-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":96.77},{"place":5,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":96.77},{"place":6,"model":"granite-4.0-micro","company":"IBM","family":"Granite","version":"Granite 4.0","score":97.06},{"place":7,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":97.3}]},{"id":"sandbox-bench-egress-proxy","name":"Sandbox-Bench: Egress Proxy","topic":"Cybersecurity","description":"OpenAI Sandbox-Bench Egress Proxy split: success rate at escaping first-layer sandbox hardening (cyber capability).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":33.3,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":33.3},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0}]},{"id":"sandbox-bench-parser","name":"Sandbox-Bench: Parser","topic":"Cybersecurity","description":"OpenAI Sandbox-Bench Parser split: success rate at escaping first-layer sandbox hardening (cyber capability).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":35.7,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":35.7},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":28.6},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":14.3},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":0},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0}]},{"id":"sandbox-bench-runtime","name":"Sandbox-Bench: Runtime","topic":"Cybersecurity","description":"OpenAI Sandbox-Bench Runtime split: success rate at escaping first-layer sandbox hardening (cyber capability).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":80,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":80},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":80},{"place":3,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":60},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":20},{"place":5,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":20},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":20}]},{"id":"sarena-icon","name":"SArena (Icon)","topic":"SVG generation","description":"SVG Arena benchmark for icon generation evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-S1-Pro","top_percent":83.5,"top_model_id":"intern-s1-pro","top_generation":"Intern-S1","top_model_base":"Intern-S1-Pro","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":83.5},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":82.6},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77.3},{"place":4,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.3},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":55.5}]},{"id":"sat","name":"SAT","topic":"Spatial reasoning","description":"Spatial Aptitude Training benchmark of static and dynamic spatial reasoning questions for VLMs.","url":"https://arxiv.org/abs/2412.07755","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2412.07755","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":96.7,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":96.7},{"place":2,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":88.7},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.7},{"place":4,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86.7},{"place":5,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":81.3},{"place":6,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":81.3},{"place":7,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":79.3},{"place":8,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":79.3},{"place":9,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":78},{"place":10,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":78},{"place":11,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":76.7},{"place":12,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":76},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.7},{"place":14,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":74},{"place":15,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":73.3},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.7},{"place":17,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70},{"place":18,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":69.3},{"place":19,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":65.3},{"place":20,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":62},{"place":21,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.7},{"place":22,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":58.7},{"place":23,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":58},{"place":24,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":50},{"place":25,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":49.3}]},{"id":"sat-math","name":"SAT Math","topic":"Math (exam)","description":"SAT mathematics questions (DeepSeekMath / Minerva-style evaluation).","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2402.03300","metric":"percent","stars":"","top_model":"DeepSeek Math 7B","top_percent":84.4,"top_model_id":"deepseek-math-7b","top_generation":"DeepSeek Math","top_model_base":"DeepSeek Math 7B","top_model_family":"DeepSeek Math","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":84.4},{"place":2,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":71.9},{"place":3,"model":"llemma-34b","company":"eleutherai","family":"Llemma","version":"Llemma","score":71.9},{"place":4,"model":"llemma-7b","company":"eleutherai","family":"Llemma","version":"Llemma","score":59.4}]},{"id":"sata-bench","name":"SATA-Bench","topic":"Multiple-answer QA","description":"Select-all-that-apply multiple-choice questions; case exact accuracy (Jev Decision Index suite, posed as typed decisions).","url":"https://huggingface.co/datasets/sata-bench/sata-bench","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"percent","stars":"","top_model":"vLLM-SR d3","top_percent":38.4,"top_model_id":"vllm-sr-d3","top_generation":"d3","top_model_base":"d3","top_model_family":"vLLM-SR d3","top_company":"vllm-sr","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":38.4},{"place":2,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":36.7},{"place":3,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":34.4},{"place":4,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":33.8},{"place":5,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":33.6},{"place":6,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":33.6},{"place":7,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":32.6},{"place":8,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":31.9},{"place":9,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":31.7},{"place":10,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":31.3},{"place":11,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":30.8},{"place":12,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":29.8},{"place":13,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":29.6},{"place":14,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":29.3},{"place":15,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":28.9},{"place":16,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":27.9},{"place":17,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":27.5},{"place":18,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":26.7},{"place":19,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":26.4},{"place":20,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":25.6},{"place":21,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":23.5},{"place":22,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":23.2},{"place":23,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":20.3},{"place":24,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":19.6},{"place":25,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":19.6},{"place":26,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":19},{"place":27,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":13.7},{"place":28,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":13},{"place":29,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":11.7},{"place":30,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":11.4},{"place":31,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":11.2},{"place":32,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":10.8},{"place":33,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":9.8},{"place":34,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":7.4},{"place":35,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":5.8},{"place":36,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":3.4},{"place":37,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":0.7},{"place":38,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":0.3}]},{"id":"scale-ai-multi-challenge","name":"Scale AI Multi Challenge","topic":"Chat & instruction following","description":"Scale AI Multi Challenge crowd-evaluated instruction following benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-122B-A10B","top_percent":61.5,"top_model_id":"qwen3.5-122b-a10b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 122B A10B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.5},{"place":2,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60},{"place":3,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":58.29},{"place":4,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56.6},{"place":5,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56.6},{"place":6,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":55.23},{"place":7,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":55.2},{"place":8,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":45.3},{"place":9,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":44.8},{"place":10,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.5},{"place":11,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":33.8}]},{"id":"scicode","name":"SciCode (sub)","topic":"Code","description":"SciCode subset score (sub).","url":"","leaderboard":"https://scicode-bench.github.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":95.1,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":216,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":95.1},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":92.3},{"place":3,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90.2},{"place":4,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":84.3},{"place":5,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.7},{"place":6,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":68.6},{"place":7,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":64.1},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":62.3},{"place":9,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":60.2},{"place":10,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":60.1},{"place":11,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":59.8},{"place":12,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":59.5},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":59},{"place":14,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":59},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":58.9},{"place":16,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":58.7},{"place":17,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":58.7},{"place":18,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":58.5},{"place":19,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.4},{"place":20,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":57.8},{"place":21,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":56.6},{"place":22,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":56.5},{"place":23,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":56.4},{"place":24,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":56.21},{"place":25,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.1},{"place":26,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":56.1},{"place":27,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":56.1},{"place":28,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56},{"place":29,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":55.92},{"place":30,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.44},{"place":31,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":54.2},{"place":32,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":54.1},{"place":33,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":53.8},{"place":34,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.6},{"place":35,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":53.5},{"place":36,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":53.5},{"place":37,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":53.5},{"place":38,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":53.1},{"place":39,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":52.6},{"place":40,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":52.5},{"place":41,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":52.2},{"place":42,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":52.1},{"place":43,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":52.1},{"place":44,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":52},{"place":45,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":52},{"place":46,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":52},{"place":47,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":52},{"place":48,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":52},{"place":49,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":51.97},{"place":50,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":51.9},{"place":51,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":51.3},{"place":52,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":51},{"place":53,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":50.6},{"place":54,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":50.5},{"place":55,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.5},{"place":56,"model":"kat-coder-pro-v2.5","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":50.3},{"place":57,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.3},{"place":58,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":50.1},{"place":59,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":50.05},{"place":60,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50},{"place":61,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":50},{"place":62,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50},{"place":63,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":49.7},{"place":64,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":49.5},{"place":65,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":49.5},{"place":66,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.3},{"place":67,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":49.2},{"place":68,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":49.11},{"place":69,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":48.7},{"place":70,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":48.7},{"place":71,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":48.4},{"place":72,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":48.3},{"place":73,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":48.2},{"place":74,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48},{"place":75,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":47.7},{"place":76,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":47.7},{"place":77,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":47.63},{"place":78,"model":"solar-mini-4","company":"upstage","family":"Solar","version":"Solar Mini 4","score":47.6},{"place":79,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":47.53},{"place":80,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":47.5},{"place":81,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":47.13},{"place":82,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":47.1},{"place":83,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":47},{"place":84,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":47},{"place":85,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":47},{"place":86,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":47},{"place":87,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":46.7},{"place":88,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":46.6},{"place":89,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":46.6},{"place":90,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":46.6},{"place":91,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.35},{"place":92,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":46.35},{"place":93,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":46.22},{"place":94,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":46.15},{"place":95,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":46.1},{"place":96,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":46.05},{"place":97,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":46.01},{"place":98,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":45.7},{"place":99,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.5},{"place":100,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":45.4},{"place":101,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":45.36},{"place":102,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":45.1},{"place":103,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":45},{"place":104,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":45},{"place":105,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.9},{"place":106,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":44.9},{"place":107,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.8},{"place":108,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.7},{"place":109,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.7},{"place":110,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":44.7},{"place":111,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":44.6},{"place":112,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":44.6},{"place":113,"model":"nemotron-3.5-bolt-74b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":44.49},{"place":114,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":44.33},{"place":115,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":44.3},{"place":116,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":44.3},{"place":117,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":44.2},{"place":118,"model":"kat-coder-v2.5-dev","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":44.2},{"place":119,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":43.8},{"place":120,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":43.6},{"place":121,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":43.6},{"place":122,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":43.49},{"place":123,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.4},{"place":124,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.3},{"place":125,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":43.1},{"place":126,"model":"claude-4.5-haiku-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43},{"place":127,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":42.9},{"place":128,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":42.9},{"place":129,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":42.8},{"place":130,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":42.74},{"place":131,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":42.7},{"place":132,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.6},{"place":133,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":42.4},{"place":134,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":42.4},{"place":135,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":42.3},{"place":136,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":42.1},{"place":137,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":42.05},{"place":138,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42},{"place":139,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42},{"place":140,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":42},{"place":141,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":41.7},{"place":142,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":41.5},{"place":143,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":41.4},{"place":144,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":41.12},{"place":145,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":41},{"place":146,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":41},{"place":147,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":41},{"place":148,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":41},{"place":149,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":40.9},{"place":150,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":40.7},{"place":151,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":40.6},{"place":152,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":40.6},{"place":153,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":40.6},{"place":154,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":40.6},{"place":155,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":40.48},{"place":156,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":40.4},{"place":157,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.32},{"place":158,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":40.3},{"place":159,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":40.3},{"place":160,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.28},{"place":161,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":40},{"place":162,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":40},{"place":163,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40},{"place":164,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":40},{"place":165,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":40},{"place":166,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":39.9},{"place":167,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.8},{"place":168,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.8},{"place":169,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.8},{"place":170,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":39.64},{"place":171,"model":"openreasoning-nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":39.6},{"place":172,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":39.6},{"place":173,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":39.6},{"place":174,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.5},{"place":175,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":39.5},{"place":176,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":39.4},{"place":177,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.3},{"place":178,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":39.2},{"place":179,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":39.2},{"place":180,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":39},{"place":181,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":39},{"place":182,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":39},{"place":183,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":39},{"place":184,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":39},{"place":185,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":38.9},{"place":186,"model":"k2-horizon-mova-36b-a4b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":38.9},{"place":187,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":38.8},{"place":188,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":38.8},{"place":189,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":38.8},{"place":190,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":38.76},{"place":191,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":38.7},{"place":192,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":38.63},{"place":193,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":38.3},{"place":194,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":38.2},{"place":195,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":38.2},{"place":196,"model":"north-mini-code-1.0","company":"cohere","family":"North","version":"North 1.0","score":38.2},{"place":197,"model":"agnes-3.0-flash-preview","company":"agnes","family":"Agnes","version":"Agnes 3.0","score":38.08},{"place":198,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38},{"place":199,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":38},{"place":200,"model":"mercury-2.5","company":"inception","family":"Mercury","version":"Mercury 2.5","score":38},{"place":201,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":38},{"place":202,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":37.9},{"place":203,"model":"k2-horizon-32b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":37.9},{"place":204,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":37.7},{"place":205,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.7},{"place":206,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37.53},{"place":207,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":37.4},{"place":208,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37.35},{"place":209,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37.24},{"place":210,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":37.1},{"place":211,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":37},{"place":212,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":37},{"place":213,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":36.9},{"place":214,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":36.8},{"place":215,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":36.7},{"place":216,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":36.6},{"place":217,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":36.46},{"place":218,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.4},{"place":219,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":36.4},{"place":220,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":36.2},{"place":221,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":36.09},{"place":222,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":36},{"place":223,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":36},{"place":224,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":36},{"place":225,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":35.8},{"place":226,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":35.6},{"place":227,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":35.6},{"place":228,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":35.6},{"place":229,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":35.5},{"place":230,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":35.42},{"place":231,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":35.4},{"place":232,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":35.33},{"place":233,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":35.2},{"place":234,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":35.11},{"place":235,"model":"nemotron-labs-dory1.0-4b-4loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":35.11},{"place":236,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":35},{"place":237,"model":"nemotron-labs-dory1.0-4b","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":34.94},{"place":238,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":34.9},{"place":239,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":34.8},{"place":240,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":34.8},{"place":241,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":34.7},{"place":242,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":34.4},{"place":243,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":34},{"place":244,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":34},{"place":245,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":34},{"place":246,"model":"g9v3-39a5b","company":"ai9stars","family":"G9","version":"G9v3","score":34},{"place":247,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":33.6},{"place":248,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":33.5},{"place":249,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":33.3},{"place":250,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":33.19},{"place":251,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":33.1},{"place":252,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":33},{"place":253,"model":"midm-k-2.5-pro","company":"kt","family":"Mi:dm","version":"Mi:dm K 2.5","score":33},{"place":254,"model":"k2-think-v2","company":"mbzuai","family":"K2","version":"K2 Think V2","score":33},{"place":255,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":32.71},{"place":256,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32.7},{"place":257,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":32.6},{"place":258,"model":"openreasoning-nemotron-14b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":32.4},{"place":259,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":32},{"place":260,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":31.9},{"place":261,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":31.38},{"place":262,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.84},{"place":263,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":30.7},{"place":264,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":30.6},{"place":265,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":30.4},{"place":266,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":30.34},{"place":267,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":30.08},{"place":268,"model":"command-a-reasoning-08-2025","company":"cohere","family":"Command","version":"Command","score":30},{"place":269,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":29.9},{"place":270,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":29.8},{"place":271,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":29.6},{"place":272,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":29},{"place":273,"model":"gemini-2.5-flash-lite-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":29},{"place":274,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":28.8},{"place":275,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.5},{"place":276,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":28.3},{"place":277,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.3},{"place":278,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.21},{"place":279,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":28},{"place":280,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":27.78},{"place":281,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.73},{"place":282,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.5},{"place":283,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.5},{"place":284,"model":"nemotron-labs-dory1.0-4b-1loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":27.3},{"place":285,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":26.1},{"place":286,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.82},{"place":287,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":25.8},{"place":288,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":25.6},{"place":289,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.58},{"place":290,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":24.9},{"place":291,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":24.9},{"place":292,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":24.4},{"place":293,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":24.2},{"place":294,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":24.11},{"place":295,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":24.1},{"place":296,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24},{"place":297,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":22.92},{"place":298,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":22.92},{"place":299,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.7},{"place":300,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":22.2},{"place":301,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":21.3},{"place":302,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":20.5},{"place":303,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":20.3},{"place":304,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":18.27},{"place":305,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":18.2},{"place":306,"model":"g9v3-3b","company":"ai9stars","family":"G9","version":"G9v3","score":17.7},{"place":307,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":16.4},{"place":308,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":16.1},{"place":309,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":15.94},{"place":310,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":15.11},{"place":311,"model":"gka-primed-hqwen3-32b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":12.34},{"place":312,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":10.63},{"place":313,"model":"gka-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":6.41},{"place":314,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6},{"place":315,"model":"gdn-primed-hqwen3-8b-reasoner","company":"amazon","family":"Hybrid Model Factory","version":"Primed-HQwen3","score":2.5},{"place":316,"model":"openreasoning-nemotron-1.5b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":1}]},{"id":"scicode-main","name":"SciCode (main)","topic":"Code","description":"SciCode main score.","url":"","leaderboard":"https://scicode-bench.github.io/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":90.6,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":90.6},{"place":2,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":78.1},{"place":3,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.1},{"place":4,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":70.3},{"place":5,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":68.6},{"place":6,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":50},{"place":7,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":50},{"place":8,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":26.6},{"place":9,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":15.6},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":15.4},{"place":11,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":12.4},{"place":12,"model":"k2-think","company":"mbzuai","family":"K2","version":"K2-THINK","score":12},{"place":13,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":11.9},{"place":14,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":11.7},{"place":15,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":11.5},{"place":16,"model":"qwq-32b","company":"qwen","family":"QwQ","version":"QwQ","score":11.5},{"place":17,"model":"nemotron-32b","company":"nvidia","family":"Nemotron","version":"Nemotron","score":11.4},{"place":18,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":11},{"place":19,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":10.9},{"place":20,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.2},{"place":21,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":9},{"place":22,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":8.2},{"place":23,"model":"phi-4-reasoning-plus","company":"microsoft","family":"Phi 4","version":"Phi-4","score":7.2},{"place":24,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":6.7},{"place":25,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":6.2},{"place":26,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.8},{"place":27,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":4.6},{"place":28,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":3.9},{"place":29,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":3.08},{"place":30,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":3.08},{"place":31,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":3.08},{"place":32,"model":"deepseek-r1-0528-qwen3-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":2.6}]},{"id":"scienceqa","name":"ScienceQA","topic":"Science QA (multimodal)","description":"Multiple-choice science questions with images, diagrams, and text context.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Youtu-VL-4B-Instruct","top_percent":97,"top_model_id":"youtu-vl-4b-instruct","top_generation":"Youtu-VL","top_model_base":"Youtu-VL 4B","top_model_family":"Youtu-VL","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":34,"total_models":3854,"placements":[{"place":1,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":97},{"place":2,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":96.7},{"place":3,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":96.2},{"place":4,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94.7},{"place":5,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":94.4},{"place":6,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":92.9},{"place":7,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":91.9},{"place":8,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":91.2},{"place":9,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":90.8},{"place":10,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":90.7},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.4},{"place":12,"model":"blip-3-4b","company":"salesforce","family":"BLIP","version":"BLIP-3","score":88.3},{"place":13,"model":"unified-io-2-xxl","company":"allenai","family":"Unified-IO","version":"Unified-IO 2","score":86.2},{"place":14,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":85.8},{"place":15,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":85.7},{"place":16,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":85.6},{"place":17,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":85.2},{"place":18,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":81.8},{"place":19,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":81},{"place":20,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":80.7},{"place":21,"model":"bunny-4b","company":"baai","family":"Bunny","version":"Bunny","score":78.3},{"place":22,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":71.6},{"place":23,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":70.6},{"place":24,"model":"vila1.5-3b","company":"nvidia","family":"VILA","version":"VILA 1.5","score":69},{"place":25,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":68.8},{"place":26,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":68.7},{"place":27,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":68.2},{"place":28,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":67.1},{"place":29,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":66.8},{"place":30,"model":"instructblip-vicuna-13b","company":"salesforce","family":"BLIP","version":"InstructBLIP","score":63.1},{"place":31,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":61.8},{"place":32,"model":"blip-2-vicuna-13b","company":"salesforce","family":"BLIP","version":"BLIP-2","score":61},{"place":33,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":60.5},{"place":34,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":44.8},{"place":35,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":39.6}]},{"id":"sciq","name":"SciQ","topic":"Science QA","description":"Multiple choice science questions.","url":"https://allenai.org/data/sciq","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3 8B Base","top_percent":96.1,"top_model_id":"qwen3-8b-base","top_generation":"Qwen3","top_model_base":"Qwen3 8B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":96.1},{"place":2,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":95.4},{"place":3,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.4},{"place":4,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":94.4},{"place":5,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":94.2},{"place":6,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":93.9},{"place":7,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":93.6},{"place":8,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":93.5},{"place":9,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":93.2},{"place":10,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":93.2},{"place":11,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":92.9},{"place":12,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":92.8},{"place":13,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":92.7},{"place":14,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":91.9},{"place":15,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.9},{"place":16,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":91.1},{"place":17,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":90.9},{"place":18,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":90.8},{"place":19,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":90.1},{"place":20,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":88.3},{"place":21,"model":"pythia-2.8b","company":"eleutherai","family":"Pythia","version":"Pythia","score":88.2},{"place":22,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":87.1},{"place":23,"model":"pythia-1b","company":"eleutherai","family":"Pythia","version":"Pythia","score":87},{"place":24,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":87},{"place":25,"model":"pythia-1.4b","company":"eleutherai","family":"Pythia","version":"Pythia","score":86.5},{"place":26,"model":"pythia-410m","company":"eleutherai","family":"Pythia","version":"Pythia","score":82.6},{"place":27,"model":"pythia-160m","company":"eleutherai","family":"Pythia","version":"Pythia","score":72},{"place":28,"model":"pythia-70m","company":"eleutherai","family":"Pythia","version":"Pythia","score":60.6},{"place":29,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":43.5},{"place":30,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":39.6}]},{"id":"scireasoner","name":"SciReasoner","topic":"Scientific reasoning","description":"Scientific reasoning benchmark evaluating multimodal AI models on scientific tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-S2-Preview-397B","top_percent":63.97,"top_model_id":"intern-s2-preview-397b","top_generation":"Intern-S2","top_model_base":"Intern-S2-Preview-397B","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":63.97},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":61.15},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":60.35},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":58},{"place":5,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":55.5},{"place":6,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":54.22},{"place":7,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":51.69},{"place":8,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":51.45},{"place":9,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.11},{"place":10,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":45.82},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.02},{"place":12,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":16.28},{"place":13,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":15.3},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":14.7},{"place":15,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":14.48},{"place":16,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":13.72},{"place":17,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":13.6},{"place":18,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":13.29},{"place":19,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":12.65},{"place":20,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":11.91},{"place":21,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":11.9}]},{"id":"scires-frontiermath-tier-1-3","name":"SciRes FrontierMath Tier 1-3","topic":"Math (frontier)","description":"SciRes FrontierMath benchmark covering tiers 1-3.","url":"","leaderboard":"https://epoch.ai/frontiermath","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol (max)","top_percent":93.7,"top_model_id":"gpt-6.1-sol-max","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":192,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":93.7},{"place":2,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":93.7},{"place":3,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":91.2},{"place":4,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":90.2},{"place":5,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":89.8},{"place":6,"model":"gpt-5.6-sol-max","company":"openai","family":"GPT","version":"GPT-5.6","score":89.1},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":89},{"place":8,"model":"claude-sonnet-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":88.8},{"place":9,"model":"gpt-5.5-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":87.7},{"place":10,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87},{"place":11,"model":"claude-fable-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":87},{"place":12,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":86},{"place":13,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":86},{"place":14,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":85.6},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":85.3},{"place":16,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":85.3},{"place":17,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":84.9},{"place":18,"model":"gpt-5.4-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":82.5},{"place":19,"model":"muse-wonder-max","company":"meta","family":"Muse","version":"Muse Wonder","score":82.1},{"place":20,"model":"gpt-5.6-luna-max","company":"openai","family":"GPT","version":"GPT-5.6","score":82.1},{"place":21,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80},{"place":22,"model":"claude-opus-4.8-max","company":"anthropic","family":"Claude","version":"Claude 4.8","score":80},{"place":23,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":78.9},{"place":24,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":78.6},{"place":25,"model":"gpt-5.4-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":78.6},{"place":26,"model":"claude-haiku-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":75.1},{"place":27,"model":"qwen3.8-max-xhigh","company":"qwen","family":"Qwen","version":"Qwen3.8","score":74.7},{"place":28,"model":"muse-spark-1.3-xhigh","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":74.4},{"place":29,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":74},{"place":30,"model":"gpt-5.2-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":74},{"place":31,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":72.2},{"place":32,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":71.6},{"place":33,"model":"deepseek-v4.1-flash-1017-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":71.2},{"place":34,"model":"claude-opus-4.7-max","company":"anthropic","family":"Claude","version":"Claude 4.7","score":70.2},{"place":35,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":69.8},{"place":36,"model":"glm-5.3-max","company":"zai","family":"GLM","version":"GLM 5.3","score":68.8},{"place":37,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":68.4},{"place":38,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":67.4},{"place":39,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":67.4},{"place":40,"model":"grok-4.6-xhigh","company":"xai","family":"Grok","version":"Grok 4.6","score":66},{"place":41,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66},{"place":42,"model":"qwen3.8-max-xhigh","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.6},{"place":43,"model":"claude-sonnet-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":65.6},{"place":44,"model":"deepseek-v4-pro-0813-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.6},{"place":45,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":64.6},{"place":46,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":62.8},{"place":47,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":59.6},{"place":48,"model":"glm-5.2-max","company":"zai","family":"GLM","version":"GLM 5.2","score":59.2},{"place":49,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":58.9},{"place":50,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":58.6},{"place":51,"model":"deepseek-v4-flash-0731-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.5},{"place":52,"model":"grok-4.5-high","company":"xai","family":"Grok","version":"Grok 4.5","score":57.2},{"place":53,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":57.2},{"place":54,"model":"glm-5.3-flash-max","company":"zai","family":"GLM","version":"GLM 5.3","score":55.8},{"place":55,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":55.8},{"place":56,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":55.4},{"place":57,"model":"glm-5.2-low","company":"zai","family":"GLM","version":"GLM 5.2","score":54.7},{"place":58,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":54},{"place":59,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":53},{"place":60,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":52.4},{"place":61,"model":"gpt-5.5-pro-high","company":"openai","family":"GPT","version":"GPT-5.5","score":52.4},{"place":62,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":51.7},{"place":63,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":51.7},{"place":64,"model":"gpt-5.4-mini-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":51.2},{"place":65,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":51.2},{"place":66,"model":"gpt-5.5-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":51},{"place":67,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":50},{"place":68,"model":"gpt-5.4-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":50},{"place":69,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":47.6},{"place":70,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":47.6},{"place":71,"model":"gpt-5.4-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":47.6},{"place":72,"model":"claude-opus-4.8-max","company":"anthropic","family":"Claude","version":"Claude 4.8","score":47.2},{"place":73,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":46.7},{"place":74,"model":"inkling-small-xhigh","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":46.3},{"place":75,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":45.3},{"place":76,"model":"grok-4.2-0309","company":"xai","family":"Grok","version":"Grok 4.2","score":44.9},{"place":77,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":44.9},{"place":78,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":43.8},{"place":79,"model":"claude-opus-4.7-xhigh","company":"anthropic","family":"Claude","version":"Claude 4.7","score":43.8},{"place":80,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":42.8},{"place":81,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":42.5},{"place":82,"model":"gpt-5.6-luna-low","company":"openai","family":"GPT","version":"GPT-5.6","score":41.4},{"place":83,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":40.7},{"place":84,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40.7},{"place":85,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40.7},{"place":86,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":40.7},{"place":87,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":40.3},{"place":88,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":40.3},{"place":89,"model":"claude-opus-4.6-thinking","company":"anthropic","family":"Claude","version":"Claude 4.6","score":40},{"place":90,"model":"claude-opus-4.6-thinking","company":"anthropic","family":"Claude","version":"Claude 4.6","score":39.7},{"place":91,"model":"gpt-5.6-luna-none","company":"openai","family":"GPT","version":"GPT-5.6","score":39.6},{"place":92,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":39},{"place":93,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":39},{"place":94,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":39},{"place":95,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":38.3},{"place":96,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":38.2},{"place":97,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.6},{"place":98,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":37.6},{"place":99,"model":"gpt-5-low","company":"openai","family":"GPT","version":"GPT-5","score":37.2},{"place":100,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":36.9},{"place":101,"model":"gpt-5.2-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":36.9},{"place":102,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":36.8},{"place":103,"model":"o4-mini-2025-04-16-high","company":"openai","family":"o4","version":"o4","score":36.1},{"place":104,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":35.6},{"place":105,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":35.1},{"place":106,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":34.4},{"place":107,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":34.4},{"place":108,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34},{"place":109,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":33.4},{"place":110,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":33.3},{"place":111,"model":"inkling-xhigh","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":33.3},{"place":112,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":32.4},{"place":113,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":32.4},{"place":114,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":32.3},{"place":115,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.2},{"place":116,"model":"gpt-5.1-thinking","company":"openai","family":"GPT","version":"GPT-5.1","score":31},{"place":117,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":31},{"place":118,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":29.8},{"place":119,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.5},{"place":120,"model":"gemini-2.5-deep-think","company":"google","family":"Gemini","version":"Gemini 2.5","score":29},{"place":121,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":28.8},{"place":122,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":28.3},{"place":123,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":27.9},{"place":124,"model":"gemini-3.1-flash-lite-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":27.7},{"place":125,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":27.2},{"place":126,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":27.2},{"place":127,"model":"gpt-5.1-medium","company":"openai","family":"GPT","version":"GPT-5.1","score":26.9},{"place":128,"model":"gpt-5.2-low","company":"openai","family":"GPT","version":"GPT-5.2","score":26.6},{"place":129,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":26.3},{"place":130,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":26.2},{"place":131,"model":"gemini-3.5-flash-lite-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":26},{"place":132,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":25.9},{"place":133,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":24.9},{"place":134,"model":"o4-mini-2025-04-16-high","company":"openai","family":"o4","version":"o4","score":24.8},{"place":135,"model":"gpt-5.4-mini-low","company":"openai","family":"GPT","version":"GPT-5.4","score":24.6},{"place":136,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":24.6},{"place":137,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":23.9},{"place":138,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":23.1},{"place":139,"model":"gemini-3.1-flash-lite-low","company":"google","family":"Gemini","version":"Gemini 3.1","score":22.5},{"place":140,"model":"qwen3.6-flash","company":"qwen","family":"Qwen","version":"Qwen3.6","score":22.5},{"place":141,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":22.1},{"place":142,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":21.4},{"place":143,"model":"gemini-3.1-flash-lite-minimal","company":"google","family":"Gemini","version":"Gemini 3.1","score":21.4},{"place":144,"model":"qwen3.5-plus","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21},{"place":145,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":20.7},{"place":146,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":20.7},{"place":147,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":20.4},{"place":148,"model":"gpt-5.4-nano-low","company":"openai","family":"GPT","version":"GPT-5.4","score":20.4},{"place":149,"model":"claude-opus-4.5-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":20.3},{"place":150,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":20.3},{"place":151,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":20},{"place":152,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":19.7},{"place":153,"model":"qwen3.7-flash","company":"qwen","family":"Qwen","version":"Qwen3.7","score":19.3},{"place":154,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":19.3},{"place":155,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":19},{"place":156,"model":"qwen3-max-2025-09-23","company":"qwen","family":"Qwen","version":"Qwen3","score":18.9},{"place":157,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":18.7},{"place":158,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":18.6},{"place":159,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.2},{"place":160,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":18.2},{"place":161,"model":"gpt-5-mini-low","company":"openai","family":"GPT","version":"GPT-5","score":18.2},{"place":162,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":17.5},{"place":163,"model":"gpt-5.1-low","company":"openai","family":"GPT","version":"GPT-5.1","score":17.3},{"place":164,"model":"qwen3.6-flash","company":"qwen","family":"Qwen","version":"Qwen3.6","score":17.2},{"place":165,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":17.2},{"place":166,"model":"o3-medium","company":"openai","family":"o3","version":"o3","score":16.9},{"place":167,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":16.4},{"place":168,"model":"o4-mini-low","company":"openai","family":"o4","version":"o4","score":16.1},{"place":169,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":15.2},{"place":170,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":14.7},{"place":171,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":14.1},{"place":172,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":13.5},{"place":173,"model":"claude-opus-4-1-20250805-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":12.6},{"place":174,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":12.4},{"place":175,"model":"o4-mini-low","company":"openai","family":"o4","version":"o4","score":10.7},{"place":176,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":10.5},{"place":177,"model":"qwen3.6-flash","company":"qwen","family":"Qwen","version":"Qwen3.6","score":10.3},{"place":178,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":10.3},{"place":179,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":10.2},{"place":180,"model":"o3-low","company":"openai","family":"o3","version":"o3","score":9.7},{"place":181,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.5},{"place":182,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":9.3},{"place":183,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":9.3},{"place":184,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":8.5},{"place":185,"model":"o1-2024-12-17-low","company":"openai","family":"GPT","version":"o1","score":8.4},{"place":186,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":8.3},{"place":187,"model":"o3-mini-medium","company":"openai","family":"o3","version":"o3","score":8.1},{"place":188,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":7.2},{"place":189,"model":"claude-opus-4-1-20250805-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":7.2},{"place":190,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":6.7},{"place":191,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.2},{"place":192,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":6},{"place":193,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":6},{"place":194,"model":"gpt-5-nano-low","company":"openai","family":"GPT","version":"GPT-5","score":6},{"place":195,"model":"claude-4.5-haiku-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":5.9},{"place":196,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":5.9},{"place":197,"model":"grok-3-mini-beta-high","company":"xai","family":"Grok","version":"Grok 3","score":5.9},{"place":198,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":5.5},{"place":199,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.8},{"place":200,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":4.6},{"place":201,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":4.5},{"place":202,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":4.5},{"place":203,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.1},{"place":204,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":4.1},{"place":205,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":4.1},{"place":206,"model":"claude-3-7-sonnet-20250219-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":4.1},{"place":207,"model":"o3-mini-2025-01-31-low","company":"openai","family":"o3","version":"o3","score":3.9},{"place":208,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":3.8},{"place":209,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":3.8},{"place":210,"model":"claude-3-7-sonnet-20250219-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 3.7","score":3.4},{"place":211,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":3.1},{"place":212,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":3.1},{"place":213,"model":"grok-3-mini-beta-low","company":"xai","family":"Grok","version":"Grok 3","score":2.8},{"place":214,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":2.4},{"place":215,"model":"gpt-5.1-none","company":"openai","family":"GPT","version":"GPT-5.1","score":2.1},{"place":216,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":2.1},{"place":217,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":1.8},{"place":218,"model":"qwen-plus-2025-04-28","company":"qwen","family":"Qwen","version":"Qwen","score":1.7},{"place":219,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":1.7},{"place":220,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1.7},{"place":221,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":1.7},{"place":222,"model":"o1-mini-2024-09-12-high","company":"openai","family":"o1","version":"o1","score":1.4},{"place":223,"model":"gpt-4.1-nano-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1},{"place":224,"model":"qwen-max-2025-01-25","company":"qwen","family":"Qwen","version":"Qwen Max","score":1},{"place":225,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1},{"place":226,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":0.7},{"place":227,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":0.7},{"place":228,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":0.7},{"place":229,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":0.7},{"place":230,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":0.4},{"place":231,"model":"mistral-medium-2505","company":"mistral","family":"Mistral","version":"Mistral","score":0.3},{"place":232,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":0.3},{"place":233,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0.3},{"place":234,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":0.3},{"place":235,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":0.3},{"place":236,"model":"llama-4-scout-17b-16e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":0},{"place":237,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":0},{"place":238,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":0}]},{"id":"scires-frontiermath-tier-4","name":"SciRes FrontierMath Tier 4","topic":"Math (frontier)","description":"SciRes FrontierMath benchmark covering tier 4.","url":"","leaderboard":"https://epoch.ai/frontiermath","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6.1 Sol (max)","top_percent":100,"top_model_id":"gpt-6.1-sol-max","top_generation":"GPT-6.1","top_model_base":"GPT-6.1 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":141,"total_models":3854,"placements":[{"place":1,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":100},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":97.6},{"place":3,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":97.6},{"place":4,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":97.6},{"place":5,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":97.6},{"place":6,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":97.6},{"place":7,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":95},{"place":8,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.2},{"place":9,"model":"claude-fable-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":90.2},{"place":10,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":90},{"place":11,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":87.8},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87.8},{"place":13,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":87.8},{"place":14,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":87.8},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83},{"place":16,"model":"gpt-6-astra-none","company":"openai","family":"GPT","version":"GPT-6","score":82.9},{"place":17,"model":"gpt-5.6-sol-max","company":"openai","family":"GPT","version":"GPT-5.6","score":82.9},{"place":18,"model":"claude-sonnet-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":80.5},{"place":19,"model":"gpt-5.6-sol-pro","company":"openai","family":"GPT","version":"GPT-5.6","score":80.5},{"place":20,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":78},{"place":21,"model":"gpt-5.5-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":78},{"place":22,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":73.2},{"place":23,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":73.2},{"place":24,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":72.5},{"place":25,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":72.5},{"place":26,"model":"muse-wonder-max","company":"meta","family":"Muse","version":"Muse Wonder","score":70.7},{"place":27,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":70.7},{"place":28,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":68.3},{"place":29,"model":"gpt-5.6-luna-max","company":"openai","family":"GPT","version":"GPT-5.6","score":61},{"place":30,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":58.5},{"place":31,"model":"gpt-5.4-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":58.5},{"place":32,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":56.1},{"place":33,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":56.1},{"place":34,"model":"claude-opus-4.8-max","company":"anthropic","family":"Claude","version":"Claude 4.8","score":56.1},{"place":35,"model":"gpt-5.4-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":49},{"place":36,"model":"deepseek-v4.1-flash-1017-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":46.3},{"place":37,"model":"claude-haiku-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":46.3},{"place":38,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":46.3},{"place":39,"model":"qwen3.8-max-xhigh","company":"qwen","family":"Qwen","version":"Qwen3.8","score":46.3},{"place":40,"model":"gpt-5.2-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":46},{"place":41,"model":"muse-spark-1.3-xhigh","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":41.5},{"place":42,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":39.6},{"place":43,"model":"gpt-5.5-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":39.6},{"place":44,"model":"gpt-5.5-pro-high","company":"openai","family":"GPT","version":"GPT-5.5","score":39.6},{"place":45,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":39},{"place":46,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":38},{"place":47,"model":"gpt-5.4-pro","company":"openai","family":"GPT","version":"GPT-5.4","score":37.5},{"place":48,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":36.6},{"place":49,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":35.4},{"place":50,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":35.4},{"place":51,"model":"qwen3.8-max-xhigh","company":"qwen","family":"Qwen","version":"Qwen3.8","score":34.1},{"place":52,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":34.1},{"place":53,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":31.7},{"place":54,"model":"grok-4.6-xhigh","company":"xai","family":"Grok","version":"Grok 4.6","score":31.7},{"place":55,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":31.7},{"place":56,"model":"claude-opus-4.7-max","company":"anthropic","family":"Claude","version":"Claude 4.7","score":31.7},{"place":57,"model":"gpt-5.2-pro","company":"openai","family":"GPT","version":"GPT-5.2","score":31.3},{"place":58,"model":"claude-opus-4.8-max","company":"anthropic","family":"Claude","version":"Claude 4.8","score":31.2},{"place":59,"model":"glm-5.3-max","company":"zai","family":"GLM","version":"GLM 5.3","score":29.3},{"place":60,"model":"claude-sonnet-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":29.3},{"place":61,"model":"glm-5.2-max","company":"zai","family":"GLM","version":"GLM 5.2","score":29.3},{"place":62,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":27.1},{"place":63,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":27.1},{"place":64,"model":"gpt-5.4-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":27.1},{"place":65,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":26.8},{"place":66,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":26.8},{"place":67,"model":"deepseek-v4-pro-0813-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":26.8},{"place":68,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":26.8},{"place":69,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":26.8},{"place":70,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":26.8},{"place":71,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":25.6},{"place":72,"model":"deepseek-v4-flash-0731-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":24.4},{"place":73,"model":"grok-4.5-high","company":"xai","family":"Grok","version":"Grok 4.5","score":24.4},{"place":74,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":22.9},{"place":75,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":22.9},{"place":76,"model":"claude-opus-4.7-xhigh","company":"anthropic","family":"Claude","version":"Claude 4.7","score":22.9},{"place":77,"model":"claude-opus-4.6-max","company":"anthropic","family":"Claude","version":"Claude 4.6","score":22.9},{"place":78,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":22},{"place":79,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":22},{"place":80,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":22},{"place":81,"model":"claude-opus-4.6-thinking","company":"anthropic","family":"Claude","version":"Claude 4.6","score":20.8},{"place":82,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":19.5},{"place":83,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":18.8},{"place":84,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":18.8},{"place":85,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":18.8},{"place":86,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":18.8},{"place":87,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":18.8},{"place":88,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":17.1},{"place":89,"model":"glm-5.3-flash-max","company":"zai","family":"GLM","version":"GLM 5.3","score":17.1},{"place":90,"model":"inkling-small-xhigh","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":17.1},{"place":91,"model":"grok-4.2-0309","company":"xai","family":"Grok","version":"Grok 4.2","score":17.1},{"place":92,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":17.1},{"place":93,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":16.7},{"place":94,"model":"gpt-5.2-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":16.7},{"place":95,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":14.6},{"place":96,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":14.6},{"place":97,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":14.6},{"place":98,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":14.6},{"place":99,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":14.6},{"place":100,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":14.6},{"place":101,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":14.6},{"place":102,"model":"gpt-5.1-thinking","company":"openai","family":"GPT","version":"GPT-5.1","score":12.5},{"place":103,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":12.5},{"place":104,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":12.5},{"place":105,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":12.5},{"place":106,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":12.2},{"place":107,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":12.2},{"place":108,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":12.2},{"place":109,"model":"gemini-2.5-deep-think","company":"google","family":"Gemini","version":"Gemini 2.5","score":10.4},{"place":110,"model":"gpt-5.4-mini-xhigh","company":"openai","family":"GPT","version":"GPT-5.4","score":9.8},{"place":111,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":8.3},{"place":112,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":8.3},{"place":113,"model":"gpt-5.4-nano-high","company":"openai","family":"GPT","version":"GPT-5.4","score":6.2},{"place":114,"model":"gpt-5.2-low","company":"openai","family":"GPT","version":"GPT-5.2","score":6.2},{"place":115,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":6.2},{"place":116,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":6.2},{"place":117,"model":"o4-mini-2025-04-16-high","company":"openai","family":"o4","version":"o4","score":6.2},{"place":118,"model":"inkling-xhigh","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":4.9},{"place":119,"model":"o4-mini-2025-04-16-high","company":"openai","family":"o4","version":"o4","score":4.9},{"place":120,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.9},{"place":121,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":4.2},{"place":122,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":4.2},{"place":123,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.2},{"place":124,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":4.2},{"place":125,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.2},{"place":126,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.2},{"place":127,"model":"gpt-5.1-medium","company":"openai","family":"GPT","version":"GPT-5.1","score":4.2},{"place":128,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.2},{"place":129,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":4.2},{"place":130,"model":"claude-opus-4-1-20250805-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":4.2},{"place":131,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.2},{"place":132,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":4.2},{"place":133,"model":"claude-opus-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":4.2},{"place":134,"model":"gpt-5.5-instant","company":"openai","family":"GPT","version":"GPT-5.5","score":2.4},{"place":135,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":2.4},{"place":136,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":2.4},{"place":137,"model":"claude-opus-4-1-20250805-thinking","company":"anthropic","family":"Claude","version":"Claude 4.1","score":2.4},{"place":138,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.4},{"place":139,"model":"qwen3.5-plus","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.1},{"place":140,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":2.1},{"place":141,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":2.1},{"place":142,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":2.1},{"place":143,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":2.1},{"place":144,"model":"claude-opus-4.5-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.1},{"place":145,"model":"claude-4.5-haiku-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.1},{"place":146,"model":"grok-4-heavy","company":"xai","family":"Grok","version":"Grok 4","score":2.1},{"place":147,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":2.1},{"place":148,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":2.1},{"place":149,"model":"o4-mini-medium","company":"openai","family":"o4","version":"o4","score":2.1},{"place":150,"model":"gpt-5-nano-medium","company":"openai","family":"GPT","version":"GPT-5","score":2.1},{"place":151,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":2.1},{"place":152,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":2.1},{"place":153,"model":"qwen3.6-flash","company":"qwen","family":"Qwen","version":"Qwen3.6","score":0},{"place":154,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0},{"place":155,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":0},{"place":156,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":0},{"place":157,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":0},{"place":158,"model":"gpt-5-nano-high","company":"openai","family":"GPT","version":"GPT-5","score":0},{"place":159,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":0},{"place":160,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":0},{"place":161,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0},{"place":162,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":0},{"place":163,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":0},{"place":164,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":0},{"place":165,"model":"gemini-3.5-flash-lite-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":0},{"place":166,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":0},{"place":167,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":0}]},{"id":"screenqa-complex","name":"ScreenQA Complex","topic":"GUI QA","description":"Complex ScreenQA benchmark accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Holo1.5-72B","top_percent":87.1,"top_model_id":"holo1.5-72b","top_generation":"Holo1.5","top_model_base":"Holo1.5-72B","top_model_family":"Holo","top_company":"hcompany","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":87.1},{"place":2,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":83.3},{"place":3,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":83.2},{"place":4,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":83.2},{"place":5,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":82.3},{"place":6,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":81.4},{"place":7,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":81.1},{"place":8,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":79.2},{"place":9,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":76},{"place":10,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":75.7},{"place":11,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":65.1},{"place":12,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":53.5}]},{"id":"screenqa-short","name":"ScreenQA Short","topic":"GUI QA","description":"Short-form ScreenQA benchmark accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Holo1.5-72B","top_percent":91.9,"top_model_id":"holo1.5-72b","top_generation":"Holo1.5","top_model_base":"Holo1.5-72B","top_model_family":"Holo","top_company":"hcompany","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":91.9},{"place":2,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":91},{"place":3,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":88.7},{"place":4,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":88.6},{"place":5,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":87.9},{"place":6,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87.9},{"place":7,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":87},{"place":8,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87},{"place":9,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":86.3},{"place":10,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":86},{"place":11,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":83.3},{"place":12,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":78.3}]},{"id":"screenspot","name":"ScreenSpot","topic":"Screen UI locators","description":"Center accuracy on ScreenSpot.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-VL 32B Instruct","top_percent":95.8,"top_model_id":"qwen3-vl-32b-instruct","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 32B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":40,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.8},{"place":2,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.4},{"place":3,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":95.2},{"place":4,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94.7},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94.4},{"place":6,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":94},{"place":7,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93.31},{"place":8,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":92.94},{"place":9,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.4},{"place":10,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90.73},{"place":11,"model":"molmoweb-ground-8b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":88.7},{"place":12,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":88.1},{"place":13,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":87.4},{"place":14,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":87.3},{"place":15,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":87.2},{"place":16,"model":"molmoweb-4b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":87.2},{"place":17,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":87.1},{"place":18,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":86.99},{"place":19,"model":"fara-7b","company":"microsoft","family":"Fara","version":"Fara","score":86.7},{"place":20,"model":"uground-v1-7b","company":"osunlp","family":"UGround","version":"UGround-V1","score":86.7},{"place":21,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":86.2},{"place":22,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":85.5},{"place":23,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":85.4},{"place":24,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":84.7},{"place":25,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":83.75},{"place":26,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":83.5},{"place":27,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":83.3},{"place":28,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":80.1},{"place":29,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":79.5},{"place":30,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":70.2},{"place":31,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":68.05},{"place":32,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":66.8},{"place":33,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":66.3},{"place":34,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.39},{"place":35,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":56.64},{"place":36,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.7},{"place":37,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":31},{"place":38,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":28.5},{"place":39,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":27.2},{"place":40,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":24.8},{"place":41,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":20.26}]},{"id":"screenspot-pro","name":"ScreenSpot-Pro","topic":"Screen UI locators","description":"Average center accuracy on ScreenSpot-Pro.","url":"","leaderboard":"https://gui-agent.github.io/grounding-leaderboard/","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":92.7,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":164,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":92.7},{"place":2,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87.3},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87.3},{"place":4,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":86.3},{"place":5,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":85.4},{"place":6,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":84.5},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.4},{"place":8,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":84.1},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":83.1},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":82.3},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":81.3},{"place":12,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":79.5},{"place":13,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":79},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":76.9},{"place":15,"model":"qwen-ui-agent-27b","company":"qwen","family":"Qwen","version":"Qwen-UI-Agent","score":76.6},{"place":16,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":76.1},{"place":17,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.9},{"place":18,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":75.4},{"place":19,"model":"ui-venus-2-27b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":74.1},{"place":20,"model":"indeed-ui-8b","company":"intelligence-indeed","family":"Indeed-UI","version":"Indeed-UI","score":73.4},{"place":21,"model":"indeed-ui-32b","company":"intelligence-indeed","family":"Indeed-UI","version":"Indeed-UI","score":73.3},{"place":22,"model":"kv-ground-guiowl1.5-8b-0315","company":"vocaela","family":"KV-Ground","version":"KV-Ground-GuiOwl1.5","score":73.2},{"place":23,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":73.1},{"place":24,"model":"ui-venus-2-9b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":73},{"place":25,"model":"duvo-eye-1","company":"duvoai","family":"Duvo Eye","version":"Duvo Eye-1","score":72.9},{"place":26,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.7},{"place":27,"model":"holo3-122b-a10b","company":"hcompany","family":"Holo","version":"Holo3","score":72.2},{"place":28,"model":"holo2-235b-a22b","company":"hcompany","family":"Holo","version":"Holo2","score":70.6},{"place":29,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.4},{"place":30,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.3},{"place":31,"model":"ui-venus-1.5-30b-a3b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":69.6},{"place":32,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.3},{"place":33,"model":"vista-9b","company":"antgroup","family":"VISTA","version":"VISTA","score":69.2},{"place":34,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":69.1},{"place":35,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":68.9},{"place":36,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.6},{"place":37,"model":"ui-venus-1.5-8b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":68.4},{"place":38,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":68.2},{"place":39,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":68.1},{"place":40,"model":"mai-ui-32b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":67.9},{"place":41,"model":"holo3-35b-a3b","company":"hcompany","family":"Holo","version":"Holo3","score":67.6},{"place":42,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":67.4},{"place":43,"model":"kv-ground-guiowl1.5-4b-0228","company":"vocaela","family":"KV-Ground","version":"KV-Ground-GuiOwl1.5","score":67},{"place":44,"model":"huzzleworld-3b","company":"huzzle","family":"HuzzleWorld","version":"HuzzleWorld","score":66.4},{"place":45,"model":"holo2-30b-a3b","company":"hcompany","family":"Holo","version":"Holo2","score":66.1},{"place":46,"model":"mai-ui-8b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":65.8},{"place":47,"model":"mai-ui-8b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":65.7},{"place":48,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.6},{"place":49,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.5},{"place":50,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":65.3},{"place":51,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.2},{"place":52,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":65.2},{"place":53,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.5},{"place":54,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":64.3},{"place":55,"model":"vista-4b","company":"antgroup","family":"VISTA","version":"VISTA","score":64.2},{"place":56,"model":"gta1-32b","company":"salesforce","family":"GTA1","version":"GTA1","score":63.6},{"place":57,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":63.3},{"place":58,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":63.25},{"place":59,"model":"kv-ground-qwen3vl-4b","company":"vocaela","family":"KV-Ground","version":"KV-Ground-Qwen3VL","score":63.2},{"place":60,"model":"step-gui-8b","company":"stepfun","family":"Step-GUI","version":"Step-GUI","score":62.6},{"place":61,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62},{"place":62,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":61.9},{"place":63,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.8},{"place":64,"model":"huzzleworld-2b","company":"huzzle","family":"HuzzleWorld","version":"HuzzleWorld","score":61.7},{"place":65,"model":"ui-tars-1.5","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":61.6},{"place":66,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":61.6},{"place":67,"model":"adazoom-gui-4b","company":"lenovo","family":"AdaZoom","version":"AdaZoom-GUI","score":61.6},{"place":68,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61},{"place":69,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":60.9},{"place":70,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":60.9},{"place":71,"model":"opencua-72b","company":"xlang","family":"OpenCUA","version":"OpenCUA","score":60.8},{"place":72,"model":"gui-arp-7b","company":"whu","family":"GUI","version":"GUI-ARP","score":60.8},{"place":73,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.5},{"place":74,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.3},{"place":75,"model":"molmopoint-gui-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":60.2},{"place":76,"model":"step-gui-4b","company":"stepfun","family":"Step-GUI","version":"Step-GUI","score":60},{"place":77,"model":"points-gui-g-8b","company":"tencent","family":"POINTS-GUI","version":"POINTS-GUI-G","score":59.9},{"place":78,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":59.6},{"place":79,"model":"gui-aima-3b","company":"adobe","family":"GUI","version":"GUI-AIMA","score":59.6},{"place":80,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.5},{"place":81,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.5},{"place":82,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":58.9},{"place":83,"model":"gta1-72b","company":"salesforce","family":"GTA1","version":"GTA1","score":58.4},{"place":84,"model":"gta1-qwen2.5vl-72b","company":"salesforce","family":"GTA1","version":"GTA1-Qwen2.5VL","score":58.4},{"place":85,"model":"gui-owl-32b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl","score":58},{"place":86,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":57.94},{"place":87,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.9},{"place":88,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":57.9},{"place":89,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":57.7},{"place":90,"model":"ui-venus-1.5-2b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":57.7},{"place":91,"model":"bami-7b","company":"tsinghua","family":"BAMI","version":"BAMI","score":57.7},{"place":92,"model":"mai-ui-2b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":57.4},{"place":93,"model":"holo2-4b","company":"hcompany","family":"Holo","version":"Holo2","score":57.2},{"place":94,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":55.6},{"place":95,"model":"huzzleworld-1b","company":"huzzle","family":"HuzzleWorld","version":"HuzzleWorld","score":55.6},{"place":96,"model":"gta1-7b","company":"salesforce","family":"GTA1","version":"GTA1","score":55.5},{"place":97,"model":"opencua-32b","company":"hku","family":"OpenCUA","version":"OpenCUA","score":55.3},{"place":98,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.9},{"place":99,"model":"gui-owl-7b","company":"alibaba","family":"GUI","version":"GUI","score":54.9},{"place":100,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.6},{"place":101,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.7},{"place":102,"model":"gta1-32b","company":"salesforce","family":"GTA1","version":"GTA1","score":53.6},{"place":103,"model":"gta1-qwen2.5vl-32b","company":"salesforce","family":"GTA1","version":"GTA1-Qwen2.5VL","score":53.6},{"place":104,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":53.3},{"place":105,"model":"ferret-ui-lite-3b","company":"apple","family":"Ferret-UI","version":"Ferret-UI Lite","score":53.3},{"place":106,"model":"llada-ui","company":"antgroup","family":"LLaDA","version":"LLaDA-UI","score":52.9},{"place":107,"model":"gui-spotlight","company":"umn","family":"GUI","version":"GUI-Spotlight","score":52.8},{"place":108,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.7},{"place":109,"model":"v2p-7b","company":"","family":"V2P","version":"V2P","score":52.5},{"place":110,"model":"molmo2-gui-8b","company":"allenai","family":"Molmo","version":"Molmo2","score":52.3},{"place":111,"model":"tianxi-action-7b","company":"lenovo","family":"TianXi","version":"TianXi Action","score":51.9},{"place":112,"model":"infigui-g1-7b","company":"infix-ai","family":"InfiGUI","version":"InfiGUI","score":51.9},{"place":113,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":51.55},{"place":114,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":51.5},{"place":115,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":51.49},{"place":116,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":51},{"place":117,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":50.8},{"place":118,"model":"v2p-7b","company":"","family":"V2P","version":"V2P","score":50.6},{"place":119,"model":"jedi-7b","company":"xlang","family":"Jedi","version":"Jedi","score":50.2},{"place":120,"model":"groundnext-7b","company":"servicenow","family":"GroundNext","version":"GroundNext","score":50.2},{"place":121,"model":"gta1-7b","company":"salesforce","family":"GTA1","version":"GTA1","score":50.1},{"place":122,"model":"gta1-qwen2.5vl-7b","company":"salesforce","family":"GTA1","version":"GTA1-Qwen2.5VL","score":50.1},{"place":123,"model":"opencua-7b","company":"xlang","family":"OpenCUA","version":"OpenCUA","score":50},{"place":124,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.9},{"place":125,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.9},{"place":126,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":49.5},{"place":127,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.5},{"place":128,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.5},{"place":129,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":48},{"place":130,"model":"ui-agile-7b","company":"kdegroup","family":"UI-AGILE","version":"UI-AGILE","score":47.9},{"place":131,"model":"gui-g2-7b","company":"zju","family":"GUI","version":"GUI","score":47.5},{"place":132,"model":"se-gui-7b","company":"se-gui","family":"SE-GUI","version":"SE-GUI","score":47.2},{"place":133,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.6},{"place":134,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":45.7},{"place":135,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":45.68},{"place":136,"model":"infigui-g1-3b","company":"infix-ai","family":"InfiGUI","version":"InfiGUI-G1","score":45.2},{"place":137,"model":"ui-agile-3b","company":"kdegroup","family":"UI-AGILE","version":"UI-AGILE","score":45},{"place":138,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":44.6},{"place":139,"model":"gui-actor-7b-qwen2.5-vl","company":"microsoft","family":"GUI-Actor","version":"GUI-Actor","score":44.6},{"place":140,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":43.6},{"place":141,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":43.6},{"place":142,"model":"phi-ground","company":"microsoft","family":"Phi","version":"Phi","score":43.2},{"place":143,"model":"gui-actor-3b-qwen2.5-vl","company":"microsoft","family":"GUI","version":"GUI-Actor-3B (Qwen2.5-VL)","score":42.2},{"place":144,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":41.9},{"place":145,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.9},{"place":146,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.4},{"place":147,"model":"gui-actor-7b-qwen2-vl","company":"microsoft","family":"GUI","version":"GUI-Actor-7B (Qwen2-VL)","score":40.7},{"place":148,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40.6},{"place":149,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":39.9},{"place":150,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":39},{"place":151,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":38.5},{"place":152,"model":"ui-tars-72b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":38.1},{"place":153,"model":"gui-actor-2b-qwen2-vl","company":"microsoft","family":"GUI","version":"GUI-Actor-2B (Qwen2-VL)","score":36.7},{"place":154,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":36.4},{"place":155,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":36.2},{"place":156,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":36.2},{"place":157,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":36.2},{"place":158,"model":"gui-g1","company":"ruc","family":"GUI","version":"GUI-G1","score":35.9},{"place":159,"model":"se-gui-3b","company":"se-gui","family":"SE-GUI","version":"SE-GUI","score":35.9},{"place":160,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":35.7},{"place":161,"model":"ui-tars-7b","company":"bytedance","family":"UI","version":"UI","score":35.7},{"place":162,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":34.84},{"place":163,"model":"uground-v1-72b","company":"osunlp","family":"UGround","version":"UGround-V1","score":34.5},{"place":164,"model":"di-gui-3b","company":"byd","family":"Di","version":"Di-GUI","score":31.6},{"place":165,"model":"uground-v1-7b","company":"osunlp","family":"UGround","version":"UGround-V1","score":31.1},{"place":166,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":30.4},{"place":167,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":29.3},{"place":168,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":29},{"place":169,"model":"zonui-3b","company":"nycu","family":"ZonUI","version":"ZonUI","score":28.7},{"place":170,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":27.7},{"place":171,"model":"ui-tars-2b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":27.7},{"place":172,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":26.8},{"place":173,"model":"uground-v1-2b","company":"osunlp","family":"UGround","version":"UGround-V1","score":26.6},{"place":174,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":26.06},{"place":175,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":23.66},{"place":176,"model":"gpt-03-cua","company":"openai","family":"o3","version":"o3","score":23.4},{"place":177,"model":"aguvis-7b","company":"hku","family":"Aguvis","version":"Aguvis","score":22.9},{"place":178,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":19.1},{"place":179,"model":"os-atlas-7b","company":"os-copilot","family":"OS-Atlas","version":"OS-Atlas","score":18.9},{"place":180,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":18.5},{"place":181,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":17.1},{"place":182,"model":"uground-7b","company":"osunlp","family":"UGround","version":"UGround","score":16.5},{"place":183,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":16.1},{"place":184,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":15.39},{"place":185,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":11.4},{"place":186,"model":"aria-ui","company":"rhymes","family":"Aria","version":"Aria-UI","score":11.3},{"place":187,"model":"showui-2b","company":"showlab","family":"ShowUI","version":"ShowUI","score":7.7},{"place":188,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":7.7},{"place":189,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":6},{"place":190,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.9},{"place":191,"model":"os-atlas-4b","company":"os-copilot","family":"OS-Atlas","version":"OS-Atlas","score":3.7},{"place":192,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":3.5},{"place":193,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3.5},{"place":194,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":3},{"place":195,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1.6},{"place":196,"model":"seeclick","company":"nju","family":"SeeClick","version":"SeeClick","score":1.1},{"place":197,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":1},{"place":198,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":0.8},{"place":199,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":0.1}]},{"id":"screenspot-pro-with-tools","name":"ScreenSpot-Pro (with tools)","topic":"Screen UI locators (with tools)","description":"ScreenSpot-Pro evaluated with tool access (e.g. zoom/crop).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.8","top_percent":87.9,"top_model_id":"claude-opus-4.8","top_generation":"Claude 4.8","top_model_base":"Claude Opus 4.8","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":87.9},{"place":2,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":87.6},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":83.1}]},{"id":"screenspot-v2","name":"ScreenSpot-v2","topic":"Screen UI locators","description":"Center accuracy on ScreenSpot-v2.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MAI-UI-32B","top_percent":96.5,"top_model_id":"mai-ui-32b","top_generation":"MAI-UI","top_model_base":"MAI-UI","top_model_family":"MAI-UI","top_company":"tongyi","top_open_source":0,"lower_is_better":false,"bench_models":88,"total_models":3854,"placements":[{"place":1,"model":"mai-ui-32b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":96.5},{"place":2,"model":"ui-venus-1.5-30b-a3b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":96.2},{"place":3,"model":"ui-venus-1.5-8b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":95.9},{"place":4,"model":"holo2-235b-a22b","company":"hcompany","family":"Holo","version":"Holo2","score":95.9},{"place":5,"model":"vista-9b","company":"antgroup","family":"VISTA","version":"VISTA","score":95.8},{"place":6,"model":"points-gui-g-8b","company":"tencent","family":"POINTS-GUI","version":"POINTS-GUI-G","score":95.7},{"place":7,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":95.4},{"place":8,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":95.3},{"place":9,"model":"gta1-32b","company":"salesforce","family":"GTA1","version":"GTA1","score":95.2},{"place":10,"model":"mai-ui-8b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":95.2},{"place":11,"model":"step-gui-8b","company":"stepfun","family":"Step-GUI","version":"Step-GUI","score":95.1},{"place":12,"model":"holo2-30b-a3b","company":"hcompany","family":"Holo","version":"Holo2","score":94.9},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":94.7},{"place":14,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":94.41},{"place":15,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":94.2},{"place":16,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":94.1},{"place":17,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":94},{"place":18,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":94},{"place":19,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":93.9},{"place":20,"model":"vista-4b","company":"antgroup","family":"VISTA","version":"VISTA","score":93.8},{"place":21,"model":"gui-g2-7b","company":"zju","family":"GUI","version":"GUI","score":93.8},{"place":22,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":93.7},{"place":23,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":93.6},{"place":24,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":93.6},{"place":25,"model":"step-gui-4b","company":"stepfun","family":"Step-GUI","version":"Step-GUI","score":93.6},{"place":26,"model":"infigui-g1-7b","company":"infix-ai","family":"InfiGUI","version":"InfiGUI","score":93.5},{"place":27,"model":"molmopoint-gui-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":93.4},{"place":28,"model":"opencua-32b","company":"hku","family":"OpenCUA","version":"OpenCUA","score":93.4},{"place":29,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":93.31},{"place":30,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":93.3},{"place":31,"model":"gui-g2-7b","company":"zju","family":"GUI","version":"GUI","score":93.3},{"place":32,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":93.2},{"place":33,"model":"holo2-4b","company":"hcompany","family":"Holo","version":"Holo2","score":93.2},{"place":34,"model":"gui-owl-32b","company":"alibaba","family":"GUI-Owl","version":"GUI-Owl","score":93.1},{"place":35,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":93},{"place":36,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":93},{"place":37,"model":"opencua-72b","company":"xlang","family":"OpenCUA","version":"OpenCUA","score":92.9},{"place":38,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.8},{"place":39,"model":"ui-venus-1.5-2b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":92.8},{"place":40,"model":"gui-owl-7b","company":"alibaba","family":"GUI","version":"GUI","score":92.8},{"place":41,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.7},{"place":42,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":92.61},{"place":43,"model":"mai-ui-2b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":92.5},{"place":44,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":92.4},{"place":45,"model":"gta1-7b","company":"salesforce","family":"GTA1","version":"GTA1","score":92.4},{"place":46,"model":"opencua-7b","company":"xlang","family":"OpenCUA","version":"OpenCUA","score":92.3},{"place":47,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":92.14},{"place":48,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.1},{"place":49,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.9},{"place":50,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":91.8},{"place":51,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.8},{"place":52,"model":"molmoweb-ground-8b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":91.8},{"place":53,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.7},{"place":54,"model":"jedi-7b","company":"xlang","family":"Jedi","version":"Jedi","score":91.7},{"place":55,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":91.66},{"place":56,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":91.6},{"place":57,"model":"ui-tars-7b","company":"bytedance","family":"UI","version":"UI","score":91.6},{"place":58,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.5},{"place":59,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.5},{"place":60,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":90.82},{"place":61,"model":"llada-ui","company":"antgroup","family":"LLaDA","version":"LLaDA-UI","score":90.7},{"place":62,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":90.5},{"place":63,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.4},{"place":64,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90},{"place":65,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":89.9},{"place":66,"model":"holotron-12b","company":"hcompany","family":"Holotron","version":"Holotron","score":89.9},{"place":67,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":89.85},{"place":68,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":89.8},{"place":69,"model":"kimi-vl-a3b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":89.8},{"place":70,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":89.5},{"place":71,"model":"molmoweb-4b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":89.5},{"place":72,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":89.5},{"place":73,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":89.3},{"place":74,"model":"fara-7b","company":"microsoft","family":"Fara","version":"Fara","score":89.3},{"place":75,"model":"groundnext-7b","company":"servicenow","family":"GroundNext","version":"GroundNext","score":89.3},{"place":76,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":88.91},{"place":77,"model":"molmo2-gui-8b","company":"allenai","family":"Molmo","version":"Molmo2","score":88.8},{"place":78,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":88.3},{"place":79,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":88.2},{"place":80,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88},{"place":81,"model":"gpt-03-cua","company":"openai","family":"o3","version":"o3","score":87.9},{"place":82,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.7},{"place":83,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":87.6},{"place":84,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":87.3},{"place":85,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":86},{"place":86,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.6},{"place":87,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":84.2},{"place":88,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":84.02},{"place":89,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.1},{"place":90,"model":"kimi-vl-a3b-thinking","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":81.8},{"place":91,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":81.4},{"place":92,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":80.7},{"place":93,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":80},{"place":94,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.5},{"place":95,"model":"uground-v1-7b","company":"osunlp","family":"UGround","version":"UGround-V1","score":76.3},{"place":96,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.5},{"place":97,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.9},{"place":98,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":49.4},{"place":99,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":36.7},{"place":100,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":31.1},{"place":101,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":28.5},{"place":102,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":20.1},{"place":103,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":3.5}]},{"id":"seal-0","name":"SEAL-0","topic":"Agentic web search","description":"Evaluation of multi-step browsing agents on search, evidence gathering, and synthesis tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiroThinker-H1","top_percent":61.3,"top_model_id":"mirothinker-h1","top_generation":"MiroThinker H1","top_model_base":"MiroThinker H1","top_model_family":"MiroThinker","top_company":"miromind","top_open_source":0,"lower_is_better":false,"bench_models":44,"total_models":3854,"placements":[{"place":1,"model":"mirothinker-h1","company":"miromind","family":"MiroThinker","version":"MiroThinker H1","score":61.3},{"place":2,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":57.4},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":57.4},{"place":4,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":56.4},{"place":5,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":56.36},{"place":6,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":56.3},{"place":7,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.95},{"place":8,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.4},{"place":9,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.4},{"place":10,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":53},{"place":11,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":52.7},{"place":12,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":51.4},{"place":13,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":51.4},{"place":14,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":51},{"place":15,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":50.45},{"place":16,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":49.6},{"place":17,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":49.55},{"place":18,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":49.5},{"place":19,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":49.5},{"place":20,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":49.5},{"place":21,"model":"webleaper-30b-a3b","company":"tongyi","family":"WebLeaper","version":"WebLeaper","score":48.6},{"place":22,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":48.2},{"place":23,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.7},{"place":24,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":47.7},{"place":25,"model":"toolmind-web-3b","company":"boss","family":"Nanbeige","version":"ToolMind-Web","score":47.7},{"place":26,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.2},{"place":27,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":46.9},{"place":28,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.9},{"place":29,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":46.2},{"place":30,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":45.8},{"place":31,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":45.5},{"place":32,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":45.1},{"place":33,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":45},{"place":34,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":45},{"place":35,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.1},{"place":36,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":42.34},{"place":37,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.4},{"place":38,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":40.4},{"place":39,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":40},{"place":40,"model":"iterresearch-30b-a3b","company":"tongyi","family":"IterResearch","version":"IterResearch","score":39.6},{"place":41,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":38.74},{"place":42,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":38.7},{"place":43,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":38.5},{"place":44,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":38.5},{"place":45,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":36.94},{"place":46,"model":"kimi-researcher","company":"moonshotai","family":"Kimi","version":"Kimi Researcher","score":36},{"place":47,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":34.2},{"place":48,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.5},{"place":49,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":25.2}]},{"id":"sec-bench-pro","name":"SEC-Bench Pro","topic":"Cybersecurity","description":"Proof-of-concept exploit generation for vulnerabilities in complex software.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":85.4,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":85.4},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":83.33},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":79.1},{"place":4,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":78.8},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":74.3},{"place":6,"model":"gpt-5.6-sol-ultra","company":"openai","family":"GPT","version":"GPT-5.6","score":74.3},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":71.2},{"place":8,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":66.3},{"place":9,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":66.3},{"place":10,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":62.8},{"place":11,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":57.7},{"place":12,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.4},{"place":13,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":48.9},{"place":14,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":47.5},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":45.8},{"place":16,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":34.2},{"place":17,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":30.9},{"place":18,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":17.7}]},{"id":"seccodebench","name":"SecCodeBench","topic":"Secure code generation","description":"Benchmark evaluating secure code generation capabilities.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2","top_percent":68.7,"top_model_id":"gpt-5.2","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":68.7},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.6},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.3},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":62.4},{"place":5,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":61.3},{"place":6,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":57.5}]},{"id":"seed-bench-2-plus","name":"SEED-Bench-2-Plus","topic":"Multimodal evaluation","description":"SEED-Bench-2-Plus overall accuracy.","url":"https://huggingface.co/datasets/AILab-CVC/SEED-Bench-2-plus","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.16790","metric":"percent","stars":"","top_model":"Claude 3.7 Sonnet","top_percent":72.9,"top_model_id":"claude-3.7-sonnet","top_generation":"Claude 3.7","top_model_base":"Claude 3.7 Sonnet","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":72.9},{"place":2,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":72.4},{"place":3,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":72},{"place":4,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":71.9},{"place":5,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":71.7},{"place":6,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":71.3},{"place":7,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":71.2},{"place":8,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":71.1},{"place":9,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":70.8},{"place":10,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":70.7},{"place":11,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":69.7},{"place":12,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":69.7},{"place":13,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":69.7},{"place":14,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":69.2},{"place":15,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":69},{"place":16,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":68},{"place":17,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.6},{"place":18,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.5},{"place":19,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.3},{"place":20,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":67.2},{"place":21,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":66.9},{"place":22,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":66.3},{"place":23,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":66.3},{"place":24,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":65.7},{"place":25,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":64.6},{"place":26,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":63.9},{"place":27,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":63},{"place":28,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":62.4},{"place":29,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":62.2},{"place":30,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":60.9},{"place":31,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":60},{"place":32,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":59},{"place":33,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":54.3},{"place":34,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":53.8},{"place":35,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":44.2}]},{"id":"seed-bench-img","name":"SEED-Bench-Img","topic":"Multimodal image understanding","description":"SEED-Bench image-only subset (SEED-Bench-Img).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Bagel 14B","top_percent":78.5,"top_model_id":"bagel-14b","top_generation":"Bagel","top_model_base":"Bagel 14B","top_model_family":"Bagel","top_company":"jondurbin","top_open_source":1,"lower_is_better":false,"bench_models":75,"total_models":3854,"placements":[{"place":1,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":78.5},{"place":2,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":78},{"place":3,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":77.7},{"place":4,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":77.1},{"place":5,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":77.1},{"place":6,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":76.8},{"place":7,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":76.8},{"place":8,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":76.6},{"place":9,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.6},{"place":10,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":76.5},{"place":11,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.4},{"place":12,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.1},{"place":13,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":76},{"place":14,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":76},{"place":15,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":75.9},{"place":16,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":75.9},{"place":17,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.8},{"place":18,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":75.7},{"place":19,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":75.6},{"place":20,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":75.4},{"place":21,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":75.4},{"place":22,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":75.4},{"place":23,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":75.3},{"place":24,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":75.3},{"place":25,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":75.2},{"place":26,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":75},{"place":27,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":74.9},{"place":28,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":74.7},{"place":29,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":74.3},{"place":30,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":74.2},{"place":31,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":74.1},{"place":32,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":74.1},{"place":33,"model":"blip-3o-4b","company":"salesforce","family":"BLIP","version":"BLIP-3O","score":73.8},{"place":34,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":73},{"place":35,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":72.7},{"place":36,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":72.7},{"place":37,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":72.7},{"place":38,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":72.6},{"place":39,"model":"bunny-4b","company":"baai","family":"Bunny","version":"Bunny","score":72.5},{"place":40,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":72.5},{"place":41,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":72.4},{"place":42,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":72.4},{"place":43,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":72.3},{"place":44,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":72.3},{"place":45,"model":"blip-3-4b","company":"salesforce","family":"BLIP","version":"BLIP-3","score":72.2},{"place":46,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":72.1},{"place":47,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":72.1},{"place":48,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":71.8},{"place":49,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":71.6},{"place":50,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":71.6},{"place":51,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.4},{"place":52,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":71.4},{"place":53,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":71},{"place":54,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":70.7},{"place":55,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":70.7},{"place":56,"model":"gemini-1.0-pro-vision","company":"google","family":"Gemini","version":"Gemini 1.0","score":70.7},{"place":57,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":70.3},{"place":58,"model":"llava-internlm2-20b-qlora","company":"internlm","family":"InternLM","version":"LLaVA-InternLM2-20B (QLoRA)","score":70.2},{"place":59,"model":"sharegpt4v-7b","company":"internlm","family":"InternLM","version":"ShareGPT4V","score":69.7},{"place":60,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":69.1},{"place":61,"model":"monkey","company":"hust","family":"Monkey","version":"Monkey","score":68.9},{"place":62,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":68.8},{"place":63,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":68.7},{"place":64,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":68.3},{"place":65,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":68.2},{"place":66,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":68.2},{"place":67,"model":"vila1.5-3b","company":"nvidia","family":"VILA","version":"VILA 1.5","score":67.9},{"place":68,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":67.1},{"place":69,"model":"harmon-1.5b","company":"harmonai","family":"Harmon","version":"Harmon-1.5B","score":67.1},{"place":70,"model":"internlm-xcomposer","company":"internlm","family":"InternLM","version":"InternLM-XComposer","score":66.1},{"place":71,"model":"unified-io-2-xxl","company":"allenai","family":"Unified-IO","version":"Unified-IO 2","score":65.6},{"place":72,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":65.4},{"place":73,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":64.1},{"place":74,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":64},{"place":75,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":62.8},{"place":76,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":62.3},{"place":77,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":61.6},{"place":78,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":58.8},{"place":79,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":58.6},{"place":80,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":58.2},{"place":81,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":53.4},{"place":82,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":53.2},{"place":83,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":52},{"place":84,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":47.4},{"place":85,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":42.7},{"place":86,"model":"llava-v1-7b","company":"llava","family":"LLaVA","version":"LLaVA-v1","score":25.5}]},{"id":"seedbench","name":"SEED-Bench","topic":"Multimodal evaluation","description":"SEED-Bench comprehensive multimodal understanding benchmark evaluating generative comprehension across multiple dimensions.","url":"https://huggingface.co/datasets/AILab-CVC/SEED-Bench","leaderboard":"","github":"https://github.com/AILab-CVC/SEED-Bench","paper":"https://arxiv.org/abs/2307.16125","metric":"percent","stars":"","top_model":"Qwen3-VL-4B-Instruct","top_percent":77,"top_model_id":"qwen3-vl-4b-instruct","top_generation":"Qwen3 VL","top_model_base":"Qwen3-VL 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77},{"place":2,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":76.9},{"place":3,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":76.78},{"place":4,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":76.55},{"place":5,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.65},{"place":6,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":75.41},{"place":7,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":74.95},{"place":8,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":73.88},{"place":9,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":73.7},{"place":10,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":72.7},{"place":11,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":72.7},{"place":12,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":71.9},{"place":13,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":71.6},{"place":14,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":71.3},{"place":15,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":70.7},{"place":16,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":70.4},{"place":17,"model":"llava-next-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":70.2},{"place":18,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":68.9},{"place":19,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":68.8},{"place":20,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":68.28},{"place":21,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":68.2},{"place":22,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":67.6},{"place":23,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":66.7},{"place":24,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":64.8},{"place":25,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":58.2},{"place":26,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":56.3}]},{"id":"sfe","name":"SFE","topic":"Multimodal reasoning","description":"Structured factual evaluation for multimodal models.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 26B A4B IT","top_percent":63.09,"top_model_id":"gemma-4-26b-a4b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 26B A4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":63.09},{"place":2,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.97},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":61.9},{"place":4,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":61.67},{"place":5,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":60.74},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":59.57},{"place":7,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59.08},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":58.9},{"place":9,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":58.43},{"place":10,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":53.7},{"place":11,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":52.7},{"place":12,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":52.66},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":52.09},{"place":14,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":52.03},{"place":15,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":51.31},{"place":16,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":51.2},{"place":17,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":50.76},{"place":18,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":50.5},{"place":19,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":48.51},{"place":20,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.7},{"place":21,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":47.5},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":46},{"place":23,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":44.4},{"place":24,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.4},{"place":25,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":36.8}]},{"id":"sgd-x-decision","name":"SGD/SGD-X (decision)","topic":"Dialogue state tracking","description":"Schema-Guided Dialogue (SGD-X) intent/slot decisions; macro-F1. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://github.com/google-research-datasets/dstc8-schema-guided-dialogue","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"Bespoke-Nimble-9B-v3","top_percent":71.8,"top_model_id":"bespoke-nimble-9b-v3","top_generation":"v3","top_model_base":"Bespoke-Nimble-9B","top_model_family":"Bespoke-Nimble","top_company":"bespokelabs","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":71.8},{"place":2,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":69.2},{"place":3,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":67.2},{"place":4,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":66.5},{"place":5,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":64.3},{"place":6,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":64.2},{"place":7,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":64},{"place":8,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":63.2},{"place":9,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":62.6},{"place":10,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":62},{"place":11,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":61.5},{"place":12,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":61.3},{"place":13,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":61.2},{"place":14,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":60.9},{"place":15,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":60.7},{"place":16,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":59.9},{"place":17,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":59.7},{"place":18,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":59.6},{"place":19,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":59.3},{"place":20,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59},{"place":21,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":58.2},{"place":22,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":57.9},{"place":23,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":57.4},{"place":24,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":57.3},{"place":25,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":51.3},{"place":26,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":47.3},{"place":27,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":43.8},{"place":28,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":43},{"place":29,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":42.4},{"place":30,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":40.7},{"place":31,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":40.6},{"place":32,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":39.2},{"place":33,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":36.3},{"place":34,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":35.7},{"place":35,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":34.2},{"place":36,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":32},{"place":37,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":9},{"place":38,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":0.8}]},{"id":"sgi-bench","name":"SGI-Bench","topic":"Scientific agents","description":"Scientific general intelligence benchmark of agentic scientific research workflows.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-S2-Preview","top_percent":52.52,"top_model_id":"intern-s2-preview","top_generation":"Intern-S2","top_model_base":"Intern-S2-Preview","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":52.52},{"place":2,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":52.41},{"place":3,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":51.89},{"place":4,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":50.63},{"place":5,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":49.37},{"place":6,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":49.06},{"place":7,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":45.7},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":45.28},{"place":9,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.44},{"place":10,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":42.77},{"place":11,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":38.36},{"place":12,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37.3},{"place":13,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":37.11},{"place":14,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":36.16},{"place":15,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.1},{"place":16,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":25.73},{"place":17,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":16.35}]},{"id":"sharerobot-affordance","name":"ShareRobot-Affordance","topic":"Embodied affordance","description":"ShareRobot affordance prediction benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ACE-Brain-0.6-9B","top_percent":48.82,"top_model_id":"ace-brain-0.6-9b","top_generation":"ACE-Brain-0.6","top_model_base":"ACE-Brain-0.6 9B","top_model_family":"ACE-Brain","top_company":"ace-robotics","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"ace-brain-0.6-9b","company":"ace-robotics","family":"ACE-Brain","version":"ACE-Brain-0.6","score":48.82},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":46.6},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":40.2},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":38.57},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":36.66},{"place":6,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":29.53}]},{"id":"sharerobot-traj","name":"ShareRobot-Trajectory","topic":"Embodied reasoning","description":"ShareRobot trajectory prediction benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"RoboBrain2.5-8B","top_percent":85.2,"top_model_id":"robobrain2.5-8b","top_generation":"RoboBrain 2.5","top_model_base":"RoboBrain 2.5 8B","top_model_family":"RoboBrain","top_company":"baai","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":85.2},{"place":2,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":85},{"place":3,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":84.9},{"place":4,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":84.5},{"place":5,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":84},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":83.1},{"place":7,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":82.8},{"place":8,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":82.1},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.9},{"place":10,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":80.9},{"place":11,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":79.3},{"place":12,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.2},{"place":13,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":69}]},{"id":"showdown","name":"Showdown","topic":"GUI agents","description":"Success rate on the Showdown UI interaction benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Holo2-235B-A22B","top_percent":80.4,"top_model_id":"holo2-235b-a22b","top_generation":"Holo2","top_model_base":"Holo2","top_model_family":"Holo","top_company":"hcompany","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"holo2-235b-a22b","company":"hcompany","family":"Holo","version":"Holo2","score":80.4},{"place":2,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":78.4},{"place":3,"model":"holo2-30b-a3b","company":"hcompany","family":"Holo","version":"Holo2","score":77.6},{"place":4,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":76.84},{"place":5,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":75.58},{"place":6,"model":"holo2-4b","company":"hcompany","family":"Holo","version":"Holo2","score":74.7},{"place":7,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":72.5},{"place":8,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":72.17},{"place":9,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":72},{"place":10,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.2},{"place":11,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":67.5},{"place":12,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":67.32},{"place":13,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.6},{"place":14,"model":"holotron-12b","company":"hcompany","family":"Holotron","version":"Holotron","score":66.1},{"place":15,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":64.27},{"place":16,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.2},{"place":17,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":59.96},{"place":18,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":58},{"place":19,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":52},{"place":20,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":50.3},{"place":21,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":41},{"place":22,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":23.9}]},{"id":"shp2-protein-function-prediction","name":"SHP2 Protein Function Prediction","topic":"Biosecurity","description":"Predict held-out functional assay measurements for single-amino-acid SHP2 variants; R² (higher is better).","url":"https://deploymentsafety.openai.com/gpt-6-1-terra","leaderboard":"","github":"","paper":"","metric":"r2","stars":"","top_model":"GPT-6 Astra","top_percent":0.4,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":0.4},{"place":2,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":0.3696},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":0.332},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":0.3},{"place":5,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":0.273},{"place":6,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":0.23},{"place":7,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":0.13}]},{"id":"sifo","name":"SIFO","topic":"Instruction following","description":"Single-turn instruction following benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-VL-30B-A3B Thinking","top_percent":66.9,"top_model_id":"qwen3-vl-30b-a3b-thinking","top_generation":"Qwen3 VL","top_model_base":"Qwen3 VL 30B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.9},{"place":2,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":50.1},{"place":3,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.1},{"place":4,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":45.7},{"place":5,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":44.8},{"place":6,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.7}]},{"id":"sifo-multiturn","name":"SIFO Multiturn","topic":"Instruction following","description":"Multi-turn SIFO benchmark for sustained instruction adherence.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-VL-30B-A3B Thinking","top_percent":60.3,"top_model_id":"qwen3-vl-30b-a3b-thinking","top_generation":"Qwen3 VL","top_model_base":"Qwen3 VL 30B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.3},{"place":2,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":38.3},{"place":3,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.7},{"place":4,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.7},{"place":5,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":35.2},{"place":6,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":35.1}]},{"id":"simplebench","name":"SimpleBench","topic":"Common-sense reasoning","description":"Multiple-choice trick questions on spatio-temporal reasoning, social intelligence and linguistic adversarial robustness where non-specialist humans outperform frontier LLMs.","url":"https://simple-bench.com/","leaderboard":"https://simple-bench.com/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":88.4,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":105,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":88.4},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":86.6},{"place":3,"model":"gpt-6-astra-pro","company":"openai","family":"GPT","version":"GPT-6","score":86.5},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":83.6},{"place":5,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":82.9},{"place":6,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":82.4},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.9},{"place":8,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":81.8},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.6},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":79.6},{"place":11,"model":"gpt-5.5-pro","company":"openai","family":"GPT","version":"GPT-5.5","score":76.9},{"place":12,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":76.7},{"place":13,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":76.4},{"place":14,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":75.9},{"place":15,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":75.9},{"place":16,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":74.5},{"place":17,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":73.1},{"place":18,"model":"gpt-5.6-sol-pro","company":"openai","family":"GPT","version":"GPT-5.6","score":71.7},{"place":19,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":70.4},{"place":20,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":70},{"place":21,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69},{"place":22,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":67.6},{"place":23,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":66.7},{"place":24,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":66.2},{"place":25,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":64.8},{"place":26,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":64.8},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.8},{"place":28,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63},{"place":29,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":62.9},{"place":30,"model":"qwen3.8-2.4t-a95b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":62.5},{"place":31,"model":"gemini-2.5-pro-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.4},{"place":32,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62},{"place":33,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":61.7},{"place":34,"model":"gpt-5-pro","company":"openai","family":"GPT","version":"GPT-5","score":61.6},{"place":35,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":61.1},{"place":36,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.1},{"place":37,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":60.7},{"place":38,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":60.6},{"place":39,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":60.5},{"place":40,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":60.2},{"place":41,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":60},{"place":42,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.7},{"place":43,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":58.8},{"place":44,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":58.8},{"place":45,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":57.9},{"place":46,"model":"gpt-5.2-pro-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":57.4},{"place":47,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":56.7},{"place":48,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":56},{"place":49,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":55.1},{"place":50,"model":"ox-alpha","company":"","family":"Stealth","version":"Ox","score":55.1},{"place":51,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.3},{"place":52,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":53.2},{"place":53,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":53.2},{"place":54,"model":"o3-high","company":"openai","family":"o3","version":"o3","score":53.1},{"place":55,"model":"deepseek-v3.2-speciale","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":52.6},{"place":56,"model":"gemini-2.5-pro-exp-03.25","company":"google","family":"Gemini","version":"Gemini 2.5","score":51.6},{"place":57,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.9},{"place":58,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":50},{"place":59,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":48.9},{"place":60,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":47.7},{"place":61,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":46.8},{"place":62,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":46.8},{"place":63,"model":"claude-3.7-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 3.7","score":46.4},{"place":64,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46.3},{"place":65,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":45.8},{"place":66,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":45.8},{"place":67,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":45.5},{"place":68,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":44.9},{"place":69,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":41.7},{"place":70,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":41.7},{"place":71,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":41.4},{"place":72,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":41.2},{"place":73,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":40.8},{"place":74,"model":"o1-2024-12-17-high","company":"openai","family":"o1","version":"o1","score":40.1},{"place":75,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":40},{"place":76,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":39.6},{"place":77,"model":"o4-mini-high","company":"openai","family":"o4","version":"o4","score":38.7},{"place":78,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":36.7},{"place":79,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":36.1},{"place":80,"model":"qwen3.6-flash","company":"qwen","family":"Qwen","version":"Qwen3.6","score":35.2},{"place":81,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":34.7},{"place":82,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":34.5},{"place":83,"model":"gemini-exp-1206","company":"google","family":"Gemini","version":"Gemini 1.0","score":31.1},{"place":84,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":31},{"place":85,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":30.9},{"place":86,"model":"gemini-2.0-flash-thinking-exp-1219","company":"google","family":"Gemini","version":"Gemini 2.0","score":30.7},{"place":87,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":27.7},{"place":88,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":27.5},{"place":89,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":27.2},{"place":90,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":27.1},{"place":91,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":27},{"place":92,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":26.3},{"place":93,"model":"gpt-4-turbo","company":"openai","family":"GPT","version":"GPT-4","score":25.1},{"place":94,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":25},{"place":95,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":23.5},{"place":96,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":23},{"place":97,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":22.8},{"place":98,"model":"grok-2","company":"xai","family":"Grok","version":"Grok 2","score":22.7},{"place":99,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":22.5},{"place":100,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":22.1},{"place":101,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":20.4},{"place":102,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":19.9},{"place":103,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":18.9},{"place":104,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":18.9},{"place":105,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":18.1},{"place":106,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":17.8},{"place":107,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":17.4},{"place":108,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":10.7},{"place":109,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":8}]},{"id":"simpleqa","name":"SimpleQA","topic":"QA","description":"Simple question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ERNIE 5.0","top_percent":74.01,"top_model_id":"ernie-5.0","top_generation":"ERNIE 5.0","top_model_base":"ERNIE 5.0","top_model_family":"ERNIE","top_company":"baidu","top_open_source":0,"lower_is_better":false,"bench_models":133,"total_models":3854,"placements":[{"place":1,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":74.01},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.1},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":69.33},{"place":4,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":62.5},{"place":5,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.1},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.5},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54},{"place":8,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":51.3},{"place":9,"model":"gpt-5-2025-08-07","company":"openai","family":"GPT","version":"GPT-5","score":51.1},{"place":10,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":50.5},{"place":11,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":50.4},{"place":12,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":50.3},{"place":13,"model":"o3","company":"openai","family":"o3","version":"o3","score":49.4},{"place":14,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":47.2},{"place":15,"model":"o1","company":"openai","family":"o1","version":"o1","score":47},{"place":16,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":45.9},{"place":17,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":44.3},{"place":18,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":42.3},{"place":19,"model":"grok-3","company":"xai","family":"Grok","version":"Grok 3","score":41.3},{"place":20,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":40.9},{"place":21,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":40.2},{"place":22,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":38.4},{"place":23,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":38.26},{"place":24,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":38.2},{"place":25,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":38.2},{"place":26,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":37.6},{"place":27,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":37.5},{"place":28,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":36.2},{"place":29,"model":"glm-5-base","company":"zai","family":"GLM","version":"GLM 5","score":36},{"place":30,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":35.3},{"place":31,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":34.9},{"place":32,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":34.37},{"place":33,"model":"glm-5.3-flash-base","company":"zai","family":"GLM","version":"GLM 5.3","score":33.5},{"place":34,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":32.3},{"place":35,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":31.9},{"place":36,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":31.6},{"place":37,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":31.2},{"place":38,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":31},{"place":39,"model":"cogito-671b-v2.1","company":"deepcogito","family":"Cogito","version":"Cogito 671B v2.1","score":30.94},{"place":40,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":30.1},{"place":41,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":30},{"place":42,"model":"gemini-2.0-flash","company":"google","family":"Gemini","version":"Gemini 2.0","score":29.9},{"place":43,"model":"kanana-2-30b-a3b-mid-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":29.7},{"place":44,"model":"kanana-2-30b-a3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":29.7},{"place":45,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":29.5},{"place":46,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":29.3},{"place":47,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":29.26},{"place":48,"model":"kanana-2-30b-a3b-base-2601","company":"kakao","family":"Kanana","version":"Kanana 2","score":29.13},{"place":49,"model":"intern-s2-mobius","company":"internlm","family":"Intern","version":"Intern-S2","score":28.9},{"place":50,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":28.4},{"place":51,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":28.4},{"place":52,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":28.2},{"place":53,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":28.02},{"place":54,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":27.8},{"place":55,"model":"gemini-2.5-flash-preview-05-20","company":"google","family":"Gemini","version":"Gemini 2.5","score":27.8},{"place":56,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":27.7},{"place":57,"model":"kanana-2-3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":27.39},{"place":58,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":27.3},{"place":59,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":27},{"place":60,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":27},{"place":61,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":27},{"place":62,"model":"kanana-1.5-32.5b-base","company":"kakao","family":"Kanana","version":"Kanana 1.5","score":26.95},{"place":63,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":26.6},{"place":64,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.47},{"place":65,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":26.47},{"place":66,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":26.47},{"place":67,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":26.3},{"place":68,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":26.3},{"place":69,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":26.2},{"place":70,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":26.15},{"place":71,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":26.1},{"place":72,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":24.9},{"place":73,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":24.9},{"place":74,"model":"mistral-large-2411","company":"mistral","family":"Mistral","version":"Mistral Large","score":24.2},{"place":75,"model":"trinity-large-preview","company":"arcee","family":"Trinity","version":"Trinity Large","score":23.92},{"place":76,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":23.9},{"place":77,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":23.8},{"place":78,"model":"kanana-2-1.3b-base","company":"kakao","family":"Kanana","version":"Kanana 2","score":23.76},{"place":79,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":23.6},{"place":80,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":23.3},{"place":81,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":23.1},{"place":82,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":22.8},{"place":83,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.39},{"place":84,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":20.87},{"place":85,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":20.6},{"place":86,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":20.5},{"place":87,"model":"grok-3-mini","company":"xai","family":"Grok","version":"Grok 3","score":20.4},{"place":88,"model":"open-mixtral-8x22b-2404","company":"mistral","family":"Mixtral","version":"Mixtral","score":19.3},{"place":89,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":18.5},{"place":90,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":18.33},{"place":91,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":17.9},{"place":92,"model":"hermes-4.3-70b","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":17.9},{"place":93,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":17.1},{"place":94,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":16.83},{"place":95,"model":"o3-mini-2025-01-31","company":"openai","family":"o3","version":"o3","score":16.3},{"place":96,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":15.9},{"place":97,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":15},{"place":98,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.2},{"place":99,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":12.9},{"place":100,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":12.6},{"place":101,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":12.4},{"place":102,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":12.2},{"place":103,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":12.1},{"place":104,"model":"gpt-3.5-turbo-1106","company":"openai","family":"GPT","version":"GPT-3.5","score":11.9},{"place":105,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":11},{"place":106,"model":"magistral-small-2509","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":10.7},{"place":107,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":10.43},{"place":108,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":10.2},{"place":109,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":10.1},{"place":110,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":10.01},{"place":111,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":10},{"place":112,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":10},{"place":113,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":9.3},{"place":114,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":9.2},{"place":115,"model":"gemini-1.5-flash-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":9.2},{"place":116,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":9.1},{"place":117,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":9.1},{"place":118,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":9},{"place":119,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":8.9},{"place":120,"model":"trinity-mini","company":"arcee","family":"Trinity","version":"Trinity","score":8.9},{"place":121,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8.7},{"place":122,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":8.6},{"place":123,"model":"granite-4.0-h-small","company":"IBM","family":"Granite","version":"Granite 4.0","score":8.6},{"place":124,"model":"granite-4.1-30b","company":"IBM","family":"Granite","version":"Granite 4.1","score":6.81},{"place":125,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":6.3},{"place":126,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":6.3},{"place":127,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":6.1},{"place":128,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":6.1},{"place":129,"model":"hermes-4.3-36b-pyche","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":6},{"place":130,"model":"ministral-8b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":5.9},{"place":131,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":5.8},{"place":132,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":5.6},{"place":133,"model":"hermes-4.3-36b","company":"nousresearch","family":"Hermes","version":"Hermes 4.3","score":5.6},{"place":134,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":5.5},{"place":135,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":5.5},{"place":136,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":5.3},{"place":137,"model":"codestral-2501","company":"mistral","family":"Codestral","version":"Codestral","score":5.3},{"place":138,"model":"gemini-1.5-flash-8b-001","company":"google","family":"Gemini","version":"Gemini 1.5","score":5},{"place":139,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":4.82},{"place":140,"model":"ministral-3b-2410","company":"mistral","family":"Ministral","version":"Ministral","score":4.8},{"place":141,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.3},{"place":142,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":4},{"place":143,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":4},{"place":144,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":3.8},{"place":145,"model":"granite-4.1-3b","company":"IBM","family":"Granite","version":"Granite 4.1","score":3.68},{"place":146,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":3.3},{"place":147,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":2.8},{"place":148,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":2.2},{"place":149,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":2.2}]},{"id":"simpleqa-search","name":"SimpleQA (with search)","topic":"QA","description":"SimpleQA answered with web search / tool use enabled (agentic setting), not closed-book.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V3.2-Exp","top_percent":97.1,"top_model_id":"deepseek-v3.2-exp","top_generation":"DeepSeek V3.2","top_model_base":"DeepSeek V3.2-Exp","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":97.1},{"place":2,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":96.8},{"place":3,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":93.4},{"place":4,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":93.4},{"place":5,"model":"jan-v1","company":"menlo","family":"Jan","version":"Jan v1","score":91.1},{"place":6,"model":"jan-v1-2509","company":"menlo","family":"Jan","version":"Jan v1","score":90.7},{"place":7,"model":"perplexity-pro","company":"perplexity","family":"Perplexity","version":"Perplexity","score":90.6},{"place":8,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":86.5},{"place":9,"model":"jan-nano-128k","company":"menlo","family":"Jan","version":"Jan nano","score":83.2},{"place":10,"model":"jan-v1-edge","company":"menlo","family":"Jan","version":"Jan v1","score":83},{"place":11,"model":"jan-nano","company":"menlo","family":"Jan","version":"Jan nano","score":80.7},{"place":12,"model":"jan-nano-yarn","company":"menlo","family":"Jan","version":"Jan nano","score":79.7},{"place":13,"model":"qwen-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":69.14}]},{"id":"simpleqa-verified","name":"SimpleQA Verified","topic":"QA","description":"Verified SimpleQA variant for parametric knowledge accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":77.3,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":82,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":77.3},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":75.6},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.1},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":71.6},{"place":5,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":69.9},{"place":6,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":68.7},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68.3},{"place":8,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":65.4},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":64.3},{"place":10,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.9},{"place":11,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57},{"place":12,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.2},{"place":13,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.8},{"place":14,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.5},{"place":15,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":48.6},{"place":16,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46.6},{"place":17,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":46.2},{"place":18,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46.2},{"place":19,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":45.3},{"place":20,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":45},{"place":21,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":44.1},{"place":22,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":43.9},{"place":23,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":43.3},{"place":24,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":43.3},{"place":25,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":42.5},{"place":26,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":42.3},{"place":27,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":41.9},{"place":28,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":41.7},{"place":29,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":38.7},{"place":30,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":38.6},{"place":31,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":38.1},{"place":32,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":38.1},{"place":33,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":38},{"place":34,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":37.9},{"place":35,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":37.4},{"place":36,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":36.9},{"place":37,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":36.9},{"place":38,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":36.8},{"place":39,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":36},{"place":40,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":34.9},{"place":41,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":34.1},{"place":42,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":32.4},{"place":43,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":31.5},{"place":44,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":30.2},{"place":45,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":30.1},{"place":46,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":29.9},{"place":47,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":29.3},{"place":48,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":29.3},{"place":49,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":28.9},{"place":50,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":28.9},{"place":51,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":28.3},{"place":52,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":28.1},{"place":53,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":27.8},{"place":54,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":27.8},{"place":55,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":27.1},{"place":56,"model":"ling-3.0-flash-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":26.9},{"place":57,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":26},{"place":58,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26},{"place":59,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":25.4},{"place":60,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":24.5},{"place":61,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":24.2},{"place":62,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":24},{"place":63,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":23.7},{"place":64,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":23.1},{"place":65,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":22.1},{"place":66,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":22.1},{"place":67,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":21.6},{"place":68,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":21.2},{"place":69,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":21.2},{"place":70,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":20.8},{"place":71,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":20.6},{"place":72,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":19.5},{"place":73,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":19.3},{"place":74,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":19.1},{"place":75,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":18.9},{"place":76,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":17.1},{"place":77,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":16.5},{"place":78,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":16.1},{"place":79,"model":"ling-2.5-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":15.9},{"place":80,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":15.1},{"place":81,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":13.5},{"place":82,"model":"gpt-oss-120b-low","company":"openai","family":"GPT","version":"GPT-OSS","score":12.1},{"place":83,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":11.7},{"place":84,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":11.5},{"place":85,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":10.4},{"place":86,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":9.5},{"place":87,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":9},{"place":88,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":8},{"place":89,"model":"ling-3.0-tiny-base","company":"antgroup","family":"Ling","version":"Ling 3.0","score":7.2},{"place":90,"model":"ling-2.5-mini-base","company":"antgroup","family":"Ling","version":"Ling 2.5","score":7.1},{"place":91,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.4},{"place":92,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":5.9},{"place":93,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":5.5}]},{"id":"simplevqa","name":"SimpleVQA","topic":"General VQA","description":"Lightweight visual question answering set with everyday scenes.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.7-Plus","top_percent":81.7,"top_model_id":"qwen3.7-plus","top_generation":"Qwen3.7","top_model_base":"Qwen3.7 Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":100,"total_models":3854,"placements":[{"place":1,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":81.7},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":79.6},{"place":3,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":78.2},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.9},{"place":5,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75},{"place":6,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":74.5},{"place":7,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":74.3},{"place":8,"model":"sensenova-mars-32b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":74.14},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.06},{"place":10,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":73.4},{"place":11,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":73.2},{"place":12,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":73.2},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":73.1},{"place":14,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":72.7},{"place":15,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":72.5},{"place":16,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":72.4},{"place":17,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":71.5},{"place":18,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.4},{"place":19,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":71.3},{"place":20,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":71.3},{"place":21,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":71.2},{"place":22,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":71.2},{"place":23,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":71.1},{"place":24,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.5},{"place":25,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":70.3},{"place":26,"model":"sensenova-mars-8b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":70.19},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":69.9},{"place":28,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":69.7},{"place":29,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.7},{"place":30,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":69.4},{"place":31,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":69.4},{"place":32,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":68.4},{"place":33,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.19},{"place":34,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":67.64},{"place":35,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.3},{"place":36,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":67.3},{"place":37,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":67.2},{"place":38,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":67.2},{"place":39,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.1},{"place":40,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":66.6},{"place":41,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.7},{"place":42,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.4},{"place":43,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":65.4},{"place":44,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":65.3},{"place":45,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":64.07},{"place":46,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":63.57},{"place":47,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":63.4},{"place":48,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":63.2},{"place":49,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.37},{"place":50,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":62.2},{"place":51,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62},{"place":52,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":61.8},{"place":53,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.7},{"place":54,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":61.7},{"place":55,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.3},{"place":56,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.3},{"place":57,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":61.1},{"place":58,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":59.92},{"place":59,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":58.9},{"place":60,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.6},{"place":61,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.3},{"place":62,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":58.2},{"place":63,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.6},{"place":64,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":57.4},{"place":65,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.9},{"place":66,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.8},{"place":67,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":56.8},{"place":68,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":56.7},{"place":69,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":56.5},{"place":70,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.1},{"place":71,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":56.1},{"place":72,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56},{"place":73,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":56},{"place":74,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":55.84},{"place":75,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":55.8},{"place":76,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":55.8},{"place":77,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.48},{"place":78,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":54.4},{"place":79,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":54.4},{"place":80,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.3},{"place":81,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":54.14},{"place":82,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.1},{"place":83,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":53.1},{"place":84,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":53},{"place":85,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.9},{"place":86,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":52.8},{"place":87,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":52.75},{"place":88,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.7},{"place":89,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":52.3},{"place":90,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.24},{"place":91,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.2},{"place":92,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.2},{"place":93,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":51.73},{"place":94,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.2},{"place":95,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":50.81},{"place":96,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":50.2},{"place":97,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":50.1},{"place":98,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48.8},{"place":99,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":48.57},{"place":100,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":48.1},{"place":101,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48},{"place":102,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":47.9},{"place":103,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":47.88},{"place":104,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.84},{"place":105,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":46.12},{"place":106,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":46},{"place":107,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.9},{"place":108,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":45.25},{"place":109,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":45},{"place":110,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":44.99},{"place":111,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":44.42},{"place":112,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":44},{"place":113,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.6},{"place":114,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.4},{"place":115,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.94},{"place":116,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":42.23},{"place":117,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":41.9},{"place":118,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":40.87},{"place":119,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":40.77},{"place":120,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40.7},{"place":121,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.7},{"place":122,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":39},{"place":123,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.5},{"place":124,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":36.68},{"place":125,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":35.45},{"place":126,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":35.4},{"place":127,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.2},{"place":128,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":33.7},{"place":129,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":33},{"place":130,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":31.51},{"place":131,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.3},{"place":132,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":30.5},{"place":133,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.4},{"place":134,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30.4},{"place":135,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":29.2},{"place":136,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.3},{"place":137,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":26},{"place":138,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":20.7},{"place":139,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":12.1}]},{"id":"simplevqa-ds","name":"SimpleVQA-DS","topic":"General VQA","description":"SimpleVQA variant curated by DeepSeek with everyday image question answering tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.5-VL-Thinking","top_percent":61.34,"top_model_id":"seed1.5-vl-thinking","top_generation":"Seed 1.5","top_model_base":"Seed 1.5 VL","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":61.34},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.09},{"place":3,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":55.8},{"place":4,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":52.19}]},{"id":"simplevqa-with-tools","name":"SimpleVQA (With Tools)","topic":"Visual factuality","description":"SimpleVQA visual factuality benchmark evaluated with tool access.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Step 3.7 Flash","top_percent":79.16,"top_model_id":"step-3.7-flash","top_generation":"Step 3.7 Flash","top_model_base":"Step 3.7 Flash","top_model_family":"Step","top_company":"stepfun","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":79.16},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":79.11},{"place":3,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":78.24},{"place":4,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":78.2},{"place":5,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":77.8},{"place":6,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":75},{"place":7,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":73.6},{"place":8,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":73.3},{"place":9,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":71.9},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.3},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.7},{"place":12,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":52.3}]},{"id":"siqa","name":"Social Interaction QA (SIQA)","topic":"Social commonsense QA","description":"Social Interaction QA benchmark evaluating social commonsense and situational reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen 14B","top_percent":78.1,"top_model_id":"qwen-14b","top_generation":"Qwen","top_model_base":"Qwen 14B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":58,"total_models":3854,"placements":[{"place":1,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":78.1},{"place":2,"model":"stablebeluga2-70b","company":"stabilityai","family":"StableBeluga","version":"StableBeluga2","score":78.1},{"place":3,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":77.9},{"place":4,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":73},{"place":5,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":72.8},{"place":6,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":70.4},{"place":7,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":69.9},{"place":8,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":69.4},{"place":9,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":68.22},{"place":10,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":64.8},{"place":11,"model":"chatglm2-6b","company":"zai","family":"ChatGLM","version":"ChatGLM2","score":64.3},{"place":12,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":61.2},{"place":13,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":60.5},{"place":14,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":57.8},{"place":15,"model":"qwen-1.8b","company":"qwen","family":"Qwen","version":"Qwen","score":56.1},{"place":16,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":54.9},{"place":17,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":54.8},{"place":18,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":54.71},{"place":19,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":53.8},{"place":20,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":53.6},{"place":21,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":53.4},{"place":22,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":52.5},{"place":23,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":52.3},{"place":24,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":52.25},{"place":25,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":51.89},{"place":26,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":51.69},{"place":27,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":51.59},{"place":28,"model":"chinchilla-70b","company":"google","family":"Chinchilla","version":"Chinchilla","score":51.3},{"place":29,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":51.23},{"place":30,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":50.97},{"place":31,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":50.8},{"place":32,"model":"gopher-280b","company":"google","family":"Gopher","version":"Gopher","score":50.6},{"place":33,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":50.41},{"place":34,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":50.4},{"place":35,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":50.4},{"place":36,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":49.44},{"place":37,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":49.4},{"place":38,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":48.9},{"place":39,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":48.77},{"place":40,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":48.72},{"place":41,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":48.52},{"place":42,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":48.5},{"place":43,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":48.5},{"place":44,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":48.41},{"place":45,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":47.34},{"place":46,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":47.2},{"place":47,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":47.13},{"place":48,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":46.32},{"place":49,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":46.1},{"place":50,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":46.01},{"place":51,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":45.5},{"place":52,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":44.88},{"place":53,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":44.6},{"place":54,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":44.4},{"place":55,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":44.32},{"place":56,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":44.3},{"place":57,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":44.11},{"place":58,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":43.1},{"place":59,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":42.89},{"place":60,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":42.7},{"place":61,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":42.32},{"place":62,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41},{"place":63,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":40.6},{"place":64,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":39.6},{"place":65,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.8}]},{"id":"skillsbench","name":"SkillsBench","topic":"Agent skills","description":"SkillsBench agentic tasks; Qwen reports avg of 5 runs on the 78-task self-contained subset (API-dependent tasks excluded).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":73.5,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":61,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.5},{"place":2,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":71.3},{"place":3,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":68.7},{"place":4,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":67.8},{"place":5,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.7},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":66.5},{"place":7,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":66.4},{"place":8,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":65},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":64.6},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.7},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":63.6},{"place":12,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":63.3},{"place":13,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":62.9},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":62.5},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":61.6},{"place":16,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.5},{"place":17,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":61.3},{"place":18,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":61.1},{"place":19,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":60.4},{"place":20,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":59.4},{"place":21,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":59.2},{"place":22,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":56.4},{"place":23,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":56.2},{"place":24,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":55.63},{"place":25,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":55.6},{"place":26,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":55.3},{"place":27,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":54.9},{"place":28,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":54.4},{"place":29,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":54.4},{"place":30,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53.5},{"place":31,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":53.2},{"place":32,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":53.19},{"place":33,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":53.1},{"place":34,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":52.8},{"place":35,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.3},{"place":36,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":51.9},{"place":37,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":51.9},{"place":38,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.1},{"place":39,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":50.03},{"place":40,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":49.59},{"place":41,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.53},{"place":42,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":48.9},{"place":43,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":48.2},{"place":44,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":47.5},{"place":45,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":47.2},{"place":46,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":46.6},{"place":47,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":45.7},{"place":48,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":45.4},{"place":49,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":45.3},{"place":50,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":44.8},{"place":51,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":44.8},{"place":52,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.7},{"place":53,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":44.3},{"place":54,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":43.7},{"place":55,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":43},{"place":56,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":42.6},{"place":57,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":42.3},{"place":58,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":42.1},{"place":59,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":42},{"place":60,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40.5},{"place":61,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":40},{"place":62,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":39.7},{"place":63,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":37.2},{"place":64,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.58},{"place":65,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35.4},{"place":66,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.4},{"place":67,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":30},{"place":68,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":29.1},{"place":69,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":28.9},{"place":70,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":28.7},{"place":71,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":28.4},{"place":72,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.2},{"place":73,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":26.4},{"place":74,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":24.9},{"place":75,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":23.6},{"place":76,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":20.3},{"place":77,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":12.3},{"place":78,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":11.9},{"place":79,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":4.4}]},{"id":"skillsbench-v1.1","name":"SkillsBench v1.1","topic":"Agent skills","description":"Public SkillsBench v1.1 benchmark (87 tasks), average score over three runs per task.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":73.5,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.5},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.9},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":70.2},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":65.1},{"place":5,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":61.2}]},{"id":"slake","name":"SLAKE","topic":"Medical VQA","description":"Semantically-Labeled Knowledge-Enhanced medical visual question answering benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":90.8,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":39,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.8},{"place":2,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":87.6},{"place":3,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":86.9},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.6},{"place":5,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":85.9},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":85.1},{"place":7,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":84.7},{"place":8,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":83.2},{"place":9,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":83},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82.9},{"place":11,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":82.8},{"place":12,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":82.4},{"place":13,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":81.6},{"place":14,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.6},{"place":15,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":81.3},{"place":16,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80},{"place":17,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.9},{"place":18,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79},{"place":19,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.7},{"place":20,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":78},{"place":21,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":76.9},{"place":22,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.4},{"place":23,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.1},{"place":24,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75.9},{"place":25,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.4},{"place":26,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.6},{"place":27,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":73.1},{"place":28,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":70.6},{"place":29,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":70.5},{"place":30,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":70.3},{"place":31,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.8},{"place":32,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.9},{"place":33,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":65},{"place":34,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.6},{"place":35,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":62},{"place":36,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.1},{"place":37,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":57},{"place":38,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.7},{"place":39,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":41}]},{"id":"smolinstruct","name":"SmolInstruct","topic":"Small molecule understanding","description":"Small molecule instruction-following and understanding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-S1-Pro","top_percent":74.8,"top_model_id":"intern-s1-pro","top_generation":"Intern-S1","top_model_base":"Intern-S1-Pro","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":74.8},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":58.3},{"place":3,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":53.5},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":48.2},{"place":5,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.6}]},{"id":"sob","name":"SOB (Structured Output Benchmark)","topic":"Structured output","description":"Structured Output Benchmark: extract values into a JSON schema from text, images and audio (5,324 records); value accuracy over exact field matches.","url":"https://interfaze.ai","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Interfaze 1.1 Lite","top_percent":81.5,"top_model_id":"interfaze-1.1-lite","top_generation":"Interfaze 1.1","top_model_base":"Interfaze 1.1 Lite","top_model_family":"Interfaze","top_company":"interfaze","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"interfaze-1.1-lite","company":"interfaze","family":"Interfaze","version":"Interfaze 1.1","score":81.5},{"place":2,"model":"interfaze","company":"interfaze","family":"Interfaze","version":"Interfaze 1","score":80.5},{"place":3,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.9},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":77.3}]},{"id":"socialiqa","name":"SocialIQA","topic":"Social commonsense","description":"Social interaction commonsense QA.","url":"https://leaderboard.allenai.org/socialiqa","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3 8B Base","top_percent":83.3,"top_model_id":"qwen3-8b-base","top_generation":"Qwen3","top_model_base":"Qwen3 8B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":83.3},{"place":2,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":83.1},{"place":3,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.9},{"place":4,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":81.1},{"place":5,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":80.7},{"place":6,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":80.3},{"place":7,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":80.3},{"place":8,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":79.8},{"place":9,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":77.5},{"place":10,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":77},{"place":11,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":76.3},{"place":12,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":54.9},{"place":13,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":51.8},{"place":14,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":50.87},{"place":15,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":49.9},{"place":16,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":49.7},{"place":17,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":49.03},{"place":18,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":48.9},{"place":19,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":47.7},{"place":20,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":46.1},{"place":21,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":45.6}]},{"id":"sparbench","name":"SPAR-Bench","topic":"Spatial reasoning","description":"Spatial perception and reasoning benchmark derived from the SPAR dataset (single- and multi-view).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2","top_percent":55.07,"top_model_id":"gpt-5.2","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":55.07},{"place":2,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":51.82},{"place":3,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.79},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":48.74},{"place":5,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":45.68},{"place":6,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":44.76},{"place":7,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":28.5}]},{"id":"spatialsense-vqa","name":"SpatialSense VQA","topic":"Spatial reasoning","description":"SpatialSense spatial-relation recognition posed as VQA (as used in Gemma/PaliGemma evaluations).","url":"https://arxiv.org/abs/1908.02660","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"T5Gemma 2 4B-4B","top_percent":51.7,"top_model_id":"t5gemma-2-4b-4b","top_generation":"T5Gemma 2","top_model_base":"T5Gemma 2 4B-4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":51.7},{"place":2,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":50.4},{"place":3,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":50.2}]},{"id":"spatialviz","name":"SpatialViz","topic":"Mental visualization","description":"Mental visualization benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2","top_percent":65.8,"top_model_id":"gpt-5.2","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":65.8},{"place":2,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":65.3},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":63.2},{"place":4,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":52.5},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":51.3},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":46.6},{"place":7,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43},{"place":8,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":41.6},{"place":9,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":38.5},{"place":10,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.4},{"place":11,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":38.2},{"place":12,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":35.7},{"place":13,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":35.2},{"place":14,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":34.8},{"place":15,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":31.1}]},{"id":"speechrole","name":"SpeechRole","topic":"Spoken role-play","description":"SpeechRole: speech role-playing agent benchmark (aggregate judge score, unbounded scale).","url":"https://arxiv.org/abs/2508.02013","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Gemini 3.1 Pro","top_percent":124.2,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":124.2},{"place":2,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":123.5},{"place":3,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":119.8}]},{"id":"spider","name":"Spider","topic":"Text-to-SQL","description":"Complex text-to-SQL benchmark over cross-domain databases.","url":"https://yale-lily.github.io/spider","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":83.9,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":83.9},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":82.7},{"place":3,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":82.49},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.4},{"place":5,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":81.79},{"place":6,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":81.37},{"place":7,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":81.04},{"place":8,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":80.7},{"place":9,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":80.58},{"place":10,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":79.18},{"place":11,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":77.55},{"place":12,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":76.76},{"place":13,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":76.43},{"place":14,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":75.78},{"place":15,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":72.8},{"place":16,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":67.1},{"place":17,"model":"llama-3-70b","company":"meta","family":"Llama","version":"Llama 3","score":67.1},{"place":18,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":63.5},{"place":19,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":61.2},{"place":20,"model":"deepseek-coder-33b","company":"deepseek","family":"DeepSeek Coder","version":"DeepSeek Coder","score":60},{"place":21,"model":"codestral-mamba","company":"mistral","family":"Codestral","version":"Codestral","score":58.8},{"place":22,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":50.8},{"place":23,"model":"codegemma-1.1-7b","company":"google","family":"CodeGemma","version":"CodeGemma","score":46.3},{"place":24,"model":"codellama-70b","company":"meta","family":"CodeLlama","version":"CodeLlama","score":37},{"place":25,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":29.3}]},{"id":"spider-2.0-lite","name":"Spider 2.0-Lite","topic":"Text-to-SQL","description":"Spider 2.0-Lite enterprise text-to-SQL over real schemas, scored by executing the query (Interfaze reports the 135-task SQLite subset).","url":"https://spider2-sql.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Interfaze","top_percent":52.9,"top_model_id":"interfaze","top_generation":"Interfaze 1","top_model_base":"Interfaze","top_model_family":"Interfaze","top_company":"interfaze","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"interfaze","company":"interfaze","family":"Interfaze","version":"Interfaze 1","score":52.9},{"place":2,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":49.6},{"place":3,"model":"interfaze-1.1-lite","company":"interfaze","family":"Interfaze","version":"Interfaze 1.1","score":48.9},{"place":4,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":45.9},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":45.2},{"place":6,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":26.7}]},{"id":"spiral-bench","name":"Spiral-Bench","topic":"Safety / sycophancy","description":"A LLM-judged benchmark measuring sycophancy and delusion reinforcement.","url":"https://eqbench.com/spiral-bench.html","leaderboard":"https://eqbench.com/spiral-bench.html","github":"https://github.com/EQ-bench","paper":"https://arxiv.org/abs/2312.06281","metric":"percent","stars":"","top_model":"GPT-5","top_percent":87,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":87},{"place":2,"model":"o3","company":"openai","family":"o3","version":"o3","score":86.1},{"place":3,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":81.4},{"place":4,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":73.3},{"place":5,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73},{"place":6,"model":"gpt-5-chat-2025-10-03","company":"openai","family":"GPT","version":"GPT-5","score":70.8},{"place":7,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.3},{"place":8,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":70.2},{"place":9,"model":"o3","company":"openai","family":"o3","version":"o3","score":63.4},{"place":10,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":57.5},{"place":11,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":57.4},{"place":12,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":57.2},{"place":13,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":53.6},{"place":14,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.1},{"place":15,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":48.1},{"place":16,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":47.7},{"place":17,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":43.5},{"place":18,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":42.6},{"place":19,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":42.3},{"place":20,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":38.7},{"place":21,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":38.2},{"place":22,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":37.5},{"place":23,"model":"gpt-5-chat","company":"openai","family":"GPT","version":"GPT-5","score":36.6},{"place":24,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":36.5},{"place":25,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":32.1},{"place":26,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":30.8},{"place":27,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":28.3},{"place":28,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":25.3},{"place":29,"model":"chatgpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":25.2},{"place":30,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":25.2},{"place":31,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":20.4},{"place":32,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":15},{"place":33,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":14.2}]},{"id":"spreadsheetbench-2","name":"SpreadsheetBench 2","topic":"Spreadsheet manipulation","description":"Second version of SpreadsheetBench real-world spreadsheet manipulation tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":35.8,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":35.8},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":34.9},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":34.8},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":34.7},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":33.6},{"place":6,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":33},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":32.7},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":32.4},{"place":9,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":32.1},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":31.6},{"place":11,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":31.5},{"place":12,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":29.3},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":29.1},{"place":14,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":28.35},{"place":15,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":28.1},{"place":16,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":26.79},{"place":17,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":26.48},{"place":18,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":24.92},{"place":19,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":23.99},{"place":20,"model":"ling-3.0-flash-fin","company":"antgroup","family":"Ling","version":"Ling 3.0","score":21.81},{"place":21,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":19.94},{"place":22,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":16.82}]},{"id":"spreadsheetbench-v1","name":"SpreadSheetBench v1","topic":"Spreadsheet manipulation","description":"Real-world spreadsheet manipulation tasks (v1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniMax M3","top_percent":89.4,"top_model_id":"minimax-m3","top_generation":"MiniMax M3","top_model_base":"MiniMax M3","top_model_family":"MiniMax","top_company":"minimax","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":89.4},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":89.3},{"place":3,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":88.5},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":88.1},{"place":5,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":87.5},{"place":6,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":87.25},{"place":7,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":87},{"place":8,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":87},{"place":9,"model":"ling-3.0-flash-fin","company":"antgroup","family":"Ling","version":"Ling 3.0","score":86.5},{"place":10,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":86.3},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":86.25},{"place":12,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":85.2},{"place":13,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84.9},{"place":14,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":84.9},{"place":15,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":84.5},{"place":16,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":84},{"place":17,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":83.75},{"place":18,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":81.75},{"place":19,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":80.2},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":56.1},{"place":21,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":55.36},{"place":22,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":40.08},{"place":23,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":35.29},{"place":24,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":34},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":27.7}]},{"id":"spreadsheetbench-verified","name":"SpreadsheetBench-Verified","topic":"Spreadsheet manipulation","description":"Verified subset of SpreadsheetBench real-world spreadsheet manipulation tasks.","url":"https://spreadsheetbench.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":82.4,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82.4},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.8},{"place":3,"model":"ernie-5.1","company":"baidu","family":"ERNIE","version":"ERNIE 5.1","score":72.5},{"place":4,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67}]},{"id":"sqa","name":"SQA","topic":"Table QA","description":"Sequential QA over tables (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":91,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":91},{"place":2,"model":"o3","company":"openai","family":"o3","version":"o3","score":86.7},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.5},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":85.5},{"place":5,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":83.6},{"place":6,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":82.1},{"place":7,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":82.1},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":81.3},{"place":9,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":81.1},{"place":10,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":79.1}]},{"id":"squad-v1.1","name":"SQuAD v1.1","topic":"Reading comprehension","description":"Extractive QA from Wikipedia articles.","url":"https://github.com/rajpurkar/SQuAD-explorer","leaderboard":"","github":"","paper":"","metric":"percent","stars":"566","top_model":"OLMo 3 7B","top_percent":93.5,"top_model_id":"olmo-3-7b","top_generation":"OLMo 3","top_model_base":"OLMo 3 7B","top_model_family":"OLMo","top_company":"allenai","top_open_source":1,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":93.5},{"place":2,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":93.4},{"place":3,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":92.1},{"place":4,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":91.5},{"place":5,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":90.3},{"place":6,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":89.6},{"place":7,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":89.6},{"place":8,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":89.3},{"place":9,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":89.2},{"place":10,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":89.2},{"place":11,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":88.8},{"place":12,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":87},{"place":13,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":85.6},{"place":14,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":81.8},{"place":15,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":77},{"place":16,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":76.4}]},{"id":"squad-v2.0","name":"SQuAD v2.0","topic":"Reading comprehension","description":"Like v1.1 with unanswerable questions.","url":"https://github.com/rajpurkar/SQuAD-explorer","leaderboard":"","github":"","paper":"","metric":"percent","stars":"566","top_model":"Ling 2.6 1T Base","top_percent":92.98,"top_model_id":"ling-2.6-1t-base","top_generation":"Ling 2.6","top_model_base":"Ling 2.6 1T Base","top_model_family":"Ling","top_company":"antgroup","top_open_source":1,"lower_is_better":false,"bench_models":35,"total_models":3854,"placements":[{"place":1,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":92.98},{"place":2,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":91.29},{"place":3,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":90.8},{"place":4,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":90.65},{"place":5,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":90},{"place":6,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.51},{"place":7,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":89.27},{"place":8,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":88.81},{"place":9,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":86.5},{"place":10,"model":"llada2.0-flash-preview","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":85.61},{"place":11,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":85.3},{"place":12,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.21},{"place":13,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":85.13},{"place":14,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":84.51},{"place":15,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":81.32},{"place":16,"model":"mapika-decider-4b","company":"mapika","family":"Decider","version":"Decider","score":76},{"place":17,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":75.56},{"place":18,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":74},{"place":19,"model":"mapika-decider-2b","company":"mapika","family":"Decider","version":"Decider","score":67.7},{"place":20,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":66.99},{"place":21,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":44.58},{"place":22,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":42.13},{"place":23,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":41.32},{"place":24,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":40.88},{"place":25,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":31.15},{"place":26,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":30.98},{"place":27,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":30.43},{"place":28,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":27.05},{"place":29,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":25.2},{"place":30,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":23.11},{"place":31,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":22.54},{"place":32,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":19.61},{"place":33,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":15.01},{"place":34,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":13.12},{"place":35,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":12.53}]},{"id":"sre-bench","name":"SRE-Bench","topic":"Cybersecurity","description":"Software reverse engineering of binaries without source code (single-attempt solve rate).","url":"https://arxiv.org/abs/2608.11469v1","leaderboard":"https://arxiv.org/abs/2608.11469v1","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":88,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":88},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":55.9},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":12.5}]},{"id":"sroie-f1","name":"SROIE (F1)","topic":"OCR","description":"SROIE text grounding and recognition, F1 mean.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":68.1,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":68.1},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":62.1},{"place":3,"model":"pp-ocrv5","company":"paddlepaddle","family":"PP-OCR","version":"PP-OCRv5","score":58.6},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":44.8},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":43.3},{"place":6,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":40.3}]},{"id":"streamingbench","name":"StreamingBench","topic":"Streaming video","description":"Streaming video understanding benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":84.4,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":84.4},{"place":2,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":77.3},{"place":3,"model":"realtime-venus-omni","company":"antgroup","family":"Realtime-Venus","version":"Realtime-Venus","score":70.2},{"place":4,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":68},{"place":5,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":67.9},{"place":6,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":64.3},{"place":7,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":63.3},{"place":8,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":60.8},{"place":9,"model":"livestar-8b","company":"livestar","family":"LiveStar","version":"LiveStar","score":60.2},{"place":10,"model":"video-salmonn-2-plus-7b","company":"tsinghua","family":"video-SALMONN","version":"video-SALMONN 2+","score":59.9},{"place":11,"model":"av-flamingo-7b","company":"nvidia","family":"Audio Flamingo","version":"AV-Flamingo","score":58.5},{"place":12,"model":"mmduet2-3b","company":"pku","family":"MMDuet","version":"MMDuet2","score":58.1},{"place":13,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57},{"place":14,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.5}]},{"id":"strongreject","name":"StrongREJECT","topic":"Safety (jailbreak refusal)","description":"StrongREJECT jailbreak benchmark; score = share of forbidden prompts safely handled.","url":"https://arxiv.org/abs/2402.10260","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2.6 Thinking","top_percent":99.8,"top_model_id":"kimi-k2.6-thinking","top_generation":"Kimi K2.6","top_model_base":"Kimi K2.6","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":99.8},{"place":2,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":99.5},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":99.4},{"place":4,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":99.4},{"place":5,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":99.3},{"place":6,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":98.7},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":98.7},{"place":8,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":98.7},{"place":9,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":98.6},{"place":10,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":98.6},{"place":11,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.6},{"place":12,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":98.5},{"place":13,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":98.5},{"place":14,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":98.4},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":98},{"place":16,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":97.6},{"place":17,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":97.4}]},{"id":"structeval-t","name":"StructEval-T","topic":"Structured output","description":"Text-only subset of StructEval: generating and converting structured formats such as JSON, YAML, CSV.","url":"https://structeval.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nemotron-3.5-Bolt-E4B","top_percent":80.4,"top_model_id":"nemotron-3.5-bolt-e4b","top_generation":"Nemotron 3.5","top_model_base":"Nemotron-3.5 Bolt E4B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":80.4},{"place":2,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":79.99},{"place":3,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":79.27},{"place":4,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":77.28},{"place":5,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.38},{"place":6,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.01},{"place":7,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63.5},{"place":8,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":16.54}]},{"id":"sunrgbd","name":"SUNRGBD","topic":"3D scene understanding","description":"SUN RGB-D benchmark for indoor scene understanding from RGB-D imagery.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 Mini (minimal)","top_percent":45.8,"top_model_id":"gpt-5-mini-minimal","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":45.8},{"place":2,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":42.2},{"place":3,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":41},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.3},{"place":5,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":38.1},{"place":6,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":37},{"place":7,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.2},{"place":8,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.2},{"place":9,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":35.4},{"place":10,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":34.9},{"place":11,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":34.9},{"place":12,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":34.7},{"place":13,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":33.8},{"place":14,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.4},{"place":15,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":32.5},{"place":16,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.7},{"place":17,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.6},{"place":18,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28},{"place":19,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.1}]},{"id":"superchem","name":"SuperChem","topic":"Chemistry reasoning","description":"Chemistry reasoning benchmark evaluating text-based chemical knowledge and problem solving.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":76.7,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":76.7},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.6},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.4},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":69.2},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":66.9},{"place":6,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":66.9},{"place":7,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":66.4},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":66.2},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":63.2},{"place":10,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62},{"place":11,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":61.9},{"place":12,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.2},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":61.1},{"place":14,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":60.5},{"place":15,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":60.2},{"place":16,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":59.8},{"place":17,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":58.5},{"place":18,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":58},{"place":19,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":56.6},{"place":20,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":55},{"place":21,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":55},{"place":22,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":54.9},{"place":23,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":54.4},{"place":24,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":52.6},{"place":25,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.8},{"place":26,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":51.6},{"place":27,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":51.4},{"place":28,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":48},{"place":29,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":47},{"place":30,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.2},{"place":31,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":34.8},{"place":32,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32.4},{"place":33,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":29.1},{"place":34,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":16.2}]},{"id":"superglue","name":"SuperGLUE","topic":"Multi-task NLU","description":"Suite of harder NLU tasks beyond GLUE.","url":"https://super.gluebenchmark.com/","leaderboard":"https://super.gluebenchmark.com/leaderboard","github":"","paper":"","metric":"percent","stars":"","top_model":"Hairuo","top_percent":91.4,"top_model_id":"hairuo","top_generation":"Hairuo","top_model_base":"Hairuo","top_model_family":"Hairuo","top_company":"generic","top_open_source":1,"lower_is_better":false,"bench_models":29,"total_models":3854,"placements":[{"place":1,"model":"hairuo","company":"generic","family":"Hairuo","version":"Hairuo","score":91.4},{"place":2,"model":"vega-v2","company":"jd","family":"Vega","version":"Vega v2","score":91.3},{"place":3,"model":"st-moe-32b","company":"google","family":"ST","version":"ST-MoE-32B","score":91.2},{"place":4,"model":"turing-nlr-v5","company":"microsoft","family":"Turing","version":"Turing NLR v5","score":90.9},{"place":5,"model":"ernie-3.0","company":"baidu","family":"ERNIE","version":"ERNIE 3.0","score":90.6},{"place":6,"model":"hairuo","company":"generic","family":"Hairuo","version":"Hairuo","score":90.6},{"place":7,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":90.4},{"place":8,"model":"t5-plus-udg-single-model-google-brain","company":"google","family":"T5","version":"T5 + UDG, Single Model (Google Brain)","score":90.4},{"place":9,"model":"deberta-turingnlrv4","company":"microsoft","family":"DeBERTa","version":"DeBERTa / TuringNLRv4","score":90.3},{"place":10,"model":"t5","company":"google","family":"T5","version":"T5","score":89.3},{"place":11,"model":"frozen-t5-1.1-plus-spot","company":"google","family":"Frozen","version":"Frozen T5 1.1 + SPoT","score":89.2},{"place":12,"model":"nezha-plus","company":"huawei","family":"NEZHA","version":"NEZHA-Plus","score":86.7},{"place":13,"model":"pai-albert","company":"alibaba","family":"PAI","version":"PAI Albert","score":86.1},{"place":14,"model":"roberta-icets","company":"infosys","family":"RoBERTa","version":"RoBERTa-iCETS","score":86},{"place":15,"model":"roberta-ensemble","company":"tencent","family":"RoBERTa","version":"RoBERTa (ensemble)","score":85.9},{"place":16,"model":"roberta-mtl-adv","company":"zhuiyi","family":"RoBERTa","version":"RoBERTa-mtl-adv","score":85.7},{"place":17,"model":"roberta","company":"meta","family":"RoBERTa","version":"RoBERTa","score":84.6},{"place":18,"model":"ailabs-team-transformers","company":"unknown","family":"AILabs","version":"AILabs Team, Transformers","score":82.6},{"place":19,"model":"fsl-plus-plus-albert-few-shot-32-examples","company":"unknown","family":"FSL++(ALBERT)","version":"FSL++(ALBERT)-Few-Shot(32 Examples)","score":77.7},{"place":20,"model":"text-to-text-petl","company":"berkeley","family":"Text","version":"Text to Text PETL","score":77},{"place":21,"model":"install-albert-few-shot-32examples","company":"casia","family":"INSTALL(ALBERT)","version":"INSTALL(ALBERT)-few-shot(32examples)","score":76.6},{"place":22,"model":"adapet-albert-few-shot","company":"unc","family":"ADAPET","version":"ADAPET (ALBERT) - few-shot","score":76},{"place":23,"model":"ipet-albert-few-shot-32-examples","company":"lmu","family":"iPET","version":"iPET (ALBERT) - Few-Shot (32 Examples)","score":75.4},{"place":24,"model":"snorkel-superglue-v1.9","company":"stanford","family":"Snorkel","version":"Snorkel [SuperGLUE v1.9]","score":74.5},{"place":25,"model":"bort-alexa-ai","company":"amazon","family":"Bort","version":"Bort (Alexa AI)","score":74.1},{"place":26,"model":"bert-mtl","company":"ibm","family":"BERT","version":"BERT-mtl","score":73.5},{"place":27,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":71.8},{"place":28,"model":"bert-plus-plus","company":"nyu","family":"BERT++","version":"BERT++","score":71.5},{"place":29,"model":"select-step-by-step","company":"unknown","family":"select","version":"select-step-by-step","score":51.9},{"place":30,"model":"warp-albert-xxl-v2-few-shot-32-examples","company":"yerevann","family":"WARP","version":"WARP (ALBERT-XXL-V2) - Few-Shot (32 Examples)","score":48.7}]},{"id":"supergpqa","name":"SuperGPQA","topic":"Graduate-level QA","description":"Harder GPQA variant assessing advanced graduate-level reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":76.6,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":149,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.6},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":75.3},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74},{"place":4,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":73.9},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":73.8},{"place":6,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":73.6},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":72.7},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":72.7},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":72.5},{"place":10,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":71.6},{"place":11,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":71.4},{"place":12,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":71.3},{"place":13,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":70.8},{"place":14,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70.6},{"place":15,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.4},{"place":16,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.9},{"place":17,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":69.6},{"place":18,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":69.2},{"place":19,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":68.7},{"place":20,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":68.5},{"place":21,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":68},{"place":22,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":67.9},{"place":23,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":67.9},{"place":24,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":67.5},{"place":25,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":67.4},{"place":26,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":67.3},{"place":27,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.1},{"place":28,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":66.8},{"place":29,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":66.8},{"place":30,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":66.4},{"place":31,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":66.4},{"place":32,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.1},{"place":33,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":66},{"place":34,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.7},{"place":35,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.6},{"place":36,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.5},{"place":37,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":64.9},{"place":38,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.9},{"place":39,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.9},{"place":40,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":64.8},{"place":41,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64.7},{"place":42,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":64.6},{"place":43,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":64.2},{"place":44,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":63.9},{"place":45,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.71},{"place":46,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.4},{"place":47,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.37},{"place":48,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":62.97},{"place":49,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":62.6},{"place":50,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62.23},{"place":51,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":61.6},{"place":52,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.4},{"place":53,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":61.37},{"place":54,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":61.23},{"place":55,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":60.8},{"place":56,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":60.59},{"place":57,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":60.5},{"place":58,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":60.41},{"place":59,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":60.34},{"place":60,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":59.8},{"place":61,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":58.9},{"place":62,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":58.8},{"place":63,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":58.6},{"place":64,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":58.32},{"place":65,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.2},{"place":66,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.8},{"place":67,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":57.63},{"place":68,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":57.22},{"place":69,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":57.2},{"place":70,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":57.2},{"place":71,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":56.8},{"place":72,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":56.5},{"place":73,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.4},{"place":74,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":55.7},{"place":75,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":55},{"place":76,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":54.9},{"place":77,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":54.6},{"place":78,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":54.4},{"place":79,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":54.1},{"place":80,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.1},{"place":81,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53.9},{"place":82,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":53.7},{"place":83,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.4},{"place":84,"model":"nanbeige4-3b-thinking-2511","company":"boss","family":"Nanbeige","version":"Nanbeige4","score":53.2},{"place":85,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.1},{"place":86,"model":"deepseek-v4.1-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":53.1},{"place":87,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":53.1},{"place":88,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.9},{"place":89,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.8},{"place":90,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":52},{"place":91,"model":"hy3-preview-base","company":"tencent","family":"HY","version":"Hy3","score":51.6},{"place":92,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":51.1},{"place":93,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":50.8},{"place":94,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":50.2},{"place":95,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":49.64},{"place":96,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":49.6},{"place":97,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":48.7},{"place":98,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":48.5},{"place":99,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.8},{"place":100,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":47.65},{"place":101,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":46.8},{"place":102,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":46.7},{"place":103,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":46.6},{"place":104,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46.5},{"place":105,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":46.17},{"place":106,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46.1},{"place":107,"model":"seed1.6","company":"bytedance","family":"Seed","version":"Seed 1.6","score":45.08},{"place":108,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":45},{"place":109,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":44.72},{"place":110,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.7},{"place":111,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.5},{"place":112,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":44.3},{"place":113,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":44.3},{"place":114,"model":"qwen3-235b-a22b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":44.06},{"place":115,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":44.06},{"place":116,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":43.6},{"place":117,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":43.6},{"place":118,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.6},{"place":119,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":43.2},{"place":120,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":42.8},{"place":121,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":42.6},{"place":122,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":42.6},{"place":123,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":42.3},{"place":124,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":42.3},{"place":125,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":41.53},{"place":126,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":41.2},{"place":127,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":41.1},{"place":128,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":41},{"place":129,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":40.85},{"place":130,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":40.8},{"place":131,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40.3},{"place":132,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":40.17},{"place":133,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":39.9},{"place":134,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.8},{"place":135,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.78},{"place":136,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":39.1},{"place":137,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":38.79},{"place":138,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":38.7},{"place":139,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.6},{"place":140,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":37.8},{"place":141,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.5},{"place":142,"model":"seed1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":36.81},{"place":143,"model":"gpt-oss-20b-moe","company":"openai","family":"GPT","version":"GPT-OSS","score":36.6},{"place":144,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":36.1},{"place":145,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":35.8},{"place":146,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":35.72},{"place":147,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":35.4},{"place":148,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":34.5},{"place":149,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":34.27},{"place":150,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":32.68},{"place":151,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":32},{"place":152,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":31.6},{"place":153,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":31.2},{"place":154,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.3},{"place":155,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":30.2},{"place":156,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.5},{"place":157,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":29.4},{"place":158,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.3},{"place":159,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":29.3},{"place":160,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":28.2},{"place":161,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":26.8},{"place":162,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":26.2},{"place":163,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":25.4},{"place":164,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":23.14},{"place":165,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22.92},{"place":166,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":22.83},{"place":167,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":21.6},{"place":168,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.3},{"place":169,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":21},{"place":170,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":21},{"place":171,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":20.79},{"place":172,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":20.5},{"place":173,"model":"codestral-12b-instruct","company":"mistral","family":"Codestral","version":"Codestral","score":19.7}]},{"id":"surds","name":"SURDS","topic":"Driving scene spatial reasoning","description":"Spatial understanding and reasoning benchmark on autonomous-driving scenes.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":79.4,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":79.4},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":77.8},{"place":3,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":77.2},{"place":4,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":73.2},{"place":5,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":66.13},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":64.6},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":63},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":62.2},{"place":10,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":58.3},{"place":11,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.95},{"place":12,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":43.06},{"place":13,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":39.72},{"place":14,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":38.6},{"place":15,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":32.8},{"place":16,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":19.54},{"place":17,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":8.5},{"place":18,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":3.1}]},{"id":"svg-bench","name":"SVG-Bench","topic":"SVG generation","description":"MiniMax internal SVG generation benchmark (build from scratch or edit from text/image inputs), VLM-verified rendering accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.6","top_percent":64.1,"top_model_id":"claude-sonnet-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Sonnet 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":64.1},{"place":2,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":63.7},{"place":3,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":62.3},{"place":4,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.7},{"place":5,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":60},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":59.2},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.2},{"place":8,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":56.9},{"place":9,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":48}]},{"id":"swe-atlas-qna","name":"SWE-Atlas Codebase QnA","topic":"Codebase understanding","description":"SWE-Atlas Codebase QnA: agentic question answering over real codebases.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":68,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":48,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":68},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":66},{"place":3,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":64.51},{"place":4,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":64},{"place":5,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":62},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":62},{"place":7,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":61.29},{"place":8,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":61},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59.7},{"place":10,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":59.7},{"place":11,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":59.4},{"place":12,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":59},{"place":13,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":59},{"place":14,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":58.1},{"place":15,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":58},{"place":16,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":57.5},{"place":17,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":55.8},{"place":18,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":55.6},{"place":19,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":55.4},{"place":20,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":54.03},{"place":21,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":54},{"place":22,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":53.5},{"place":23,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53.4},{"place":24,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":52.7},{"place":25,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.6},{"place":26,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":51.08},{"place":27,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":50.8},{"place":28,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":50},{"place":29,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":48.8},{"place":30,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":46.2},{"place":31,"model":"laguna-s-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":46.2},{"place":32,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":45.4},{"place":33,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":45.2},{"place":34,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":42.2},{"place":35,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":42},{"place":36,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":41.9},{"place":37,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":41.2},{"place":38,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":40.3},{"place":39,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":39.8},{"place":40,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":37.9},{"place":41,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":37.9},{"place":42,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":37.1},{"place":43,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":35.2},{"place":44,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":35},{"place":45,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":34.6},{"place":46,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":33.33},{"place":47,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":32.26},{"place":48,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":31.8},{"place":49,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":31.5},{"place":50,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":31.2},{"place":51,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":30.8},{"place":52,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":27.2},{"place":53,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":24.2},{"place":54,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":20.6},{"place":55,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.4},{"place":56,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":17.9},{"place":57,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":17.7},{"place":58,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":15.5},{"place":59,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":13.5},{"place":60,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.2},{"place":61,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":11.3},{"place":62,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.2},{"place":63,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.3}]},{"id":"swe-atlas-refactoring","name":"SWE-Atlas Refactoring","topic":"Software engineering","description":"SWE-Atlas refactoring track: agentic refactoring tasks over real codebases.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":60,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":60},{"place":2,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":53.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":52.4},{"place":4,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":51.9},{"place":5,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":51},{"place":6,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":48.6},{"place":7,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":48.6},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":46.7},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":44.8},{"place":10,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":42.6},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":37.4},{"place":12,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":32.9},{"place":13,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":32.9},{"place":14,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":30},{"place":15,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":29.7},{"place":16,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.4},{"place":17,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":16.6},{"place":18,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":11.4},{"place":19,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":10.2},{"place":20,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":4.3}]},{"id":"swe-atlas-test-writing","name":"SWE-Atlas Test Writing","topic":"Software testing","description":"SWE-Atlas Test Writing: agentic test-writing tasks over real codebases (Scale AI SWE Atlas).","url":"https://labs.scale.com/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":68.7,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":68.7},{"place":2,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":57.8},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":52.8},{"place":4,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":49.6},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":49.6},{"place":6,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":45.6},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":42.6},{"place":8,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":40},{"place":9,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":39.1},{"place":10,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":38.5},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":38.21},{"place":12,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":38.2},{"place":13,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":35.9},{"place":14,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":35.6},{"place":15,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":31.8},{"place":16,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":30.8},{"place":17,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":29.8},{"place":18,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":27.8},{"place":19,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":23.3},{"place":20,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":18.9},{"place":21,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.5},{"place":22,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":15.3},{"place":23,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":13.3},{"place":24,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.8},{"place":25,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":4.4}]},{"id":"swe-bench","name":"SWE-Bench","topic":"Code repair","description":"Supervised software engineering benchmark across many repos and issues.","url":"https://github.com/princeton-nlp/SWE-bench","leaderboard":"https://www.swebench.com/","github":"","paper":"","metric":"percent","stars":"3442","top_model":"GPT-5 Codex","top_percent":74.5,"top_model_id":"gpt-5-codex","top_generation":"GPT-5","top_model_base":"GPT-5 Codex","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":43,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":74.5},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74.4},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.2},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":72.8},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":71.8},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70},{"place":7,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.2},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":66.6},{"place":9,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.2},{"place":10,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":60.6},{"place":11,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":60},{"place":12,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":59},{"place":13,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":58.7},{"place":14,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":54.4},{"place":15,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":48.4},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":47},{"place":17,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":43},{"place":18,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":42},{"place":19,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":41.3},{"place":20,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.8},{"place":21,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":37.6},{"place":22,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":35.7},{"place":23,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":34.6},{"place":24,"model":"gpt-oss-20b-a4b","company":"openai","family":"GPT","version":"GPT-OSS","score":34},{"place":25,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":32.8},{"place":26,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":32},{"place":27,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":30.8},{"place":28,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":30.8},{"place":29,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":28.2},{"place":30,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":26.7},{"place":31,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":25.5},{"place":32,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":24.8},{"place":33,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":22.7},{"place":34,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":22},{"place":35,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":22},{"place":36,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":21.6},{"place":37,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":19.3},{"place":38,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":18.3},{"place":39,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":12.7},{"place":40,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":11.7},{"place":41,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":9.4},{"place":42,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":2.7},{"place":43,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":0},{"place":44,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":0}]},{"id":"swe-bench-multilingual","name":"SWE-Bench Multilingual","topic":"Code repair (multilingual)","description":"Multilingual variant of SWE-Bench for issue fixing.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":93.9,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":169,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.9},{"place":2,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":92.2},{"place":3,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":90.67},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":90.33},{"place":5,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":90.3},{"place":6,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":90},{"place":7,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":90},{"place":8,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89.5},{"place":9,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":89.1},{"place":10,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":88.5},{"place":11,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":87.3},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.6},{"place":13,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":84.8},{"place":14,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":84.4},{"place":15,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":84},{"place":16,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":83.7},{"place":17,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":83},{"place":18,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":82.9},{"place":19,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.6},{"place":20,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":82},{"place":21,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":81.67},{"place":22,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":81.3},{"place":23,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81},{"place":24,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.8},{"place":25,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":80.5},{"place":26,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":80.5},{"place":27,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":79.6},{"place":28,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":78.9},{"place":29,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":78.56},{"place":30,"model":"laguna-s-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":78.5},{"place":31,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":78.4},{"place":32,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":78.3},{"place":33,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":78.3},{"place":34,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":78.3},{"place":35,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":78.3},{"place":36,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":78},{"place":37,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77.9},{"place":38,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.8},{"place":39,"model":"swe-1.7","company":"cognition","family":"SWE","version":"SWE-1.7","score":77.8},{"place":40,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.5},{"place":41,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.5},{"place":42,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.5},{"place":43,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":77.3},{"place":44,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":77.3},{"place":45,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77.3},{"place":46,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":77.1},{"place":47,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":77.1},{"place":48,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":77},{"place":49,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.9},{"place":50,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":76.8},{"place":51,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":76.8},{"place":52,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":76.7},{"place":53,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":76.5},{"place":54,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.5},{"place":55,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":76.4},{"place":56,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.2},{"place":57,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.2},{"place":58,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.2},{"place":59,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.9},{"place":60,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":75.8},{"place":61,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.8},{"place":62,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":75.8},{"place":63,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":75.7},{"place":64,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75.7},{"place":65,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":75.4},{"place":66,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":75.1},{"place":67,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75},{"place":68,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":74.8},{"place":69,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":74.8},{"place":70,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":74.5},{"place":71,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.1},{"place":72,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":74.1},{"place":73,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":73.8},{"place":74,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.8},{"place":75,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.8},{"place":76,"model":"composer-2","company":"cursor","family":"Composer","version":"Composer 2","score":73.7},{"place":77,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":73.6},{"place":78,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":73.5},{"place":79,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":73.33},{"place":80,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":73.3},{"place":81,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":73.3},{"place":82,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.3},{"place":83,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.3},{"place":84,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":73},{"place":85,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":73},{"place":86,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73},{"place":87,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":72.7},{"place":88,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":72.5},{"place":89,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72.44},{"place":90,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":72.4},{"place":91,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":72.4},{"place":92,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":72},{"place":93,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":72},{"place":94,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72},{"place":95,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":71.8},{"place":96,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":71.7},{"place":97,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":71.7},{"place":98,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":71.7},{"place":99,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":71.7},{"place":100,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.7},{"place":101,"model":"composer-2.5","company":"cursor","family":"Composer","version":"Composer 2.5","score":71.6},{"place":102,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":71.4},{"place":103,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":71.4},{"place":104,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":71.3},{"place":105,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":71.1},{"place":106,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":71},{"place":107,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.9},{"place":108,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":70.3},{"place":109,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":70.2},{"place":110,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":70.2},{"place":111,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":70.2},{"place":112,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.8},{"place":113,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69.7},{"place":114,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":69.33},{"place":115,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.3},{"place":116,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.3},{"place":117,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":69.3},{"place":118,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":69},{"place":119,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":68.9},{"place":120,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.8},{"place":121,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":68.3},{"place":122,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":68.3},{"place":123,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68},{"place":124,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68},{"place":125,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.72},{"place":126,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.7},{"place":127,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.7},{"place":128,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.4},{"place":129,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":67.4},{"place":130,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":67.3},{"place":131,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.2},{"place":132,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":67.2},{"place":133,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.11},{"place":134,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67},{"place":135,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67},{"place":136,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":66.9},{"place":137,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":66.7},{"place":138,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":66.7},{"place":139,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":66.6},{"place":140,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":66.56},{"place":141,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":66.2},{"place":142,"model":"xing4.0-29b-a4b","company":"teleai","family":"Xing","version":"Xing4.0","score":66},{"place":143,"model":"composer-1.5","company":"cursor","family":"Composer","version":"Composer 1.5","score":65.9},{"place":144,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":65.5},{"place":145,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":65.22},{"place":146,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":65.1},{"place":147,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":65},{"place":148,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65},{"place":149,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":64.7},{"place":150,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.4},{"place":151,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":63.7},{"place":152,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.7},{"place":153,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.4},{"place":154,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":63.1},{"place":155,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":63.1},{"place":156,"model":"kat-coder-v2.5-dev","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":63},{"place":157,"model":"qwen3-coder-next","company":"qwen","family":"Qwen","version":"Qwen3","score":62.8},{"place":158,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":62.7},{"place":159,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":62.4},{"place":160,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62.3},{"place":161,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62},{"place":162,"model":"devstral-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":61.3},{"place":163,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":61.1},{"place":164,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.3},{"place":165,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":59.33},{"place":166,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":58.7},{"place":167,"model":"swe-1.6","company":"cognition","family":"SWE","version":"SWE-1.6","score":58.3},{"place":168,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":57.9},{"place":169,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":57.8},{"place":170,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":57.7},{"place":171,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.67},{"place":172,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57},{"place":173,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":56.9},{"place":174,"model":"composer-1","company":"cursor","family":"Composer","version":"Composer 1","score":56.9},{"place":175,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":56.7},{"place":176,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":56.5},{"place":177,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":55.9},{"place":178,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":55.9},{"place":179,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":55.9},{"place":180,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":55.7},{"place":181,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":55.3},{"place":182,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":55.3},{"place":183,"model":"qwen3-coder-480b-a35b","company":"qwen","family":"Qwen","version":"Qwen3","score":54.7},{"place":184,"model":"qwen3-coder-plus","company":"qwen","family":"Qwen","version":"Qwen3","score":54.7},{"place":185,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":54.5},{"place":186,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":54.5},{"place":187,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":54.4},{"place":188,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":53.8},{"place":189,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":53.3},{"place":190,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":53.3},{"place":191,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":52.7},{"place":192,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":52},{"place":193,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.7},{"place":194,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":51.67},{"place":195,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":51},{"place":196,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51},{"place":197,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":49.8},{"place":198,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":49.33},{"place":199,"model":"iquest-coder-v1-14b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":48},{"place":200,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":48},{"place":201,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.67},{"place":202,"model":"kimi-k2-instruct-0711","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":47.3},{"place":203,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":47.3},{"place":204,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":45.78},{"place":205,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":44},{"place":206,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.4},{"place":207,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.3},{"place":208,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":42.7},{"place":209,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":41.93},{"place":210,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":41.89},{"place":211,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.7},{"place":212,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":39.33},{"place":213,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":38.1},{"place":214,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":37.2},{"place":215,"model":"iquest-coder-v1-14b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":37},{"place":216,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":33.73},{"place":217,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.5},{"place":218,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":31.5},{"place":219,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":31.3},{"place":220,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":30.8},{"place":221,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":30.78},{"place":222,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":30},{"place":223,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.7},{"place":224,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.33},{"place":225,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":25.8},{"place":226,"model":"llada2.2-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":25},{"place":227,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":23.3},{"place":228,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":20.9},{"place":229,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":20.67},{"place":230,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":17.3},{"place":231,"model":"iquest-coder-v1-7b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":17.3},{"place":232,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":14.07},{"place":233,"model":"iquest-coder-v1-7b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":13.3},{"place":234,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5}]},{"id":"swe-bench-multimodal","name":"SWE-bench Multimodal","topic":"Software engineering","description":"SWE-bench variant with visual context (screenshots, design mockups) in issue descriptions.","url":"https://arxiv.org/abs/2410.03859","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":61.4,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":61.4},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":59.4},{"place":3,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":59},{"place":4,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":54.7},{"place":5,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":54.3},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.1},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":40.2},{"place":8,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":39.2},{"place":9,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":39.2},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":38.4},{"place":11,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":38.2},{"place":12,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":37.3},{"place":13,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":34.5},{"place":14,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":30.7},{"place":15,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":28.1},{"place":16,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":27.1},{"place":17,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":25.5},{"place":18,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":20.6},{"place":19,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":19.8}]},{"id":"swe-bench-openhands","name":"SWE-Bench (OpenHands)","topic":"Code repair","description":"SWE-Bench results using the OpenHands autonomous coding agent.","url":"https://github.com/princeton-nlp/SWE-bench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"3442","top_model":"Qwen3.5-35B-A3B","top_percent":69.2,"top_model_id":"qwen3.5-35b-a3b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 35B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.2},{"place":2,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.4},{"place":3,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60.5},{"place":4,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60.47},{"place":5,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":59.5},{"place":6,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56.9},{"place":7,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":50.2},{"place":8,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":41.9},{"place":9,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.8},{"place":10,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":34},{"place":11,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":22}]},{"id":"swe-bench-pro","name":"SWE-Bench Pro","topic":"Software engineering","description":"Full SWE-Bench Pro benchmark for software-engineering agents.","url":"https://www.swebench.com/","leaderboard":"https://scale.com/leaderboard/swe_bench_pro_public","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5.5","top_percent":89.9,"top_model_id":"claude-opus-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":139,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":89.9},{"place":2,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":81.3},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":81.2},{"place":4,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.3},{"place":5,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":79.2},{"place":7,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":77.8},{"place":8,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":76.9},{"place":9,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":76.5},{"place":10,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":76.2},{"place":11,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":74.7},{"place":12,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":73.6},{"place":13,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.2},{"place":14,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":68.74},{"place":15,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":68.54},{"place":16,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":68.54},{"place":17,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":68},{"place":18,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67.7},{"place":19,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":65.7},{"place":20,"model":"nex-n2.5-max","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":65.7},{"place":21,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.5},{"place":22,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.3},{"place":23,"model":"kat-coder-pro-v2.5","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":65.2},{"place":24,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":65.1},{"place":25,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":65.1},{"place":26,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":64.84},{"place":27,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":64.8},{"place":28,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.6},{"place":29,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":64.6},{"place":30,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.4},{"place":31,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":64.3},{"place":32,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":63.4},{"place":33,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":63.4},{"place":34,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":63.3},{"place":35,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.2},{"place":36,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":63.06},{"place":37,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":62.7},{"place":38,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":62.2},{"place":39,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":62.1},{"place":40,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":62.1},{"place":41,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":62},{"place":42,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":61.83},{"place":43,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":61.7},{"place":44,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":61.6},{"place":45,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":61.56},{"place":46,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":61.5},{"place":47,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":61.4},{"place":48,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":61.2},{"place":49,"model":"sage-a1.5","company":"internlm","family":"Agents","version":"A1.5","score":61.2},{"place":50,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":61},{"place":51,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":60.6},{"place":52,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":60.3},{"place":53,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":60.3},{"place":54,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":59.8},{"place":55,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":59.6},{"place":56,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":59.6},{"place":57,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":59.5},{"place":58,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":59.4},{"place":59,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":59.1},{"place":60,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.6},{"place":61,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":58.6},{"place":62,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":58.4},{"place":63,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":58.4},{"place":64,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":58.3},{"place":65,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":58.3},{"place":66,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":58.1},{"place":67,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":57.9},{"place":68,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":57.7},{"place":69,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":57.7},{"place":70,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":57.59},{"place":71,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":57.5},{"place":72,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":57.3},{"place":73,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":57.2},{"place":74,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":57},{"place":75,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":57},{"place":76,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.9},{"place":77,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":56.8},{"place":78,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":56.77},{"place":79,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":56.6},{"place":80,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":56.3},{"place":81,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":56.2},{"place":82,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":56.1},{"place":83,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":55.6},{"place":84,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":55.6},{"place":85,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":55.6},{"place":86,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.6},{"place":87,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.4},{"place":88,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":55.4},{"place":89,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":55.4},{"place":90,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.4},{"place":91,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.4},{"place":92,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.4},{"place":93,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":55.1},{"place":94,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":55},{"place":95,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":55},{"place":96,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":54.4},{"place":97,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":54.3},{"place":98,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.2},{"place":99,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":54.2},{"place":100,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":54.1},{"place":101,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":53.9},{"place":102,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":53.76},{"place":103,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":53.5},{"place":104,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":53.49},{"place":105,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53.4},{"place":106,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.6},{"place":107,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.6},{"place":108,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":52.4},{"place":109,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":52},{"place":110,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":51.8},{"place":111,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.6},{"place":112,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":51.3},{"place":113,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":51.2},{"place":114,"model":"gpt-5.1-thinking","company":"openai","family":"GPT","version":"GPT-5.1","score":50.8},{"place":115,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":50.7},{"place":116,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":50.4},{"place":117,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":50.2},{"place":118,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":50.2},{"place":119,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.98},{"place":120,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":49.7},{"place":121,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":49.5},{"place":122,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":49.1},{"place":123,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":48.3},{"place":124,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":47.9},{"place":125,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":47.5},{"place":126,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":46.9},{"place":127,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":46.9},{"place":128,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":46.7},{"place":129,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":46.7},{"place":130,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":46.6},{"place":131,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":46},{"place":132,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":46},{"place":133,"model":"kat-coder-v2.5-dev","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":45.96},{"place":134,"model":"mimo-v2.6-distill-qwen-9b","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":44.6},{"place":135,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":44.4},{"place":136,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.3},{"place":137,"model":"qwen3-coder-next","company":"qwen","family":"Qwen","version":"Qwen3","score":44.3},{"place":138,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":43.9},{"place":139,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":43.8},{"place":140,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":43.6},{"place":141,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":43.6},{"place":142,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.55},{"place":143,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":43.3},{"place":144,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":42.9},{"place":145,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":42.5},{"place":146,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":42.3},{"place":147,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.13},{"place":148,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":40.9},{"place":149,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":40.63},{"place":150,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":40.63},{"place":151,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":40.6},{"place":152,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":39.8},{"place":153,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":38.7},{"place":154,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.03},{"place":155,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38},{"place":156,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":36.9},{"place":157,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":35.7},{"place":158,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":34.6},{"place":159,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":34.47},{"place":160,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34.3},{"place":161,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":34.1},{"place":162,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.8},{"place":163,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.97},{"place":164,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":32.9},{"place":165,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32},{"place":166,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":31.88},{"place":167,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.3},{"place":168,"model":"llada2.2-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":30.1},{"place":169,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.4},{"place":170,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.2},{"place":171,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":28},{"place":172,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21.9},{"place":173,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":19.84},{"place":174,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":14.4},{"place":175,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":12.3},{"place":176,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":10.4},{"place":177,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":9.58},{"place":178,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4},{"place":179,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.3},{"place":180,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1.9},{"place":181,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0.8},{"place":182,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":0.6},{"place":183,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":0.4},{"place":184,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":0.1},{"place":185,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0},{"place":186,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":0}]},{"id":"swe-bench-pro-public","name":"SWE-Bench Pro (Public)","topic":"Software engineering","description":"Public subset of the SWE-Bench Pro benchmark for software-engineering agents.","url":"","leaderboard":"https://scale.com/leaderboard/swe_bench_pro_public","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Fable 5","top_percent":80.4,"top_model_id":"claude-fable-5","top_generation":"Claude 5","top_model_base":"Claude Fable 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":102,"total_models":3854,"placements":[{"place":1,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.4},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.3},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80},{"place":4,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":73.7},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":69.2},{"place":6,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67.7},{"place":7,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":66.1},{"place":8,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":65.5},{"place":9,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":64.7},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":64.6},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":64.3},{"place":12,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":63.3},{"place":13,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.2},{"place":14,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":62.7},{"place":15,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":62.5},{"place":16,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":62.2},{"place":17,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":62.1},{"place":18,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":61.7},{"place":19,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":61.5},{"place":20,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":60.6},{"place":21,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":60.37},{"place":22,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":60.3},{"place":23,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":59.7},{"place":24,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":59.5},{"place":25,"model":"laguna-s-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":59.4},{"place":26,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":59},{"place":27,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59},{"place":28,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":59},{"place":29,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":58.8},{"place":30,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":58.8},{"place":31,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":58.7},{"place":32,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.6},{"place":33,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":58.6},{"place":34,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":58.4},{"place":35,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":57.9},{"place":36,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":57.7},{"place":37,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":57.6},{"place":38,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":57.3},{"place":39,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57.3},{"place":40,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":57.2},{"place":41,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.1},{"place":42,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.91},{"place":43,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":56.8},{"place":44,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":56.8},{"place":45,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":56.6},{"place":46,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":56.54},{"place":47,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":56.4},{"place":48,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":56.4},{"place":49,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":56.22},{"place":50,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":56.2},{"place":51,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":56.1},{"place":52,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56},{"place":53,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":55.9},{"place":54,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":55.8},{"place":55,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":55.6},{"place":56,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":55.6},{"place":57,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.4},{"place":58,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.4},{"place":59,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":55.4},{"place":60,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":55.1},{"place":61,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":55.1},{"place":62,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":54.4},{"place":63,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.4},{"place":64,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":54.3},{"place":65,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.2},{"place":66,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":54.2},{"place":67,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":53.9},{"place":68,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":53.8},{"place":69,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":53.8},{"place":70,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":53.5},{"place":71,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53.4},{"place":72,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53},{"place":73,"model":"mai-thinking-1","company":"microsoft","family":"MAI","version":"MAI-Thinking-1","score":52.8},{"place":74,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.6},{"place":75,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":52.4},{"place":76,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.3},{"place":77,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.1},{"place":78,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":51.78},{"place":79,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":51.66},{"place":80,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.6},{"place":81,"model":"gpt-5.3-codex-spark","company":"openai","family":"GPT","version":"GPT-5.3","score":51.5},{"place":82,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":51.48},{"place":83,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.2},{"place":84,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":51.2},{"place":85,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":51.2},{"place":86,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":50.93},{"place":87,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.9},{"place":88,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":50.7},{"place":89,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":50.4},{"place":90,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":50.3},{"place":91,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":50.3},{"place":92,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":50.2},{"place":93,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":49.66},{"place":94,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":49.5},{"place":95,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":49.2},{"place":96,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.1},{"place":97,"model":"gpt-5.1-codex-mini-high","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":49},{"place":98,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":48.4},{"place":99,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":47.6},{"place":100,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":46.9},{"place":101,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":46.4},{"place":102,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":46.3},{"place":103,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":45.7},{"place":104,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.9},{"place":105,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.6},{"place":106,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":44.5},{"place":107,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":43.3},{"place":108,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":42.9},{"place":109,"model":"north-mini-code-1.0","company":"cohere","family":"North","version":"North 1.0","score":40.2},{"place":110,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":39.5},{"place":111,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":38.3},{"place":112,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":36.9},{"place":113,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":35.7},{"place":114,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":35.7},{"place":115,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":35.2},{"place":116,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":33.29},{"place":117,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.3},{"place":118,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.6},{"place":119,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":23.26},{"place":120,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":22.71},{"place":121,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":19.11},{"place":122,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":17.65},{"place":123,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":16.2},{"place":124,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":13.8},{"place":125,"model":"gemini-2.5-pro-preview-06-05","company":"google","family":"Gemini","version":"Gemini 2.5","score":13.54},{"place":126,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":13},{"place":127,"model":"swesmith-32b","company":"swe","family":"SWE Smith","version":"SWE Smith","score":6.84},{"place":128,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":4.92},{"place":129,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.42}]},{"id":"swe-bench-pro-v2","name":"SWE-Bench Pro v2","topic":"Software engineering","description":"SWE-Bench Pro v2 (Scale AI) agentic software-engineering tasks; full set.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-27B","top_percent":94.9,"top_model_id":"qwen3.8-27b","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 27B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":94.9},{"place":2,"model":"flint","company":"recursive","family":"Flint","version":"Flint","score":89.7},{"place":3,"model":"flint-nvfp4","company":"recursive","family":"Flint","version":"Flint","score":88.5},{"place":4,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":86},{"place":5,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":73.8},{"place":6,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.6},{"place":7,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.7},{"place":8,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":38.6}]},{"id":"swe-bench-pro-v2-hard","name":"SWE-Bench Pro v2 (Hard)","topic":"Software engineering","description":"Hard split of SWE-Bench Pro v2 (Scale AI) for software-engineering agents.","url":"https://scale.com/leaderboard","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":88.2,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":88.2},{"place":2,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":84.3},{"place":3,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":77.2},{"place":4,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":76.5},{"place":5,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":56.9}]},{"id":"swe-bench-verified","name":"SWE-Bench Verified","topic":"Code repair","description":"Verified subset of SWE-Bench for issue fixing.","url":"https://www.swebench.com/","leaderboard":"https://www.swebench.com/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":96,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":342,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":96},{"place":2,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":95.5},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":95},{"place":4,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":93.9},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":93.2},{"place":6,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":93},{"place":7,"model":"ember-1","company":"fireworks","family":"Ember","version":"Ember-1","score":92.2},{"place":8,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":88.6},{"place":9,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":87.6},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":87.6},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":86.2},{"place":12,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":86},{"place":13,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":86},{"place":14,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":85.8},{"place":15,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":85.2},{"place":16,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":84.5},{"place":17,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.4},{"place":18,"model":"lar-27b","company":"amazon","family":"LAR","version":"LAR","score":84.2},{"place":19,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":84.2},{"place":20,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":83},{"place":21,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":82.9},{"place":22,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.8},{"place":23,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":82.4},{"place":24,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":81.6},{"place":25,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":81.6},{"place":26,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":81.4},{"place":27,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":81},{"place":28,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.9},{"place":29,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.9},{"place":30,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.9},{"place":31,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":80.9},{"place":32,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":80.8},{"place":33,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":80.8},{"place":34,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":80.8},{"place":35,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":80.8},{"place":36,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":80.8},{"place":37,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.6},{"place":38,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.6},{"place":39,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":80.6},{"place":40,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.6},{"place":41,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":80.5},{"place":42,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":80.4},{"place":43,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.4},{"place":44,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":80.2},{"place":45,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.2},{"place":46,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":80.2},{"place":47,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":80.2},{"place":48,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.2},{"place":49,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":80},{"place":50,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":80},{"place":51,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":80},{"place":52,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":80},{"place":53,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":80},{"place":54,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":80},{"place":55,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":79.9},{"place":56,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":79.6},{"place":57,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":79.6},{"place":58,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79.4},{"place":59,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":79.1},{"place":60,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79},{"place":61,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79},{"place":62,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":79},{"place":63,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":78.9},{"place":64,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":78.8},{"place":65,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":78.7},{"place":66,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.6},{"place":67,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":78.6},{"place":68,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":78.4},{"place":69,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.2},{"place":70,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":71,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":72,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":73,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":78},{"place":74,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":78},{"place":75,"model":"gpt-5.1-codex-max","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":77.9},{"place":76,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":77.8},{"place":77,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":77.7},{"place":78,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":77.6},{"place":79,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":77.6},{"place":80,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":77.4},{"place":81,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77.4},{"place":82,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.2},{"place":83,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.2},{"place":84,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.2},{"place":85,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":77.2},{"place":86,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":76.8},{"place":87,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":76.8},{"place":88,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.8},{"place":89,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":76.7},{"place":90,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":76.5},{"place":91,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.4},{"place":92,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":76.4},{"place":93,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":76.3},{"place":94,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":76.3},{"place":95,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.2},{"place":96,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":76.2},{"place":97,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.2},{"place":98,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":76.2},{"place":99,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.2},{"place":100,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":76.2},{"place":101,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":76.2},{"place":102,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":76.2},{"place":103,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":76.2},{"place":104,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76},{"place":105,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":76},{"place":106,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":76},{"place":107,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":76},{"place":108,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":75.7},{"place":109,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.6},{"place":110,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":75.6},{"place":111,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":75.6},{"place":112,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.6},{"place":113,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.4},{"place":114,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":75.4},{"place":115,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":75.3},{"place":116,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":75.3},{"place":117,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":75.27},{"place":118,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75},{"place":119,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":75},{"place":120,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":75},{"place":121,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":75},{"place":122,"model":"xing4.0-29b-a4b","company":"teleai","family":"Xing","version":"Xing4.0","score":75},{"place":123,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":74.9},{"place":124,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":74.9},{"place":125,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":74.9},{"place":126,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":74.8},{"place":127,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":74.8},{"place":128,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":74.6},{"place":129,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":74.6},{"place":130,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":74.6},{"place":131,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":74.5},{"place":132,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":74.5},{"place":133,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.5},{"place":134,"model":"claude-opus-4.5-medium","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74.4},{"place":135,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":74.4},{"place":136,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":74.4},{"place":137,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":74.4},{"place":138,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":74.2},{"place":139,"model":"flint","company":"recursive","family":"Flint","version":"Flint","score":74.2},{"place":140,"model":"flint-nvfp4","company":"recursive","family":"Flint","version":"Flint","score":74.1},{"place":141,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":74},{"place":142,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":74},{"place":143,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":74},{"place":144,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.9},{"place":145,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":73.8},{"place":146,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":73.8},{"place":147,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":73.8},{"place":148,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.8},{"place":149,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":73.8},{"place":150,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.7},{"place":151,"model":"gpt-5.1-codex","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":73.7},{"place":152,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.6},{"place":153,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73.6},{"place":154,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":73.6},{"place":155,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.5},{"place":156,"model":"mai-thinking-1","company":"microsoft","family":"MAI","version":"MAI-Thinking-1","score":73.5},{"place":157,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.5},{"place":158,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":73.5},{"place":159,"model":"kat-coder","company":"kuaishou","family":"KAT","version":"KAT","score":73.4},{"place":160,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":73.4},{"place":161,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":73.4},{"place":162,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":73.4},{"place":163,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.3},{"place":164,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":73.2},{"place":165,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":73.1},{"place":166,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":73.1},{"place":167,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":73},{"place":168,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":72.9},{"place":169,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":72.8},{"place":170,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":72.8},{"place":171,"model":"jais-3-mova-36b-a4b","company":"g42","family":"Jais","version":"Jais 3","score":72.8},{"place":172,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":72.7},{"place":173,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":72.6},{"place":174,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":72.5},{"place":175,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":72.5},{"place":176,"model":"ring-1t-2.5","company":"antgroup","family":"Ring","version":"Ring 2.5","score":72.4},{"place":177,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.4},{"place":178,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":72.4},{"place":179,"model":"jais-3-32b","company":"g42","family":"Jais","version":"Jais 3","score":72.4},{"place":180,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":72.3},{"place":181,"model":"devstral-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":72.2},{"place":182,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":72.2},{"place":183,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":72.07},{"place":184,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":72},{"place":185,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72},{"place":186,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":72},{"place":187,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.9},{"place":188,"model":"gpt-5.2-high","company":"openai","family":"GPT","version":"GPT-5.2","score":71.8},{"place":189,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.8},{"place":190,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":71.8},{"place":191,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":71.6},{"place":192,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.6},{"place":193,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.47},{"place":194,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":71.4},{"place":195,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":71.3},{"place":196,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.1},{"place":197,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.1},{"place":198,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":71},{"place":199,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":71},{"place":200,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":71},{"place":201,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":70.9},{"place":202,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":70.8},{"place":203,"model":"claude-sonnet-4-moatless-tools","company":"anthropic","family":"Claude","version":"Claude 4","score":70.8},{"place":204,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":70.8},{"place":205,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":70.8},{"place":206,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":70.8},{"place":207,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":70.7},{"place":208,"model":"qwen3-coder-next","company":"qwen","family":"Qwen","version":"Qwen3","score":70.6},{"place":209,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":70.6},{"place":210,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":70.4},{"place":211,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":70.2},{"place":212,"model":"jais-3-375b-a23b","company":"g42","family":"Jais","version":"Jais 3","score":70.2},{"place":213,"model":"jais-3-7b","company":"g42","family":"Jais","version":"Jais 3","score":70.2},{"place":214,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":70.12},{"place":215,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":70},{"place":216,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70},{"place":217,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":70},{"place":218,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":70},{"place":219,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":69.9},{"place":220,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.7},{"place":221,"model":"qwen3-coder-480b-a35b","company":"qwen","family":"Qwen","version":"Qwen3","score":69.6},{"place":222,"model":"qwen3-coder-plus","company":"qwen","family":"Qwen","version":"Qwen3","score":69.6},{"place":223,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69.6},{"place":224,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":69.6},{"place":225,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":69.4},{"place":226,"model":"kat-coder-v2.5-dev","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":69.4},{"place":227,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":69.4},{"place":228,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.2},{"place":229,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.2},{"place":230,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.2},{"place":231,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.2},{"place":232,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":69.2},{"place":233,"model":"o3","company":"openai","family":"o3","version":"o3","score":69.1},{"place":234,"model":"gpt-5.2-medium","company":"openai","family":"GPT","version":"GPT-5.2","score":69},{"place":235,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":68.6},{"place":236,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":68.5},{"place":237,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":68.4},{"place":238,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":68.2},{"place":239,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":68.2},{"place":240,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":68.2},{"place":241,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":68.2},{"place":242,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":68},{"place":243,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":68},{"place":244,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":67.8},{"place":245,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.8},{"place":246,"model":"north-mini-code-1.0","company":"cohere","family":"North","version":"North 1.0","score":67.6},{"place":247,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.2},{"place":248,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":66.9},{"place":249,"model":"claude-sonnet-4-r2e-gym","company":"anthropic","family":"Claude","version":"Claude 4","score":66.9},{"place":250,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":66.8},{"place":251,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":66.8},{"place":252,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":66.6},{"place":253,"model":"claude-sonnet-4-swe-agent","company":"anthropic","family":"Claude","version":"Claude 4","score":66.6},{"place":254,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":66.6},{"place":255,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.6},{"place":256,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":66.4},{"place":257,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":66.4},{"place":258,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":66.2},{"place":259,"model":"iquest-coder-v1-14b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":66.2},{"place":260,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":66},{"place":261,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":66},{"place":262,"model":"gpt-5.1-medium","company":"openai","family":"GPT","version":"GPT-5.1","score":66},{"place":263,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":66},{"place":264,"model":"kimi-k2-instruct-0711","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":65.8},{"place":265,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":65.8},{"place":266,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":267,"model":"gpt-5-r2e-gym","company":"openai","family":"GPT","version":"GPT-5","score":65.7},{"place":268,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":65.6},{"place":269,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":65},{"place":270,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":64.4},{"place":271,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":64.3},{"place":272,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":64.2},{"place":273,"model":"glm-4.5-358b","company":"zai","family":"GLM","version":"GLM 4.5","score":64.2},{"place":274,"model":"glm-4.5-358b-swe-agent","company":"zai","family":"GLM","version":"GLM 4.5","score":64.2},{"place":275,"model":"lar-9b","company":"amazon","family":"LAR","version":"LAR","score":64.2},{"place":276,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.2},{"place":277,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":64},{"place":278,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":63.8},{"place":279,"model":"iquest-coder-v1-14b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":63.6},{"place":280,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":63.6},{"place":281,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.5},{"place":282,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":63.2},{"place":283,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.2},{"place":284,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":63.1},{"place":285,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63.08},{"place":286,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":62.8},{"place":287,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":62.5},{"place":288,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":62.4},{"place":289,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":62.4},{"place":290,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":62.4},{"place":291,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":62.3},{"place":292,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":62},{"place":293,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":62},{"place":294,"model":"nemotron-labs-dory1.0-4b-4loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":61.8},{"place":295,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":61.6},{"place":296,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":61.5},{"place":297,"model":"ling-2.6-flash","company":"antgroup","family":"Ling","version":"Ling 2.6","score":61.2},{"place":298,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":61.2},{"place":299,"model":"mimo-v2.6-distill-qwen-9b","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":61.1},{"place":300,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":61},{"place":301,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":61},{"place":302,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61},{"place":303,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":60.9},{"place":304,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":60.8},{"place":305,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":60.8},{"place":306,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":60.6},{"place":307,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":60.6},{"place":308,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":60.6},{"place":309,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":60.4},{"place":310,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":60.4},{"place":311,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":60.3},{"place":312,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60.2},{"place":313,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60},{"place":314,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":59.8},{"place":315,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.6},{"place":316,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":59.6},{"place":317,"model":"nemotron-labs-dory1.0-4b","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":59.5},{"place":318,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":59.2},{"place":319,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":59},{"place":320,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.6},{"place":321,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":58.6},{"place":322,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":57.9},{"place":323,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.8},{"place":324,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":57.6},{"place":325,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":57.6},{"place":326,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":57.6},{"place":327,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":57.4},{"place":328,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":57},{"place":329,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":56},{"place":330,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":55.8},{"place":331,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":55.7},{"place":332,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":55.6},{"place":333,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":55.5},{"place":334,"model":"qwen3-coder-480b","company":"qwen","family":"Qwen","version":"Qwen3","score":55.4},{"place":335,"model":"qwen3-coder-480b-a35b-mini-swe-agent","company":"qwen","family":"Qwen","version":"Qwen3","score":55.4},{"place":336,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":55.1},{"place":337,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.7},{"place":338,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":54.6},{"place":339,"model":"frogboss-32b-2510","company":"microsoft","family":"FrogBoss","version":"FrogBoss","score":54.6},{"place":340,"model":"glm-4.5-358b","company":"zai","family":"GLM","version":"GLM 4.5","score":54.2},{"place":341,"model":"glm-4.5-358b-mini-swe-agent","company":"zai","family":"GLM","version":"GLM 4.5","score":54.2},{"place":342,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":54},{"place":343,"model":"openthinkeragent-32b","company":"openthinker","family":"OpenThinker","version":"OpenThinkerAgent","score":54},{"place":344,"model":"cwm-32b","company":"cwm","family":"CWM","version":"CWM","score":53.9},{"place":345,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":53.7},{"place":346,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":53.6},{"place":347,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":53.4},{"place":348,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":53.4},{"place":349,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.2},{"place":350,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.1},{"place":351,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":53},{"place":352,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":53},{"place":353,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":52.44},{"place":354,"model":"swe-mirror-lm-32b","company":"swe-mirror","family":"SWE-Mirror","version":"SWE-Mirror","score":52.2},{"place":355,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52},{"place":356,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":51.6},{"place":357,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":51.6},{"place":358,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":51.56},{"place":359,"model":"telechat3-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":51},{"place":360,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":51},{"place":361,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":51},{"place":362,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.8},{"place":363,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":50.8},{"place":364,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":50.6},{"place":365,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":50.6},{"place":366,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":50.5},{"place":367,"model":"nemotron-labs-dory1.0-4b-1loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":50.3},{"place":368,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":50},{"place":369,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50},{"place":370,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":49.8},{"place":371,"model":"sera-32b","company":"allenai","family":"SERA","version":"SERA","score":49.5},{"place":372,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":49.4},{"place":373,"model":"llada2.2-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.2","score":49.28},{"place":374,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":49.2},{"place":375,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":49},{"place":376,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.9},{"place":377,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.9},{"place":378,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":48.6},{"place":379,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":47.7},{"place":380,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":47.67},{"place":381,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":47.2},{"place":382,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":47},{"place":383,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":47},{"place":384,"model":"devstral","company":"mistral","family":"Devstral","version":"Devstral","score":46.8},{"place":385,"model":"sera-32b-ga","company":"allenai","family":"SERA","version":"SERA","score":46.6},{"place":386,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":46.4},{"place":387,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":45.6},{"place":388,"model":"frogmini-14b-2510","company":"microsoft","family":"FrogMini","version":"FrogMini","score":45.3},{"place":389,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":45},{"place":390,"model":"iquest-coder-v1-7b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":45},{"place":391,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":45},{"place":392,"model":"swe-swiss-32b","company":"swe-swiss","family":"SWE-Swiss","version":"SWE-Swiss","score":45},{"place":393,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":44.2},{"place":394,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":44},{"place":395,"model":"gpt-5.4-mini-none","company":"openai","family":"GPT","version":"GPT-5.4","score":43.8},{"place":396,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":43.2},{"place":397,"model":"nemotron-cascade-14b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":43.1},{"place":398,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.7},{"place":399,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":42.4},{"place":400,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":42.4},{"place":401,"model":"deepswe-32b-preview","company":"deepswe","family":"DeepSWE","version":"DeepSWE","score":42.2},{"place":402,"model":"cogito-671b-v2.1","company":"deepcogito","family":"Cogito","version":"Cogito 671B v2.1","score":42},{"place":403,"model":"telechat3-105b-a4.7b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":42},{"place":404,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":42},{"place":405,"model":"sera-14b","company":"allenai","family":"SERA","version":"SERA","score":41.7},{"place":406,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":41.6},{"place":407,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.2},{"place":408,"model":"swe-rl-70b","company":"swe-rl","family":"SWE-RL","version":"SWE-RL","score":41},{"place":409,"model":"claude-3-5-haiku-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":40.6},{"place":410,"model":"swe-smith-lm-32b","company":"swe-smith","family":"SWE-Smith","version":"SWE-Smith","score":40.2},{"place":411,"model":"rnj-1.5","company":"essential","family":"Rnj","version":"Rnj 1.5","score":40},{"place":412,"model":"sa-swe-32b","company":"novasky","family":"SkyRL","version":"SkyRL-Agent","score":39.4},{"place":413,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":38.8},{"place":414,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.8},{"place":415,"model":"iquest-coder-v1-7b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":38.8},{"place":416,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.8},{"place":417,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":38.8},{"place":418,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.6},{"place":419,"model":"nemotron-cascade-8b-thinking","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":38.5},{"place":420,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":38.4},{"place":421,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":38.4},{"place":422,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":38.2},{"place":423,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":38},{"place":424,"model":"skywork-swe-32b","company":"skywork","family":"Skywork","version":"Skywork SWE","score":38},{"place":425,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":37.3},{"place":426,"model":"nemotron-cascade-8b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade","score":37.2},{"place":427,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":36.8},{"place":428,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":36.1},{"place":429,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":35.8},{"place":430,"model":"frogboss-32b-2510","company":"microsoft","family":"FrogBoss","version":"FrogBoss","score":35},{"place":431,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":34.4},{"place":432,"model":"r2e-gym-32b","company":"r2e-gym","family":"R2E-Gym","version":"R2E-Gym","score":34.4},{"place":433,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":34.2},{"place":434,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":34.08},{"place":435,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":34},{"place":436,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":34},{"place":437,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":33.7},{"place":438,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.6},{"place":439,"model":"swe-fixer-72b","company":"swe-fixer","family":"SWE-Fixer","version":"SWE-Fixer","score":32.8},{"place":440,"model":"swe-smith-lm-32b","company":"swe-smith","family":"SWE-Smith","version":"SWE-Smith","score":32.6},{"place":441,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":32.5},{"place":442,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":32.2},{"place":443,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":31.8},{"place":444,"model":"sera-8b-ga","company":"allenai","family":"SERA","version":"SERA","score":31.7},{"place":445,"model":"sera-8b","company":"allenai","family":"SERA","version":"SERA","score":31.7},{"place":446,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":31},{"place":447,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":30.8},{"place":448,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.6},{"place":449,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":29.6},{"place":450,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":29.3},{"place":451,"model":"gpt-4o-r2e-gym","company":"openai","family":"GPT","version":"GPT-4o","score":29.3},{"place":452,"model":"spark-x2.5-1.7b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":28.3},{"place":453,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":28.2},{"place":454,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":28},{"place":455,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":28},{"place":456,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.4},{"place":457,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":26.7},{"place":458,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":26},{"place":459,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25.8},{"place":460,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":25},{"place":461,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":24.5},{"place":462,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":24.44},{"place":463,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":24.4},{"place":464,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":23.8},{"place":465,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":23.6},{"place":466,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":23},{"place":467,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":23},{"place":468,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":22.6},{"place":469,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":22.6},{"place":470,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":22},{"place":471,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":21},{"place":472,"model":"rnj-1","company":"essential","family":"Rnj","version":"Rnj 1","score":20.8},{"place":473,"model":"swe-gym-32b","company":"swe-gym","family":"SWE-Gym","version":"SWE-Gym","score":20.6},{"place":474,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":20.5},{"place":475,"model":"internlm3-8b-nex-n1","company":"nex-agi","family":"Nex","version":"Nex-N1","score":20.3},{"place":476,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":19},{"place":477,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":17.7},{"place":478,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":17.4},{"place":479,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":16.8},{"place":480,"model":"g9v3-3b","company":"ai9stars","family":"G9","version":"G9v3","score":16.4},{"place":481,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":16},{"place":482,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":15.4},{"place":483,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15},{"place":484,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":14.4},{"place":485,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":14},{"place":486,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":11.6},{"place":487,"model":"skyrl-agent-8b-v0","company":"novasky","family":"SkyRL","version":"SkyRL-v0","score":9.4},{"place":488,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":7.2},{"place":489,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.8},{"place":490,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":6},{"place":491,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":5.7},{"place":492,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5},{"place":493,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.5},{"place":494,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.4},{"place":495,"model":"codestral-12b-instruct","company":"mistral","family":"Codestral","version":"Codestral","score":3.7},{"place":496,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3},{"place":497,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":2.4},{"place":498,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":2},{"place":499,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":2},{"place":500,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":1.8},{"place":501,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1.8},{"place":502,"model":"gpt-oss-20b-moe","company":"openai","family":"GPT","version":"GPT-OSS","score":1.1},{"place":503,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":1.1},{"place":504,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":0.6},{"place":505,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0.5},{"place":506,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":0.4},{"place":507,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":0.4},{"place":508,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":0.4},{"place":509,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":0},{"place":510,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":511,"model":"allam-7b-instruct-preview","company":"humain","family":"ALLaM","version":"ALLaM","score":0},{"place":512,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":0}]},{"id":"swe-dev","name":"SWE-Dev","topic":"Code repair","description":"Software engineering development and bug fixing benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4","top_percent":67.1,"top_model_id":"claude-sonnet-4","top_generation":"Claude 4","top_model_base":"Claude Sonnet 4","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":67.1},{"place":2,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":66.6},{"place":3,"model":"qwen3-coder-480b-a35b","company":"qwen","family":"Qwen","version":"Qwen3","score":64.7},{"place":4,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":63.2},{"place":5,"model":"kimi-k2-instruct-0711","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":61.9},{"place":6,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":53.3}]},{"id":"swe-fficiency","name":"SWE-fficiency","topic":"Code performance optimization","description":"SWE-fficiency: repository-level performance-optimization tasks; agents must speed up real codebases while keeping tests passing.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":46.6,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":46.6},{"place":2,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":42.2},{"place":3,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":34.8},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":19.7},{"place":5,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":14}]},{"id":"swe-interact","name":"SWE-Interact","topic":"Interactive software engineering","description":"Interactive SWE benchmark (75 tasks) where the agent must clarify underspecified issues with a simulated user before fixing them.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":21.3,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":21.3},{"place":2,"model":"ember-1","company":"fireworks","family":"Ember","version":"Ember-1","score":20},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":13.3},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":6.7}]},{"id":"swe-lancer","name":"SWE-Lancer","topic":"Code repair (freelance tasks)","description":"Software engineering benchmark using real freelance-style issues.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2502.12115","metric":"percent","stars":"","top_model":"GPT-5.1 Codex-Max","top_percent":79.9,"top_model_id":"gpt-5.1-codex-max","top_generation":"GPT-5.1 Codex","top_model_base":"GPT-5.1 Codex-Max","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.1-codex-max","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":79.9},{"place":2,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":40.8},{"place":3,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":39.1},{"place":4,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":38.5},{"place":5,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":37.3},{"place":6,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":30.5},{"place":7,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":24.1},{"place":8,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":23}]},{"id":"swe-lancer-diamond","name":"SWE-Lancer Diamond","topic":"Code repair (freelance)","description":"Diamond subset of SWE-Lancer focusing on the hardest freelance-style issues.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.3 Codex","top_percent":81.4,"top_model_id":"gpt-5.3-codex","top_generation":"GPT-5.3 Codex","top_model_base":"GPT-5.3 Codex","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":81.4},{"place":2,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":76},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":74.6},{"place":4,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":32.6},{"place":5,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":23.3},{"place":6,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":10.8}]},{"id":"swe-lancer-ic-diamond","name":"SWE-Lancer IC Diamond","topic":"Code repair (freelance)","description":"Individual Contributor Diamond subset of SWE-Lancer.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.3 Codex","top_percent":81.4,"top_model_id":"gpt-5.3-codex","top_generation":"GPT-5.3 Codex","top_model_base":"GPT-5.3 Codex","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":81.4},{"place":2,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":76},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":74.6}]},{"id":"swe-marathon","name":"SWE-Marathon","topic":"Software engineering","description":"Abundant AI's SWE-Marathon: very long-horizon software engineering tasks (1M context, max effort).","url":"https://www.abundant.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Wonder Full","top_percent":57.5,"top_model_id":"muse-wonder-full","top_generation":"Muse Wonder","top_model_base":"Muse Wonder Full","top_model_family":"Muse","top_company":"meta","top_open_source":0,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":57.5},{"place":2,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":53.1},{"place":3,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":51.7},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":46.3},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":45.6},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":42.5},{"place":7,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":42.5},{"place":8,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":42},{"place":9,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":40},{"place":10,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":40},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":39},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":35},{"place":13,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":31.9},{"place":14,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":31},{"place":15,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":29},{"place":16,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":26},{"place":17,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":24},{"place":18,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":19},{"place":19,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":16},{"place":20,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":14},{"place":21,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":13},{"place":22,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":12},{"place":23,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":5},{"place":24,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":4},{"place":25,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":1}]},{"id":"swe-marathon-v1.1","name":"SWE-Marathon v1.1","topic":"Software engineering","description":"SWE-Marathon v1.1: very long-horizon software engineering tasks (Abundant AI).","url":"https://www.abundant.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.8","top_percent":48.8,"top_model_id":"claude-opus-4.8","top_generation":"Claude 4.8","top_model_base":"Claude Opus 4.8","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":48.8},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":48.1},{"place":3,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":45},{"place":4,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":42.5},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":42.5},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":33.1},{"place":7,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":19.4}]},{"id":"swe-perf","name":"SWE-Perf","topic":"Code repair","description":"Software engineering benchmark focused on performance-oriented fixes.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":6.5,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":6.5},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4.7},{"place":3,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":3.6},{"place":4,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":3.1},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3},{"place":6,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":1.4},{"place":7,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":0.9}]},{"id":"swe-review","name":"SWE-Review","topic":"Code review","description":"Software engineering review benchmark for assessing code review quality.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":16.2,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":16.2},{"place":2,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":10.5},{"place":3,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":8.9},{"place":4,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":6.4},{"place":5,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":3.4}]},{"id":"swebbench","name":"SWebBench","topic":"Web research agents","description":"iFlytek in-house benchmark for web browsing, information retrieval and research (reported with Spark-X2.6).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Spark-X2.6-4B","top_percent":71.7,"top_model_id":"spark-x2.6-4b","top_generation":"Spark X2.6","top_model_base":"Spark-X2.6-4B","top_model_family":"Spark","top_company":"iflytek","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":71.7},{"place":2,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":46.3},{"place":3,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.3},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.2},{"place":5,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32},{"place":6,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":19.3}]},{"id":"swt-bench","name":"SWT-Bench","topic":"Code repair","description":"Software tool-use benchmark for code tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2 Thinking","top_percent":80.7,"top_model_id":"gpt-5.2-thinking","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":80.7},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.2},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":79.7},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.5},{"place":5,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":69.3},{"place":6,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":62},{"place":7,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":32.8}]},{"id":"sysbench","name":"SysBench","topic":"System prompts","description":"System prompt understanding and adherence benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.6","top_percent":94.9,"top_model_id":"claude-sonnet-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Sonnet 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":94.9},{"place":2,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":93.9},{"place":3,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":93.6},{"place":4,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":93.3},{"place":5,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":91.4},{"place":6,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":91.1},{"place":7,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":90.8},{"place":8,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":90.7},{"place":9,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":87.9},{"place":10,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":86.5},{"place":11,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":86.2},{"place":12,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":82.6},{"place":13,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":74.1},{"place":14,"model":"hunyuan-7b-instruct","company":"tencent","family":"Hunyuan","version":"Hunyuan","score":72.7},{"place":15,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":71.3},{"place":16,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":69.8},{"place":17,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.9},{"place":18,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.88},{"place":19,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.34},{"place":20,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":67.22},{"place":21,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.85},{"place":22,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":65.62},{"place":23,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60.88},{"place":24,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":60.45},{"place":25,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.3}]},{"id":"t-eval","name":"T-Eval","topic":"Tool use","description":"Step-by-step evaluation of LLM tool-utilization (instruct, plan, reason, retrieve, understand, review); EN/ZH average.","url":"https://github.com/open-compass/T-Eval","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2312.14033","metric":"percent","stars":"","top_model":"Qwen 14B Chat","top_percent":66.2,"top_model_id":"qwen-14b-chat","top_generation":"Qwen","top_model_base":"Qwen 14B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":66.2},{"place":2,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":65.8},{"place":3,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":65.5},{"place":4,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":65.4},{"place":5,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":64.4},{"place":6,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":64.3},{"place":7,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":63},{"place":8,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":59.3},{"place":9,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":58.3},{"place":10,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":52.5},{"place":11,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":46.8},{"place":12,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":39},{"place":13,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":37.2}]},{"id":"tabfact","name":"TabFact","topic":"Table fact verification","description":"Table-based fact verification (MMTab subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2.5","top_percent":90.6,"top_model_id":"kimi-k2.5","top_generation":"Kimi K2.5","top_model_base":"Kimi K2.5","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":90.6},{"place":2,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":90.6},{"place":3,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":90.4},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":89.8},{"place":5,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":85.2},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.1},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":63.5},{"place":8,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":52.8},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":30.7}]},{"id":"tabmwp","name":"TabMWP","topic":"Table math","description":"Tabular math word problems (MMTab subset, image tables).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2.5","top_percent":95.9,"top_model_id":"kimi-k2.5","top_generation":"Kimi K2.5","top_model_base":"Kimi K2.5","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":95.9},{"place":2,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":91.8},{"place":3,"model":"yi-coder-9b","company":"01ai","family":"Yi","version":"Yi-Coder","score":81.2},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.1},{"place":5,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":75.3},{"place":6,"model":"codellama-34b","company":"codellama","family":"CodeLlama-34B","version":"CodeLlama-34B","score":69.8},{"place":7,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":67.9},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":67.6},{"place":9,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":67.2},{"place":10,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":65},{"place":11,"model":"codellama-13b","company":"codellama","family":"CodeLlama-13B","version":"CodeLlama-13B","score":60.3},{"place":12,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":52.9},{"place":13,"model":"starcoderbase-16b","company":"bigcode","family":"StarCoder","version":"StarCoder","score":45},{"place":14,"model":"codegeex2-6b","company":"zai","family":"CodeGeeX","version":"CodeGeeX2","score":44.6},{"place":15,"model":"yi-coder-1.5b","company":"01ai","family":"Yi","version":"Yi-Coder","score":36.2},{"place":16,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":30},{"place":17,"model":"codeshell-7b","company":"wisdomshell","family":"CodeShell","version":"CodeShell","score":28.2}]},{"id":"tacit-knowledge-and-troubleshooting","name":"Tacit Knowledge and Troubleshooting","topic":"Biosecurity","description":"OpenAI bio eval of tacit lab knowledge and troubleshooting that requires expertise or practical experience (cons@32).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Luna (2026-10-07)","top_percent":94,"top_model_id":"gpt-6-luna-2026-10-07","top_generation":"GPT-6","top_model_base":"GPT-6 Luna","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":94},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":92.55},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":88.5},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":79.2},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.3},{"place":6,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":72.45},{"place":7,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":69.2}]},{"id":"tallyqa","name":"TallyQA","topic":"Visual counting","description":"TallyQA open-ended counting questions over images (simple and complex).","url":"https://arxiv.org/abs/1810.12440","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"T5Gemma 2 4B-4B","top_percent":39.6,"top_model_id":"t5gemma-2-4b-4b","top_generation":"T5Gemma 2","top_model_base":"T5Gemma 2 4B-4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":39.6},{"place":2,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":32.2},{"place":3,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":26.4}]},{"id":"tat-qa","name":"TAT-QA","topic":"Table QA","description":"Hybrid tabular and textual financial QA (MMTab subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":74.9,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":74.9},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":62.4},{"place":3,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":61.4},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":50.5},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":44.5},{"place":6,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":28}]},{"id":"tau-voice-airline","name":"τ-Voice Airline","topic":"Voice agents","description":"τ-Voice (Sierra): τ-bench airline customer-service tasks over a live speech-to-speech connection; pass^1 (%).","url":"https://sierra.ai/blog/tau-voice","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2603.13686","metric":"percent","stars":"","top_model":"GPT-Live-1 (medium)","top_percent":76.67,"top_model_id":"gpt-live-1-medium","top_generation":"GPT-Live-1","top_model_base":"GPT-Live-1","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":29,"total_models":3854,"placements":[{"place":1,"model":"gpt-live-1-medium","company":"openai","family":"GPT","version":"GPT-Live-1","score":76.67},{"place":2,"model":"gpt-live-1-low","company":"openai","family":"GPT","version":"GPT-Live-1","score":76},{"place":3,"model":"gemini-3.8-live-extended-thinking-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":72},{"place":4,"model":"grok-voice-3.0","company":"xai","family":"Grok","version":"Grok Voice","score":69.33},{"place":5,"model":"grok-voice-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":66},{"place":6,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":64},{"place":7,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":62.67},{"place":8,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":62},{"place":9,"model":"qwen-audio-3.0-realtime-plus","company":"qwen","family":"Qwen","version":"Qwen Audio 3.0","score":61.33},{"place":10,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":60},{"place":11,"model":"grok-voice-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":58},{"place":12,"model":"gpt-realtime-2.0-medium","company":"openai","family":"GPT","version":"GPT-realtime-2","score":56.67},{"place":13,"model":"grok-voice-2.0","company":"xai","family":"Grok","version":"Grok Voice","score":56},{"place":14,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.67},{"place":15,"model":"qwen-audio-3.0-realtime-flash","company":"qwen","family":"Qwen","version":"Qwen Audio 3.0","score":54},{"place":16,"model":"gpt-realtime-2.1","company":"openai","family":"GPT","version":"GPT-realtime-2","score":52.67},{"place":17,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":52},{"place":18,"model":"gemini-3.8-live","company":"google","family":"Gemini","version":"Gemini 3.8","score":48.67},{"place":19,"model":"gpt-realtime-2.1-mini-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":47.33},{"place":20,"model":"higgs-realtime","company":"bosonai","family":"Higgs","version":"Higgs Realtime","score":46},{"place":21,"model":"eleven-realtime-v1-mini","company":"elevenlabs","family":"Eleven","version":"Eleven Realtime v1","score":45.33},{"place":22,"model":"deepslate-opal","company":"deepslate","family":"Deepslate","version":"Deepslate Opal","score":45.33},{"place":23,"model":"gemini-2.5-flash-native-audio-preview-12-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":44},{"place":24,"model":"eleven-realtime-v1-max","company":"elevenlabs","family":"Eleven","version":"Eleven Realtime v1","score":44},{"place":25,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":43.33},{"place":26,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":41.33},{"place":27,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":40},{"place":28,"model":"grok-voice-fast-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":38.67},{"place":29,"model":"gpt-realtime-2.1-mini","company":"openai","family":"GPT","version":"GPT-realtime-2","score":36},{"place":30,"model":"grok-voice-fast-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":36},{"place":31,"model":"gpt-4o-realtime-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o","score":33.33},{"place":32,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":31.33},{"place":33,"model":"gpt-realtime-mini","company":"openai","family":"GPT","version":"GPT Realtime","score":22}]},{"id":"tau-voice-retail","name":"τ-Voice Retail","topic":"Voice agents","description":"τ-Voice (Sierra): τ-bench retail customer-service tasks over a live speech-to-speech connection; pass^1 (%).","url":"https://sierra.ai/blog/tau-voice","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2603.13686","metric":"percent","stars":"","top_model":"GPT-Live-1 (medium)","top_percent":72.51,"top_model_id":"gpt-live-1-medium","top_generation":"GPT-Live-1","top_model_base":"GPT-Live-1","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":29,"total_models":3854,"placements":[{"place":1,"model":"gpt-live-1-medium","company":"openai","family":"GPT","version":"GPT-Live-1","score":72.51},{"place":2,"model":"grok-voice-3.0","company":"xai","family":"Grok","version":"Grok Voice","score":66.08},{"place":3,"model":"grok-voice-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":62.3},{"place":4,"model":"gpt-live-1-low","company":"openai","family":"GPT","version":"GPT-Live-1","score":56.14},{"place":5,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":51.46},{"place":6,"model":"gemini-3.8-live-extended-thinking-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":50},{"place":7,"model":"grok-voice-2.0","company":"xai","family":"Grok","version":"Grok Voice","score":49.71},{"place":8,"model":"qwen-audio-3.0-realtime-plus","company":"qwen","family":"Qwen","version":"Qwen Audio 3.0","score":48.96},{"place":9,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":45.61},{"place":10,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":45.6},{"place":11,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":44.7},{"place":12,"model":"grok-voice-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":44.15},{"place":13,"model":"gpt-realtime-2.1","company":"openai","family":"GPT","version":"GPT-realtime-2","score":41.23},{"place":14,"model":"eleven-realtime-v1-max","company":"elevenlabs","family":"Eleven","version":"Eleven Realtime v1","score":40.06},{"place":15,"model":"grok-voice-fast-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":38.6},{"place":16,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":37.72},{"place":17,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":37.7},{"place":18,"model":"eleven-realtime-v1-mini","company":"elevenlabs","family":"Eleven","version":"Eleven Realtime v1","score":36.55},{"place":19,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":36.26},{"place":20,"model":"gpt-realtime-2.0-medium","company":"openai","family":"GPT","version":"GPT-realtime-2","score":33.63},{"place":21,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":33.33},{"place":22,"model":"gpt-4o-realtime-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o","score":31.58},{"place":23,"model":"gemini-3.8-live","company":"google","family":"Gemini","version":"Gemini 3.8","score":29.24},{"place":24,"model":"qwen-audio-3.0-realtime-flash","company":"qwen","family":"Qwen","version":"Qwen Audio 3.0","score":29.24},{"place":25,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":21.93},{"place":26,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":21.93},{"place":27,"model":"grok-voice-fast-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":21.93},{"place":28,"model":"gpt-realtime-2.1-mini-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":19.88},{"place":29,"model":"gpt-realtime-mini","company":"openai","family":"GPT","version":"GPT Realtime","score":15.79},{"place":30,"model":"gpt-realtime-2.1-mini","company":"openai","family":"GPT","version":"GPT-realtime-2","score":13.16},{"place":31,"model":"gemini-2.5-flash-native-audio-preview-12-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":9.36},{"place":32,"model":"deepslate-opal","company":"deepslate","family":"Deepslate","version":"Deepslate Opal","score":5.85},{"place":33,"model":"higgs-realtime","company":"bosonai","family":"Higgs","version":"Higgs Realtime","score":5.26}]},{"id":"tau-voice-telecom","name":"τ-Voice Telecom","topic":"Voice agents","description":"τ-Voice (Sierra): τ²-bench telecom tasks over a live speech-to-speech connection; pass^1 (%).","url":"https://sierra.ai/blog/tau-voice","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2603.13686","metric":"percent","stars":"","top_model":"Gemini 3.8 Live Extended Thinking (high)","top_percent":83.92,"top_model_id":"gemini-3.8-live-extended-thinking-high","top_generation":"Gemini 3.8","top_model_base":"Gemini 3.8 Live Extended Thinking","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":29,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.8-live-extended-thinking-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":83.92},{"place":2,"model":"grok-voice-3.0","company":"xai","family":"Grok","version":"Grok Voice","score":79.53},{"place":3,"model":"gpt-live-1-medium","company":"openai","family":"GPT","version":"GPT-Live-1","score":74.27},{"place":4,"model":"grok-voice-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":73.7},{"place":5,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":70.2},{"place":6,"model":"grok-voice-2.0","company":"xai","family":"Grok","version":"Grok Voice","score":63.74},{"place":7,"model":"eleven-realtime-v1-max","company":"elevenlabs","family":"Eleven","version":"Eleven Realtime v1","score":58.77},{"place":8,"model":"eleven-realtime-v1-mini","company":"elevenlabs","family":"Eleven","version":"Eleven Realtime v1","score":58.48},{"place":9,"model":"grok-voice-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":54.09},{"place":10,"model":"qwen-audio-3.0-realtime-plus","company":"qwen","family":"Qwen","version":"Qwen Audio 3.0","score":53.51},{"place":11,"model":"gpt-live-1-low","company":"openai","family":"GPT","version":"GPT-Live-1","score":45.61},{"place":12,"model":"grok-voice-fast-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":40.4},{"place":13,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":29.39},{"place":14,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":28.72},{"place":15,"model":"qwen-audio-3.0-realtime-flash","company":"qwen","family":"Qwen","version":"Qwen Audio 3.0","score":24.56},{"place":16,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":23.68},{"place":17,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":22.22},{"place":18,"model":"gpt-realtime","company":"openai","family":"GPT","version":"GPT Realtime","score":22.22},{"place":19,"model":"gpt-realtime-2.0-medium","company":"openai","family":"GPT","version":"GPT-realtime-2","score":21.93},{"place":20,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":21.9},{"place":21,"model":"grok-voice-fast-1.0","company":"xai","family":"Grok","version":"Grok Voice","score":21.64},{"place":22,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":21.1},{"place":23,"model":"gpt-realtime-2.1-mini-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":21.05},{"place":24,"model":"gpt-realtime-2.1","company":"openai","family":"GPT","version":"GPT-realtime-2","score":20.18},{"place":25,"model":"gpt-4o-realtime-preview-2024-12-17","company":"openai","family":"GPT","version":"GPT-4o","score":18.71},{"place":26,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":18.42},{"place":27,"model":"gpt-realtime-2.1-mini","company":"openai","family":"GPT","version":"GPT-realtime-2","score":18.42},{"place":28,"model":"gemini-2.5-flash-native-audio-preview-12-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":15.04},{"place":29,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":13.45},{"place":30,"model":"gemini-3.8-live","company":"google","family":"Gemini","version":"Gemini 3.8","score":12.28},{"place":31,"model":"gpt-realtime-mini","company":"openai","family":"GPT","version":"GPT Realtime","score":7.6},{"place":32,"model":"higgs-realtime","company":"bosonai","family":"Higgs","version":"Higgs Realtime","score":4.68},{"place":33,"model":"deepslate-opal","company":"deepslate","family":"Deepslate","version":"Deepslate Opal","score":1.47}]},{"id":"tau1-airline","name":"TAU1-Airline","topic":"Agent tasks (airline)","description":"Tool-augmented agent evaluation in airline scenarios (TAU1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"openPangu-R-72B-2512 Slow Thinking","top_percent":56,"top_model_id":"openpangu-r-72b-2512-slow-thinking","top_generation":"openPangu-R","top_model_base":"openPangu-R 72B","top_model_family":"openPangu-R","top_company":"freedomintelligence","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":56},{"place":2,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":54},{"place":3,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":50},{"place":4,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":49},{"place":5,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":48},{"place":6,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":46},{"place":7,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":45.3},{"place":8,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":44},{"place":9,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":44},{"place":10,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":42.7},{"place":11,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":40},{"place":12,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":29},{"place":13,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":17}]},{"id":"tau1-retail","name":"TAU1-Retail","topic":"Agent tasks (retail)","description":"Tool-augmented agent evaluation in retail scenarios (TAU1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"openPangu-R-72B-2512 Slow Thinking","top_percent":73,"top_model_id":"openpangu-r-72b-2512-slow-thinking","top_generation":"openPangu-R","top_model_base":"openPangu-R 72B","top_model_family":"openPangu-R","top_company":"freedomintelligence","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":73},{"place":2,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.3},{"place":3,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":70.1},{"place":4,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":69.6},{"place":5,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":69},{"place":6,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":67.8},{"place":7,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":67.8},{"place":8,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":65.2},{"place":9,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":61.7},{"place":10,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":60.9},{"place":11,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":59.1},{"place":12,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":52.8},{"place":13,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":40.1}]},{"id":"tau2-airline","name":"TAU2-Airline","topic":"Agent tasks (airline)","description":"Tool-augmented agent evaluation in airline scenarios (TAU2).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.7","top_percent":88.5,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":101,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":88.5},{"place":2,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":88},{"place":3,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.5},{"place":4,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83.3},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82.5},{"place":6,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82},{"place":7,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":82},{"place":8,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":82},{"place":9,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":81.8},{"place":10,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":80.8},{"place":11,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":80.5},{"place":12,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":80.5},{"place":13,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":80},{"place":14,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":80},{"place":15,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.8},{"place":16,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":79.25},{"place":17,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":78},{"place":18,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":78},{"place":19,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":78},{"place":20,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":77.5},{"place":21,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":77.25},{"place":22,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":77.25},{"place":23,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":76.7},{"place":24,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":76.5},{"place":25,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":76.5},{"place":26,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":76.5},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.5},{"place":28,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76},{"place":29,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.3},{"place":30,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":73},{"place":31,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":72.7},{"place":32,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.7},{"place":33,"model":"areal-sea-235b-a22b","company":"antgroup","family":"AReaL-SEA","version":"AReaL-SEA","score":71},{"place":34,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71},{"place":35,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":70.7},{"place":36,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":70.7},{"place":37,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70},{"place":38,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":68.7},{"place":39,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.5},{"place":40,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":66},{"place":41,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66},{"place":42,"model":"ember-1","company":"fireworks","family":"Ember","version":"Ember-1","score":66},{"place":43,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":65.3},{"place":44,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":65.3},{"place":45,"model":"o3","company":"openai","family":"o3","version":"o3","score":64.8},{"place":46,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":64},{"place":47,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":63.8},{"place":48,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.6},{"place":49,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.5},{"place":50,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":63},{"place":51,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":63},{"place":52,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":62.7},{"place":53,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":62.6},{"place":54,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":62.5},{"place":55,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":62},{"place":56,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62},{"place":57,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":61.33},{"place":58,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":60.8},{"place":59,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":60.5},{"place":60,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":60.5},{"place":61,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":60.4},{"place":62,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":60},{"place":63,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":60},{"place":64,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":60},{"place":65,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":59.6},{"place":66,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":59.33},{"place":67,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":59.3},{"place":68,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":58.7},{"place":69,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":58.6},{"place":70,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":58},{"place":71,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":58},{"place":72,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":58},{"place":73,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":58},{"place":74,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":58},{"place":75,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58},{"place":76,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":58},{"place":77,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56.9},{"place":78,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.66},{"place":79,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":56.5},{"place":80,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":56.5},{"place":81,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":56.5},{"place":82,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56.25},{"place":83,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":56},{"place":84,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":55.8},{"place":85,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":55.5},{"place":86,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":54.5},{"place":87,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":54},{"place":88,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":53.5},{"place":89,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":52.8},{"place":90,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":52.7},{"place":91,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":52.67},{"place":92,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":52.4},{"place":93,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":52},{"place":94,"model":"o3","company":"openai","family":"o3","version":"o3","score":52},{"place":95,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":52},{"place":96,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":52},{"place":97,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":52},{"place":98,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":50},{"place":99,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":50},{"place":100,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":49.2},{"place":101,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":48},{"place":102,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":47.33},{"place":103,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":45.5},{"place":104,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":45.5},{"place":105,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":45.5},{"place":106,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":45.3},{"place":107,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":44.67},{"place":108,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":44},{"place":109,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":44},{"place":110,"model":"nemotron-labs-3-elastic-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":43.33},{"place":111,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":42.5},{"place":112,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":40},{"place":113,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":40},{"place":114,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":39},{"place":115,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":38},{"place":116,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":38},{"place":117,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":35},{"place":118,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":34.7},{"place":119,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":33.3},{"place":120,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":32},{"place":121,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":28},{"place":122,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":27},{"place":123,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":26.5},{"place":124,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":24}]},{"id":"tau2-airline-verified","name":"TAU2-Bench Airline (Verified)","topic":"Agent tasks","description":"Human-validated revision of the tau2-bench airline domain (amazon-agi/tau2-bench-verified).","url":"https://github.com/amazon-agi/tau2-bench-verified","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.1","top_percent":72.4,"top_model_id":"gpt-5.1","top_generation":"GPT-5.1","top_model_base":"GPT-5.1","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":72.4},{"place":2,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":72},{"place":3,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":70.8},{"place":4,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":68.8},{"place":5,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":68.8},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66.8},{"place":7,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":65.2},{"place":8,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":64.8},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":60},{"place":10,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54},{"place":11,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":44}]},{"id":"tau2-bench","name":"TAU2-Bench","topic":"Agent tasks","description":"Aggregate tool-augmented agent evaluation across airline, retail, and telecom scenarios (TAU2).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":91.6,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":91.6},{"place":2,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":87.1},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.7},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85.4},{"place":5,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.6},{"place":6,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77},{"place":7,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":68.1},{"place":8,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":59.78},{"place":9,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":34.58}]},{"id":"tau2-retail","name":"TAU2-Retail","topic":"Agent tasks (retail)","description":"Tool-augmented agent evaluation in retail scenarios (TAU2).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":91.9,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":114,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.9},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.9},{"place":3,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":91.7},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":90.8},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88.9},{"place":6,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88.9},{"place":7,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":88.9},{"place":8,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":88.6},{"place":9,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":86.8},{"place":10,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":86.8},{"place":11,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":86.2},{"place":12,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":86.2},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85.3},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":85.3},{"place":15,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":85.09},{"place":16,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":85.09},{"place":17,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.7},{"place":18,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":83.8},{"place":19,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.77},{"place":20,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":83.22},{"place":21,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83.2},{"place":22,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":82.79},{"place":23,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":82.68},{"place":24,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":82.4},{"place":25,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":82},{"place":26,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":82},{"place":27,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":82},{"place":28,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":81.8},{"place":29,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":81.8},{"place":30,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":81.8},{"place":31,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":81.8},{"place":32,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.6},{"place":33,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":81.4},{"place":34,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":81.14},{"place":35,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":81.1},{"place":36,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":81.1},{"place":37,"model":"o3","company":"openai","family":"o3","version":"o3","score":80.2},{"place":38,"model":"areal-sea-235b-a22b","company":"antgroup","family":"AReaL-SEA","version":"AReaL-SEA","score":79},{"place":39,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":78.7},{"place":40,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":78.6},{"place":41,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":78.3},{"place":42,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":78.2},{"place":43,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":78.07},{"place":44,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":77.9},{"place":45,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":77.9},{"place":46,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":77.85},{"place":47,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":76.5},{"place":48,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":75.73},{"place":49,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":75.4},{"place":50,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":75},{"place":51,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":74.8},{"place":52,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":74.6},{"place":53,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":74.34},{"place":54,"model":"o3","company":"openai","family":"o3","version":"o3","score":73.9},{"place":55,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":73.8},{"place":56,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":73.7},{"place":57,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":73.68},{"place":58,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":73.39},{"place":59,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":73.1},{"place":60,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":72.15},{"place":61,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.93},{"place":62,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":71.9},{"place":63,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":71.9},{"place":64,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":71.8},{"place":65,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":71.6},{"place":66,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":71.6},{"place":67,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":71.4},{"place":68,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":71.3},{"place":69,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":71.3},{"place":70,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.8},{"place":71,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":70.6},{"place":72,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":69.9},{"place":73,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.8},{"place":74,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":69.24},{"place":75,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":69.1},{"place":76,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":69.1},{"place":77,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":68.7},{"place":78,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":68.4},{"place":79,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":67.8},{"place":80,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":67.8},{"place":81,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":67.8},{"place":82,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":67.55},{"place":83,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":67.5},{"place":84,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":67.5},{"place":85,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67},{"place":86,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67},{"place":87,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.7},{"place":88,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":66.67},{"place":89,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":66.4},{"place":90,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64.9},{"place":91,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":64.3},{"place":92,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64.3},{"place":93,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":63.9},{"place":94,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":63.5},{"place":95,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":63.4},{"place":96,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":63.2},{"place":97,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":62.9},{"place":98,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":62.83},{"place":99,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.6},{"place":100,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":62.28},{"place":101,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.69},{"place":102,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":61.4},{"place":103,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":61.4},{"place":104,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":60.8},{"place":105,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":60.5},{"place":106,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":59.94},{"place":107,"model":"nemotron-labs-3-elastic-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":59.36},{"place":108,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":59.3},{"place":109,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":58.8},{"place":110,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.6},{"place":111,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":58.5},{"place":112,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":57.9},{"place":113,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":57.3},{"place":114,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":57},{"place":115,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":57},{"place":116,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56.9},{"place":117,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":56.43},{"place":118,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":56.14},{"place":119,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":55.7},{"place":120,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.4},{"place":121,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55.26},{"place":122,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":53.51},{"place":123,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":53.51},{"place":124,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":53.51},{"place":125,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":49.7},{"place":126,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":48.8},{"place":127,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":46.78},{"place":128,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.11},{"place":129,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":40.8},{"place":130,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":39.82},{"place":131,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":39.8},{"place":132,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":38},{"place":133,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":37.5},{"place":134,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":34.8},{"place":135,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":18.95},{"place":136,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":18.86},{"place":137,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":18.42},{"place":138,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":17.84},{"place":139,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":13.68},{"place":140,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":9.6},{"place":141,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":7.02},{"place":142,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":7.02},{"place":143,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":6.43},{"place":144,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":6.14},{"place":145,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":6.14},{"place":146,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.14},{"place":147,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":5.56}]},{"id":"tau2-retail-verified","name":"TAU2-Bench Retail (Verified)","topic":"Agent tasks","description":"Human-validated revision of the tau2-bench retail domain (amazon-agi/tau2-bench-verified).","url":"https://github.com/amazon-agi/tau2-bench-verified","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5","top_percent":78.3,"top_model_id":"gpt-5","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":78.3},{"place":2,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":78.3},{"place":3,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":77.7},{"place":4,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":77.7},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":77.5},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.2},{"place":7,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":76.5},{"place":8,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":73.7},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.3},{"place":10,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":69.1},{"place":11,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.7}]},{"id":"tau2-telecom","name":"TAU2-Telecom","topic":"Agent tasks (telecom)","description":"Tool-augmented agent evaluation in telecom scenarios (TAU2).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.6-35B-A3B","top_percent":100,"top_model_id":"qwen3.6-35b-a3b","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 35B A3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":203,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":100},{"place":2,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":99.3},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":99.3},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":99.3},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":99.3},{"place":6,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":99.3},{"place":7,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":99.12},{"place":8,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":99.1},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":98.9},{"place":10,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":98.7},{"place":11,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":98.7},{"place":12,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":98.7},{"place":13,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":98.68},{"place":14,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":98.5},{"place":15,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":98.3},{"place":16,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.2},{"place":17,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.2},{"place":18,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98.2},{"place":19,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":98.2},{"place":20,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":98.2},{"place":21,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":98},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98},{"place":23,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":98},{"place":25,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98},{"place":26,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":98},{"place":27,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":97.9},{"place":28,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":97.7},{"place":29,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97.7},{"place":30,"model":"longcat-flash-thinking-zigzag","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":97.4},{"place":31,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":97.1},{"place":32,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":96.8},{"place":33,"model":"ring-2.6-1t-high","company":"antgroup","family":"Ring","version":"Ring 2.6","score":96.71},{"place":34,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":96.7},{"place":35,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":96.5},{"place":36,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":96.2},{"place":37,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":96.2},{"place":38,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":96.05},{"place":39,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":95.9},{"place":40,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":95.9},{"place":41,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":95.9},{"place":42,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":95.8},{"place":43,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":95.8},{"place":44,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":95.6},{"place":45,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.6},{"place":46,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":95.18},{"place":47,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95},{"place":48,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":95},{"place":49,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":94.96},{"place":50,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":94.7},{"place":51,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":94.7},{"place":52,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":94.7},{"place":53,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":94.7},{"place":54,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":93.9},{"place":55,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":93.5},{"place":56,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":93.4},{"place":57,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":93},{"place":58,"model":"areal-sea-235b-a22b","company":"antgroup","family":"AReaL-SEA","version":"AReaL-SEA","score":93},{"place":59,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":92.8},{"place":60,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":92.7},{"place":61,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":92.5},{"place":62,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":92.1},{"place":63,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.1},{"place":64,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":91.5},{"place":65,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":91.5},{"place":66,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":91},{"place":67,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.4},{"place":68,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":90.4},{"place":69,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":90.1},{"place":70,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90},{"place":71,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":88.9},{"place":72,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":88.6},{"place":73,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":88.07},{"place":74,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.72},{"place":75,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":87.5},{"place":76,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.2},{"place":77,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":87.1},{"place":78,"model":"gpt-5-codex-high","company":"openai","family":"GPT","version":"GPT-5","score":87},{"place":79,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":87},{"place":80,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":87},{"place":81,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87},{"place":82,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":87},{"place":83,"model":"midm-k-2.5-pro","company":"kt","family":"Mi:dm","version":"Mi:dm K 2.5","score":87},{"place":84,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":86.8},{"place":85,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86.5},{"place":86,"model":"ax-k1","company":"skt","family":"A.X","version":"A.X","score":86},{"place":87,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.8},{"place":88,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":85},{"place":89,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":85},{"place":90,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":85},{"place":91,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":84.8},{"place":92,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":84.8},{"place":93,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":84.2},{"place":94,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.3},{"place":95,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":83.11},{"place":96,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":83},{"place":97,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83},{"place":98,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82.5},{"place":99,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":81.9},{"place":100,"model":"tri-21b-think","company":"trillionlabs","family":"Tri","version":"Tri","score":81},{"place":101,"model":"o3","company":"openai","family":"o3","version":"o3","score":80.7},{"place":102,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":80},{"place":103,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":80},{"place":104,"model":"joyai-llm-flash","company":"jd","family":"JoyAI-LLM","version":"JoyAI-LLM","score":79.83},{"place":105,"model":"minicpm5-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":79.53},{"place":106,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":79.28},{"place":107,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78.1},{"place":108,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":78},{"place":109,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":76.75},{"place":110,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":76},{"place":111,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":75.7},{"place":112,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":75},{"place":113,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":74.9},{"place":114,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":74.23},{"place":115,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":74.1},{"place":116,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":74.01},{"place":117,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":73.5},{"place":118,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73.4},{"place":119,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73.4},{"place":120,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":73.19},{"place":121,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":73.1},{"place":122,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":73},{"place":123,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":73},{"place":124,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":72.8},{"place":125,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":71.7},{"place":126,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":71.5},{"place":127,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":71.4},{"place":128,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":71.1},{"place":129,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":71},{"place":130,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":71},{"place":131,"model":"gpt-5-mini-medium","company":"openai","family":"GPT","version":"GPT-5","score":71},{"place":132,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":70.5},{"place":133,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":69},{"place":134,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69},{"place":135,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":68.4},{"place":136,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":68.1},{"place":137,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":68},{"place":138,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":68},{"place":139,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":67.5},{"place":140,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":67},{"place":141,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":66},{"place":142,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":66},{"place":143,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":65.8},{"place":144,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":65.8},{"place":145,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":65.8},{"place":146,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":65.8},{"place":147,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":65.8},{"place":148,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":64.6},{"place":149,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":64.36},{"place":150,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":64.3},{"place":151,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":63.7},{"place":152,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":62.06},{"place":153,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":61.7},{"place":154,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":61.5},{"place":155,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":61.1},{"place":156,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":60.5},{"place":157,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":60.3},{"place":158,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":60.2},{"place":159,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":60.2},{"place":160,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":60},{"place":161,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":57.8},{"place":162,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":57.8},{"place":163,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":57.7},{"place":164,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":57.24},{"place":165,"model":"gpt-5.2-none","company":"openai","family":"GPT","version":"GPT-5.2","score":57.2},{"place":166,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":57},{"place":167,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":55.6},{"place":168,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55},{"place":169,"model":"claude-4.5-haiku-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55},{"place":170,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.7},{"place":171,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.1},{"place":172,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54},{"place":173,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":53.8},{"place":174,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":53.2},{"place":175,"model":"qwen3-235b-a22b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":53.2},{"place":176,"model":"qwen3-235b-a22b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":53},{"place":177,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":53},{"place":178,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":52},{"place":179,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.8},{"place":180,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":50.2},{"place":181,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":49.7},{"place":182,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":49.6},{"place":183,"model":"openpangu-r-72b-2512-slow-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":49.4},{"place":184,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":49},{"place":185,"model":"gpt-4.1-mini","company":"openai","family":"GPT","version":"GPT-4.1","score":48.9},{"place":186,"model":"openpangu-r-72b-2512-fast-thinking","company":"freedomintelligence","family":"openPangu-R","version":"openPangu-R","score":48.8},{"place":187,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.7},{"place":188,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":47.4},{"place":189,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":47.3},{"place":190,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":46.5},{"place":191,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":46},{"place":192,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":45.9},{"place":193,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":45.6},{"place":194,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":45.6},{"place":195,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":45.3},{"place":196,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":45.2},{"place":197,"model":"gpt-5.1-none","company":"openai","family":"GPT","version":"GPT-5.1","score":45.2},{"place":198,"model":"openpangu-r-7b-2512-slow-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":45},{"place":199,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.7},{"place":200,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":43.9},{"place":201,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":43.6},{"place":202,"model":"openpangu-r-7b-2512-fast-thinking","company":"huawei","family":"openPangu-R","version":"openPangu-R","score":43},{"place":203,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":42.2},{"place":204,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.11},{"place":205,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":41.5},{"place":206,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":41.5},{"place":207,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":40.9},{"place":208,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":38.6},{"place":209,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":38.3},{"place":210,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":37.1},{"place":211,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":37},{"place":212,"model":"command-a-reasoning-08-2025","company":"cohere","family":"Command","version":"Command","score":37},{"place":213,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":36.5},{"place":214,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":34},{"place":215,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":34},{"place":216,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":33.9},{"place":217,"model":"nemotron-labs-3-elastic-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":33.33},{"place":218,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":33},{"place":219,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33},{"place":220,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":32.5},{"place":221,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":32.5},{"place":222,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":32},{"place":223,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":32},{"place":224,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":31.6},{"place":225,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":31.6},{"place":226,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":31.5},{"place":227,"model":"gemini-2.5-flash-lite-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":31},{"place":228,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":31},{"place":229,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":30.99},{"place":230,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":29.8},{"place":231,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.36},{"place":232,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":28.1},{"place":233,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":28.1},{"place":234,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":28.1},{"place":235,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":28},{"place":236,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":27.8},{"place":237,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":27.8},{"place":238,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":27.2},{"place":239,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.75},{"place":240,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":26.3},{"place":241,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":26},{"place":242,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":25.4},{"place":243,"model":"falcon-h1r-7b","company":"tii","family":"Falcon","version":"Falcon H1R","score":25.4},{"place":244,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":24.9},{"place":245,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":24.6},{"place":246,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":24.6},{"place":247,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":23.7},{"place":248,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":22.37},{"place":249,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":22.1},{"place":250,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.93},{"place":251,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":21.93},{"place":252,"model":"qwen3-0.6b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.1},{"place":253,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":20.8},{"place":254,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":20.8},{"place":255,"model":"lfm2.5-1.2b-thinking","company":"liquidai","family":"LFM","version":"LFM2.5","score":19.6},{"place":256,"model":"lfm2.5-350m","company":"liquidai","family":"LFM","version":"LFM2.5","score":18.86},{"place":257,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":18},{"place":258,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":17.8},{"place":259,"model":"amazon-nova-lite-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":17.5},{"place":260,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":17.3},{"place":261,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":17},{"place":262,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.9},{"place":263,"model":"granite-4.0-h-tiny","company":"IBM","family":"Granite","version":"Granite 4.0","score":16.67},{"place":264,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":16.1},{"place":265,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":15.68},{"place":266,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.33},{"place":267,"model":"amazon-nova-pro-v1.0","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":14},{"place":268,"model":"granite-4-h-300m","company":"IBM","family":"Granite","version":"Granite 4","score":13.74},{"place":269,"model":"lfm2-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2","score":13.6},{"place":270,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":13.2},{"place":271,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12.57},{"place":272,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":12.3},{"place":273,"model":"nemotron-h-47b-reasoning","company":"nvidia","family":"Nemotron-H","version":"Nemotron-H","score":11.4},{"place":274,"model":"lfm2-350m","company":"liquidai","family":"LFM","version":"LFM2","score":10.82},{"place":275,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":10.8},{"place":276,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":9.36},{"place":277,"model":"lfm2.5-230m","company":"liquidai","family":"LFM","version":"LFM2.5","score":5.26},{"place":278,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":4.39},{"place":279,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":4.39},{"place":280,"model":"granite-4-300m","company":"IBM","family":"Granite","version":"Granite 4","score":2.92}]},{"id":"tau3-airline","name":"τ³-Bench Airline","topic":"Agent tasks (airline)","description":"τ³-Bench airline domain: tool-augmented customer-service agent with simulated user.","url":"https://github.com/sierra-research/tau2-bench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K2.6 Thinking","top_percent":85.8,"top_model_id":"kimi-k2.6-thinking","top_generation":"Kimi K2.6","top_model_base":"Kimi K2.6","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":85.8},{"place":2,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":85},{"place":3,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":83},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.5},{"place":5,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":81.5},{"place":6,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.8},{"place":7,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.8},{"place":8,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":79.5},{"place":9,"model":"mercury-voice","company":"inception","family":"Mercury","version":"Mercury 2.5","score":78},{"place":10,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":76.5},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.5},{"place":12,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":75.3},{"place":13,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":72},{"place":14,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72},{"place":15,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":66},{"place":16,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":54},{"place":17,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":53.5},{"place":18,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":41.5},{"place":19,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":38.5}]},{"id":"tau3-banking","name":"τ³-Bench Banking","topic":"Agent tasks (banking)","description":"τ³-Bench banking domain: tool-augmented customer-service agent with knowledge retrieval and simulated user.","url":"https://github.com/sierra-research/tau2-bench","leaderboard":"https://taubench.com/","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":55.2,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":121,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":55.2},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":54.6},{"place":3,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":50.3},{"place":4,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":50},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":48.7},{"place":6,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":48},{"place":7,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":47.8},{"place":8,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":47.2},{"place":9,"model":"solar-mini-4","company":"upstage","family":"Solar","version":"Solar Mini 4","score":47.2},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.9},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":46},{"place":12,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":44.5},{"place":13,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":44.3},{"place":14,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":44.3},{"place":15,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":43.3},{"place":16,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":42.5},{"place":17,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":42.1},{"place":18,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":41.2},{"place":19,"model":"ling-3.0-flash-fin","company":"antgroup","family":"Ling","version":"Ling 3.0","score":41},{"place":20,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":40.2},{"place":21,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":39.6},{"place":22,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.6},{"place":23,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":38.1},{"place":24,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":38},{"place":25,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":37.3},{"place":26,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":37.1},{"place":27,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":37.1},{"place":28,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":37.1},{"place":29,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":36.1},{"place":30,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":35.3},{"place":31,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":34.8},{"place":32,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":34.6},{"place":33,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":34},{"place":34,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":33.4},{"place":35,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":33},{"place":36,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":32.8},{"place":37,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":31.3},{"place":38,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":31.1},{"place":39,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":30.5},{"place":40,"model":"mercury-3","company":"inception","family":"Mercury","version":"Mercury 3","score":30.24},{"place":41,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":30.1},{"place":42,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":29.1},{"place":43,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":28.7},{"place":44,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":28.4},{"place":45,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":28},{"place":46,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":27.6},{"place":47,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":26.8},{"place":48,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":26.8},{"place":49,"model":"k2-horizon-mova-36b-a4b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":26.8},{"place":50,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":26.7},{"place":51,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":25.9},{"place":52,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":25.8},{"place":53,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":25.8},{"place":54,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":25.8},{"place":55,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":25},{"place":56,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":24.3},{"place":57,"model":"k2-horizon-32b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":24.1},{"place":58,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":24},{"place":59,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":23.7},{"place":60,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":23.5},{"place":61,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":23.3},{"place":62,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":23.1},{"place":63,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":23},{"place":64,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":23},{"place":65,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":22.9},{"place":66,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":22.9},{"place":67,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":22.68},{"place":68,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":22.6},{"place":69,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":22.4},{"place":70,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":22.3},{"place":71,"model":"g9v3-39a5b","company":"ai9stars","family":"G9","version":"G9v3","score":22.1},{"place":72,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":21.7},{"place":73,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":21.7},{"place":74,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":21.13},{"place":75,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":20.9},{"place":76,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":20.88},{"place":77,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":20.8},{"place":78,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":20.8},{"place":79,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":20.75},{"place":80,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":20.6},{"place":81,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":20.6},{"place":82,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":20.6},{"place":83,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":20.6},{"place":84,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":19.6},{"place":85,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":18.88},{"place":86,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":18.4},{"place":87,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":18.17},{"place":88,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":18.1},{"place":89,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":17.7},{"place":90,"model":"nemotron-3.5-bolt-74b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":17.01},{"place":91,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":16.7},{"place":92,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":16.5},{"place":93,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":16.5},{"place":94,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":16.2},{"place":95,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":16},{"place":96,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":15.5},{"place":97,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":15.5},{"place":98,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":15.3},{"place":99,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":15.1},{"place":100,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":14.9},{"place":101,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":14.8},{"place":102,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":14.7},{"place":103,"model":"nemotron-labs-dory1.0-4b-4loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":14.69},{"place":104,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":14.6},{"place":105,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":14.6},{"place":106,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":14.4},{"place":107,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.2},{"place":108,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":14.2},{"place":109,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":14.2},{"place":110,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":14.2},{"place":111,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":14.02},{"place":112,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":13.8},{"place":113,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":13.66},{"place":114,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":13.6},{"place":115,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":13.4},{"place":116,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":13.4},{"place":117,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":13.2},{"place":118,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":13.06},{"place":119,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":13},{"place":120,"model":"nemotron-labs-dory1.0-4b","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":12.89},{"place":121,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":12.8},{"place":122,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":12.37},{"place":123,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":12},{"place":124,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":11.9},{"place":125,"model":"nemotron-labs-dory1.0-4b-1loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":11.6},{"place":126,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":11.5},{"place":127,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":11.3},{"place":128,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":11.3},{"place":129,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":11.3},{"place":130,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":10.6},{"place":131,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":10.52},{"place":132,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":10.3},{"place":133,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":10.3},{"place":134,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":10.1},{"place":135,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.8},{"place":136,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":9.54},{"place":137,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":9.48},{"place":138,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":9.3},{"place":139,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":9.28},{"place":140,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":9.1},{"place":141,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":8.9},{"place":142,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.7},{"place":143,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":8.7},{"place":144,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":8.4},{"place":145,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":8.04},{"place":146,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":7.7},{"place":147,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":7.63},{"place":148,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":7.6},{"place":149,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":7.4},{"place":150,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":7.22},{"place":151,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":7.2},{"place":152,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":7.2},{"place":153,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":7.2},{"place":154,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":7.01},{"place":155,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":7.01},{"place":156,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":7},{"place":157,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":7},{"place":158,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":6.8},{"place":159,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":6.6},{"place":160,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":6.4},{"place":161,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":5.8},{"place":162,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":5.8},{"place":163,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":5.7},{"place":164,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":5.7},{"place":165,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":5.7},{"place":166,"model":"kolibri-origin","company":"alephalpha","family":"Kolibri","version":"Kolibri Origin","score":5.7},{"place":167,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":5.67},{"place":168,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":5.6},{"place":169,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5.45},{"place":170,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":5.4},{"place":171,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":5.4},{"place":172,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5.15},{"place":173,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5.03},{"place":174,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.54},{"place":175,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.12},{"place":176,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.1},{"place":177,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.9},{"place":178,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":3.4},{"place":179,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.35},{"place":180,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.1},{"place":181,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":2.1},{"place":182,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":1.2}]},{"id":"tau3-banking-voice","name":"τ³-Banking (Voice)","topic":"Voice agents","description":"Sierra τ³ banking knowledge tasks run voice-to-voice; pass@1 (%).","url":"https://sierra.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.8 Live Extended Thinking (high)","top_percent":35.1,"top_model_id":"gemini-3.8-live-extended-thinking-high","top_generation":"Gemini 3.8","top_model_base":"Gemini 3.8 Live Extended Thinking","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.8-live-extended-thinking-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":35.1},{"place":2,"model":"gpt-live-1-medium","company":"openai","family":"GPT","version":"GPT-Live-1","score":32},{"place":3,"model":"gpt-live-1-medium","company":"openai","family":"GPT","version":"GPT-Live-1","score":31.96},{"place":4,"model":"gpt-realtime-2.1-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":12.37},{"place":5,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":11.3},{"place":6,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":10.31},{"place":7,"model":"gpt-realtime-2.0-high","company":"openai","family":"GPT","version":"GPT-realtime-2","score":10.3}]},{"id":"tau3-retail","name":"τ³-Bench Retail","topic":"Agent tasks (retail)","description":"τ³-Bench retail domain: tool-augmented customer-service agent with simulated user.","url":"https://github.com/sierra-research/tau2-bench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V4-Flash","top_percent":89.1,"top_model_id":"deepseek-v4-flash","top_generation":"DeepSeek V4","top_model_base":"DeepSeek V4 Flash","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.1},{"place":2,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":88.9},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":88.5},{"place":4,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.4},{"place":5,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":84.9},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.4},{"place":7,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":84.1},{"place":8,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":82.9},{"place":9,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":76.3},{"place":10,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":76.1},{"place":11,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":75.9},{"place":12,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":72.8},{"place":13,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.4},{"place":14,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":70.2},{"place":15,"model":"mercury-voice","company":"inception","family":"Mercury","version":"Mercury 2.5","score":69.3},{"place":16,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69.3},{"place":17,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":67.8},{"place":18,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":64.3},{"place":19,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":64}]},{"id":"tau3-telecom","name":"τ³-Bench Telecom","topic":"Agent tasks (telecom)","description":"τ³-Bench telecom domain: tool-augmented customer-service agent with simulated user (dual-control).","url":"https://github.com/sierra-research/tau2-bench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-5.1","top_percent":98.7,"top_model_id":"glm-5.1","top_generation":"GLM 5.1","top_model_base":"GLM-5.1","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":98.7},{"place":2,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":98.3},{"place":3,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":98},{"place":4,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97.8},{"place":5,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":97.8},{"place":6,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":96.9},{"place":7,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":96.3},{"place":8,"model":"mercury-2.5","company":"inception","family":"Mercury","version":"Mercury 2.5","score":96},{"place":9,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":92.9},{"place":10,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":91.4},{"place":11,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":89.6},{"place":12,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":86.8},{"place":13,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.9},{"place":14,"model":"mercury-voice","company":"inception","family":"Mercury","version":"Mercury 2.5","score":77.2},{"place":15,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":70.4},{"place":16,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":65},{"place":17,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":60.5},{"place":18,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50},{"place":19,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":48.2},{"place":20,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":47.1},{"place":21,"model":"mistral-medium-3.1","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":46.9}]},{"id":"tempcompass","name":"TempCompass","topic":"Temporal reasoning","description":"Temporal reasoning benchmark evaluating understanding of time-related concepts in videos and images.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":88,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":86.9},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.9},{"place":4,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":83.7},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":82.8},{"place":6,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":82.6},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.9},{"place":8,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":80.4},{"place":9,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":80.2},{"place":10,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.4},{"place":11,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":76.05},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.8},{"place":13,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":75.5},{"place":14,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":75.1},{"place":15,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":74.9},{"place":16,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":74.64},{"place":17,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":74.4},{"place":18,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":74.4},{"place":19,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":74.36},{"place":20,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.3},{"place":21,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":73.99},{"place":22,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":73.4},{"place":23,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":73},{"place":24,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":72.8},{"place":25,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":72.8},{"place":26,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":72.7},{"place":27,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":72.7},{"place":28,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":72.3},{"place":29,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70.8},{"place":30,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":70.3},{"place":31,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":69.4},{"place":32,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":69.3},{"place":33,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":68.8},{"place":34,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":67.1},{"place":35,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":66.6}]},{"id":"terminal-bench","name":"Terminal-Bench","topic":"Agent terminal tasks","description":"Command-line task completion benchmark for agents.","url":"https://www.tbench.ai/","leaderboard":"https://www.tbench.ai/leaderboard","github":"https://github.com/laude-institute/terminal-bench","paper":"","metric":"percent","stars":"637","top_model":"Claude Sonnet 4.5","top_percent":64.5,"top_model_id":"claude-sonnet-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Sonnet 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":90,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":64.5},{"place":2,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":61.3},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.3},{"place":4,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.3},{"place":5,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":58.8},{"place":6,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":58.8},{"place":7,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":56.3},{"place":8,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":54.8},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":54.2},{"place":10,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":54.2},{"place":11,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":54},{"place":12,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":53.8},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":53.4},{"place":14,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":52.5},{"place":15,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":52.3},{"place":16,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51},{"place":17,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51},{"place":18,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":50.8},{"place":19,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50},{"place":20,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":49},{"place":21,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":48.8},{"place":22,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":47.7},{"place":23,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":47.6},{"place":24,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":47.6},{"place":25,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":47.1},{"place":26,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":46.5},{"place":27,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":46.4},{"place":28,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":46.4},{"place":29,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":46.3},{"place":30,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":45.3},{"place":31,"model":"claude-sonnet-4-thinking","company":"anthropic","family":"Claude","version":"Claude 4","score":45},{"place":32,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.5},{"place":33,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.5},{"place":34,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":44.5},{"place":35,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":43.8},{"place":36,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":43.8},{"place":37,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":43.3},{"place":38,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":43.2},{"place":39,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.8},{"place":40,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":42.8},{"place":41,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.5},{"place":42,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":42.1},{"place":43,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":42},{"place":44,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":41.8},{"place":45,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":41.3},{"place":46,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":41.3},{"place":47,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":41.3},{"place":48,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":41.3},{"place":49,"model":"nova-2-pro","company":"amazon","family":"Nova","version":"Nova 2","score":41.3},{"place":50,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":41},{"place":51,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":41},{"place":52,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":40.5},{"place":53,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":40.1},{"place":54,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":39.9},{"place":55,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":39.2},{"place":56,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":39},{"place":57,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":39},{"place":58,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":38.8},{"place":59,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":37.7},{"place":60,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":37.7},{"place":61,"model":"kimi-k2-instruct-0711","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":37.5},{"place":62,"model":"qwen3-coder-480b-a35b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.5},{"place":63,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":37.5},{"place":64,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":37.5},{"place":65,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":36.7},{"place":66,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":36.4},{"place":67,"model":"qwen3-max-instruct-preview","company":"qwen","family":"Qwen","version":"Qwen3","score":36.3},{"place":68,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":36.3},{"place":69,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":35.5},{"place":70,"model":"glaive-swe-v1","company":"glaive","family":"Glaive","version":"Glaive SWE","score":35.3},{"place":71,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":35.2},{"place":72,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":35},{"place":73,"model":"telechat3-coder-36b-thinking","company":"teleai","family":"TeleChat","version":"TeleChat3","score":34.8},{"place":74,"model":"longcat-flash-lite","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":33.75},{"place":75,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":33.7},{"place":76,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":33},{"place":77,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":33},{"place":78,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":33},{"place":79,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":33},{"place":80,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":32.6},{"place":81,"model":"nova-2-lite","company":"amazon","family":"Nova","version":"Nova 2","score":32.5},{"place":82,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":31.8},{"place":83,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":31.3},{"place":84,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":31.3},{"place":85,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":31.3},{"place":86,"model":"qwen3-30b-a3b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":31.3},{"place":87,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":31.3},{"place":88,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":30.8},{"place":89,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":30.3},{"place":90,"model":"o3","company":"openai","family":"o3","version":"o3","score":30.2},{"place":91,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":30},{"place":92,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":30},{"place":93,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":29.8},{"place":94,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":29.5},{"place":95,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":27.8},{"place":96,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":27.5},{"place":97,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":26.3},{"place":98,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":26.3},{"place":99,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":26.3},{"place":100,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":26.1},{"place":101,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":25.3},{"place":102,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":24.2},{"place":103,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":23.8},{"place":104,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":23.6},{"place":105,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":23.1},{"place":106,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":22.5},{"place":107,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":22.2},{"place":108,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.3},{"place":109,"model":"grok-code-fast","company":"xai","family":"Grok","version":"Grok Code","score":20},{"place":110,"model":"kimi-linear-instruct","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":20},{"place":111,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":20},{"place":112,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":18.8},{"place":113,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":18.75},{"place":114,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":17.5},{"place":115,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":17.5},{"place":116,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":17.1},{"place":117,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.8},{"place":118,"model":"hypernova-60b-2605","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":15.9},{"place":119,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":15.5},{"place":120,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":15.5},{"place":121,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":15.19},{"place":122,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":13.8},{"place":123,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":13.5},{"place":124,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":12.2},{"place":125,"model":"hypernova-60b-2602","company":"multiverse","family":"HyperNova","version":"HyperNova 60B","score":12.1},{"place":126,"model":"amazon-nova-premier","company":"amazon","family":"Amazon Nova","version":"Amazon Nova","score":11.3},{"place":127,"model":"codex-mini-latest","company":"openai","family":"Codex","version":"Codex","score":11.3},{"place":128,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":10.1},{"place":129,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":9.1},{"place":130,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":8.3},{"place":131,"model":"kat-dev-72b-exp","company":"kuaishou","family":"KAT","version":"KAT","score":7.9},{"place":132,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":7.8},{"place":133,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":6.6},{"place":134,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":5.7},{"place":135,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":4.5},{"place":136,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.5},{"place":137,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":3.4},{"place":138,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":2.5},{"place":139,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":2.3},{"place":140,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":1.2},{"place":141,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":0},{"place":142,"model":"qwen2.5-coder-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0},{"place":143,"model":"qwen2.5-coder-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":0}]},{"id":"terminal-bench-2.0","name":"Terminal-Bench 2.0","topic":"Agent terminal tasks","description":"Second-generation Terminal-Bench leaderboard for end-to-end terminal agents.","url":"https://www.tbench.ai/","leaderboard":"https://www.tbench.ai/leaderboard","github":"https://github.com/laude-institute/terminal-bench","paper":"","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":84.7,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":144,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.7},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":82.7},{"place":3,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":82},{"place":4,"model":"iquest-coder-v1-40b-loop-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":81.4},{"place":5,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.9},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.2},{"place":7,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":80.2},{"place":8,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":78.4},{"place":9,"model":"gemini-3-flash-preview","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":10,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":77.3},{"place":11,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":77.3},{"place":12,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.2},{"place":13,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":76.4},{"place":14,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":76.3},{"place":15,"model":"gemini-3-pro-preview","company":"google","family":"Gemini","version":"Gemini 3","score":76.2},{"place":16,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":75.2},{"place":17,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":75.1},{"place":18,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":73.8},{"place":19,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":73.1},{"place":20,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":71.3},{"place":21,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":70.3},{"place":22,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":69.7},{"place":23,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":69.4},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":69.4},{"place":25,"model":"kimi-k2-instruct-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":69.2},{"place":26,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":69},{"place":27,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":68.5},{"place":28,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":68.4},{"place":29,"model":"lar-27b","company":"amazon","family":"LAR","version":"LAR","score":68.2},{"place":30,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67.9},{"place":31,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":67},{"place":32,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":66.7},{"place":33,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":66.5},{"place":34,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":66.5},{"place":35,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":65.8},{"place":36,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":65.4},{"place":37,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":65.4},{"place":38,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":65.4},{"place":39,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":65.4},{"place":40,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":64.9},{"place":41,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":64.8},{"place":42,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":64.7},{"place":43,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":64.7},{"place":44,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":64.3},{"place":45,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":64},{"place":46,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":64},{"place":47,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":63.5},{"place":48,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":63.3},{"place":49,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":63.1},{"place":50,"model":"kat-dev-32b","company":"kuaishou","family":"KAT","version":"KAT","score":62.4},{"place":51,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":62.2},{"place":52,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":62.2},{"place":53,"model":"composer-2","company":"cursor","family":"Composer","version":"Composer 2","score":61.7},{"place":54,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":61.6},{"place":55,"model":"gpt-5.1-codex-mini","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":61.6},{"place":56,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":60.5},{"place":57,"model":"kimi-dev-72b","company":"moonshotai","family":"Kimi","version":"Kimi Dev","score":60.4},{"place":58,"model":"gpt-5.1-codex-max","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":60.4},{"place":59,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":60},{"place":60,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":60},{"place":61,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":60},{"place":62,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.8},{"place":63,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.8},{"place":64,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":59.6},{"place":65,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":59.3},{"place":66,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":59.3},{"place":67,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.1},{"place":68,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.1},{"place":69,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":59},{"place":70,"model":"gpt-5.3-codex-spark","company":"openai","family":"GPT","version":"GPT-5.3","score":58.4},{"place":71,"model":"gpt-5.1-codex-max","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":58.1},{"place":72,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":58},{"place":73,"model":"gpt-5.1-codex","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":57.8},{"place":74,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":57.3},{"place":75,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":57.1},{"place":76,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":57},{"place":77,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.9},{"place":78,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.9},{"place":79,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.6},{"place":80,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":56.2},{"place":81,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.2},{"place":82,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.2},{"place":83,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":55.8},{"place":84,"model":"mai-code-1-flash","company":"microsoft","family":"MAI","version":"MAI-Code-1","score":54.8},{"place":85,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":54.4},{"place":86,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":54.2},{"place":87,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":54},{"place":88,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54},{"place":89,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":53.4},{"place":90,"model":"gpt-5.1-codex","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":52.8},{"place":91,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52.5},{"place":92,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":52.4},{"place":93,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":52.1},{"place":94,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":51.9},{"place":95,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":51.5},{"place":96,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":51},{"place":97,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51},{"place":98,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":51},{"place":99,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":50.8},{"place":100,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":50.8},{"place":101,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50},{"place":102,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":49.6},{"place":103,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.4},{"place":104,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.1},{"place":105,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":48.31},{"place":106,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":48.3},{"place":107,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":47.9},{"place":108,"model":"composer-1.5","company":"cursor","family":"Composer","version":"Composer 1.5","score":47.9},{"place":109,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":47.6},{"place":110,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":47.6},{"place":111,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":47.6},{"place":112,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":47.3},{"place":113,"model":"grok-4.2","company":"xai","family":"Grok","version":"Grok 4.2","score":47.1},{"place":114,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":46.5},{"place":115,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":46.5},{"place":116,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":46.4},{"place":117,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":46.4},{"place":118,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":46.3},{"place":119,"model":"gpt-5.1-codex-mini-high","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":46.1},{"place":120,"model":"gpt-5.4-none","company":"openai","family":"GPT","version":"GPT-5.4","score":46.07},{"place":121,"model":"mai-thinking-1","company":"microsoft","family":"MAI","version":"MAI-Thinking-1","score":46},{"place":122,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":45.8},{"place":123,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":45.2},{"place":124,"model":"qwen3-235b-a22b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":45.2},{"place":125,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":45.1},{"place":126,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":45},{"place":127,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":44.6},{"place":128,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":44.3},{"place":129,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":44.1},{"place":130,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":43.3},{"place":131,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":43.2},{"place":132,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.9},{"place":133,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.8},{"place":134,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.8},{"place":135,"model":"tmax-27b","company":"allenai","family":"Tmax","version":"Tmax","score":42.7},{"place":136,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":42.7},{"place":137,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.6},{"place":138,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":41.6},{"place":139,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":41},{"place":140,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":40.7},{"place":141,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.5},{"place":142,"model":"ling-2.6-1t","company":"antgroup","family":"Ling","version":"Ling 2.6","score":40.45},{"place":143,"model":"composer-1","company":"cursor","family":"Composer","version":"Composer 1","score":40},{"place":144,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.6},{"place":145,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":39.6},{"place":146,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":39.3},{"place":147,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":39.3},{"place":148,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":38.5},{"place":149,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":38.2},{"place":150,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":38},{"place":151,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.5},{"place":152,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":37.5},{"place":153,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":37.1},{"place":154,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":36.6},{"place":155,"model":"qwen3-coder-next","company":"qwen","family":"Qwen","version":"Qwen3","score":36.2},{"place":156,"model":"north-mini-code-1.0","company":"cohere","family":"North","version":"North 1.0","score":36},{"place":157,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":36},{"place":158,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":35.7},{"place":159,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":35.7},{"place":160,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":35.5},{"place":161,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":35.2},{"place":162,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":34.8},{"place":163,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.2},{"place":164,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":33.7},{"place":165,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":33.4},{"place":166,"model":"lar-9b","company":"amazon","family":"LAR","version":"LAR","score":32.8},{"place":167,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":32.6},{"place":168,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":32.6},{"place":169,"model":"devstral-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":32.6},{"place":170,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":31.9},{"place":171,"model":"ling-2.5-1t","company":"antgroup","family":"Ling","version":"Ling 2.5","score":31.46},{"place":172,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":31},{"place":173,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":30.1},{"place":174,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":30},{"place":175,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":29.8},{"place":176,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":29.21},{"place":177,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.2},{"place":178,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":29},{"place":179,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":27.8},{"place":180,"model":"nemotron-terminal-32b","company":"nvidia","family":"Nemotron Terminal","version":"Nemotron Terminal","score":27.4},{"place":181,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":27.2},{"place":182,"model":"tmax-9b","company":"allenai","family":"Tmax","version":"Tmax","score":27.2},{"place":183,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":27.2},{"place":184,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":27},{"place":185,"model":"openthinkeragent-32b","company":"openthinker","family":"OpenThinker","version":"OpenThinkerAgent","score":26.2},{"place":186,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":25.8},{"place":187,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.8},{"place":188,"model":"qwen3-coder-480b-a35b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.4},{"place":189,"model":"qwen3-coder-plus","company":"qwen","family":"Qwen","version":"Qwen3","score":25.4},{"place":190,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":24.6},{"place":191,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":24.6},{"place":192,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":24.5},{"place":193,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":23.6},{"place":194,"model":"omnicoder-9b","company":"tesslate","family":"OmniCoder","version":"OmniCoder","score":23.6},{"place":195,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":23.2},{"place":196,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":22.5},{"place":197,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":22.5},{"place":198,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":21.8},{"place":199,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":21.1},{"place":200,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.1},{"place":201,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21.1},{"place":202,"model":"nemotron-terminal-14b","company":"nvidia","family":"Nemotron Terminal","version":"Nemotron Terminal","score":20.2},{"place":203,"model":"termigen-32b","company":"ucsb","family":"TermiGen","version":"TermiGen","score":19.3},{"place":204,"model":"tmax-4b","company":"allenai","family":"Tmax","version":"Tmax","score":18.9},{"place":205,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":18.7},{"place":206,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":18.7},{"place":207,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":17.1},{"place":208,"model":"afterquery-gpt-oss-20b","company":"afterquery","family":"GPT","version":"GPT-OSS","score":17},{"place":209,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.9},{"place":210,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":16.6},{"place":211,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.6},{"place":212,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":13.3},{"place":213,"model":"nemotron-terminal-8b","company":"nvidia","family":"Nemotron Terminal","version":"Nemotron Terminal","score":13},{"place":214,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":12.4},{"place":215,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":11.5},{"place":216,"model":"solar-pro-3","company":"upstage","family":"Solar","version":"Solar Pro 3","score":10.1},{"place":217,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.2},{"place":218,"model":"ling-1t","company":"antgroup","family":"Ling","version":"Ling 1T","score":8.99},{"place":219,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":8.5},{"place":220,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":7.5},{"place":221,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":4.04},{"place":222,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":3.4},{"place":223,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":3.37},{"place":224,"model":"tmax-2b","company":"allenai","family":"Tmax","version":"Tmax","score":2.9},{"place":225,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":2.47},{"place":226,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":2.3}]},{"id":"terminal-bench-2.1","name":"Terminal-Bench 2.1","topic":"Agent terminal tasks","description":"Updated Terminal-Bench 2.x task set (89 tasks) for end-to-end terminal/command-line agents; successor to Terminal-Bench 2.0.","url":"https://www.tbench.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"SWE-2","top_percent":92.8,"top_model_id":"swe-2","top_generation":"SWE-2","top_model_base":"SWE-2","top_model_family":"SWE","top_company":"cognition","top_open_source":0,"lower_is_better":false,"bench_models":197,"total_models":3854,"placements":[{"place":1,"model":"swe-2","company":"cognition","family":"SWE","version":"SWE-2","score":92.8},{"place":2,"model":"gpt-5.6-sol-ultra","company":"openai","family":"GPT","version":"GPT-5.6","score":91.9},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":91.4},{"place":4,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":90.6},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":90.2},{"place":6,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":89.9},{"place":7,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":89.9},{"place":8,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":89.6},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":89.5},{"place":10,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":89.4},{"place":11,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":89.3},{"place":12,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":89.1},{"place":13,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":88.8},{"place":14,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":88.8},{"place":15,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":88.8},{"place":16,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":88.4},{"place":17,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":88.3},{"place":18,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":88.2},{"place":19,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88},{"place":20,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88},{"place":21,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.9},{"place":22,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":87.9},{"place":23,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":87.6},{"place":24,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":87.4},{"place":25,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":87.4},{"place":26,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":86.9},{"place":27,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":86.7},{"place":28,"model":"naive-n0.5-flash","company":"naiveai","family":"Naive","version":"Naive-N0.5","score":86.7},{"place":29,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.6},{"place":30,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":86.2},{"place":31,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.1},{"place":32,"model":"nex-n2.5-max","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":86.1},{"place":33,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":86.1},{"place":34,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":86},{"place":35,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":85.8},{"place":36,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":85.8},{"place":37,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":85.6},{"place":38,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":85.4},{"place":39,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":85.4},{"place":40,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":85.2},{"place":41,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":85.1},{"place":42,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":85},{"place":43,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":85},{"place":44,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":84.7},{"place":45,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":84.6},{"place":46,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84.6},{"place":47,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84.3},{"place":48,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":84.3},{"place":49,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.2},{"place":50,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84},{"place":51,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":84},{"place":52,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.9},{"place":53,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":83.9},{"place":54,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.8},{"place":55,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":83.4},{"place":56,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":83.4},{"place":57,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":83.3},{"place":58,"model":"iquest-q1","company":"iquest","family":"IQuest","version":"IQuest Q1","score":83.2},{"place":59,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":83.1},{"place":60,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":83},{"place":61,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":82.9},{"place":62,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":82.7},{"place":63,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.7},{"place":64,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":82.7},{"place":65,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":82.7},{"place":66,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":82.7},{"place":67,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":82.7},{"place":68,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":82.5},{"place":69,"model":"fugu-ultra","company":"sakana","family":"Fugu","version":"Fugu 1","score":82.1},{"place":70,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":82},{"place":71,"model":"ember-1","company":"fireworks","family":"Ember","version":"Ember-1","score":82},{"place":72,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":81.8},{"place":73,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":81.8},{"place":74,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":81.6},{"place":75,"model":"swe-1.7","company":"cognition","family":"SWE","version":"SWE-1.7","score":81.5},{"place":76,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.3},{"place":77,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":81.2},{"place":78,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":81.18},{"place":79,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":81},{"place":80,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":81},{"place":81,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":80.9},{"place":82,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":80.9},{"place":83,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":80.9},{"place":84,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.5},{"place":85,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.4},{"place":86,"model":"fugu","company":"sakana","family":"Fugu","version":"Fugu 1","score":80.2},{"place":87,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":80.1},{"place":88,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":80},{"place":89,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":79.8},{"place":90,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":79.4},{"place":91,"model":"tev-27b","company":"tev","family":"Tev","version":"Tev","score":79.4},{"place":92,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":78.9},{"place":93,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":78.9},{"place":94,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":78.9},{"place":95,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78.7},{"place":96,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":78.3},{"place":97,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":78.2},{"place":98,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":78.2},{"place":99,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":78.2},{"place":100,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":78},{"place":101,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":77.9},{"place":102,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":77.6},{"place":103,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":77.5},{"place":104,"model":"lar-27b","company":"amazon","family":"LAR","version":"LAR","score":77.3},{"place":105,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77},{"place":106,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.8},{"place":107,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.8},{"place":108,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":76.4},{"place":109,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":76.4},{"place":110,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":76.4},{"place":111,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":76.2},{"place":112,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":76.2},{"place":113,"model":"composer-2.5","company":"cursor","family":"Composer","version":"Composer 2.5","score":76},{"place":114,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":75.7},{"place":115,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":75.3},{"place":116,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":75.1},{"place":117,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":75},{"place":118,"model":"motif-3","company":"motif","family":"Motif","version":"Motif 3","score":74.9},{"place":119,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":74.6},{"place":120,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":74.6},{"place":121,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":74.5},{"place":122,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":74},{"place":123,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":73.8},{"place":124,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":73.8},{"place":125,"model":"jais-3-375b-a23b","company":"g42","family":"Jais","version":"Jais 3","score":73.8},{"place":126,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":73.5},{"place":127,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":73.4},{"place":128,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73},{"place":129,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":73},{"place":130,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":72.7},{"place":131,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72.1},{"place":132,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72.1},{"place":133,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":72},{"place":134,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":71.9},{"place":135,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":71.7},{"place":136,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":71.7},{"place":137,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":71.3},{"place":138,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":71.2},{"place":139,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":71},{"place":140,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":70.8},{"place":141,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":70.8},{"place":142,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.7},{"place":143,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70.3},{"place":144,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":70.3},{"place":145,"model":"laguna-s-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":70.2},{"place":146,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":70.2},{"place":147,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":69.8},{"place":148,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":69.7},{"place":149,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":69.1},{"place":150,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":69},{"place":151,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":68.5},{"place":152,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":67.8},{"place":153,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":67.6},{"place":154,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":67.42},{"place":155,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":67.3},{"place":156,"model":"jais-3-mova-36b-a4b","company":"g42","family":"Jais","version":"Jais 3","score":67.3},{"place":157,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":67.2},{"place":158,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":67},{"place":159,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":66.7},{"place":160,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":66.5},{"place":161,"model":"grm-3.2-sky","company":"orionllm","family":"GRM","version":"GRM-3.2","score":66.3},{"place":162,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":66.29},{"place":163,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":66.1},{"place":164,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":66},{"place":165,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":65.9},{"place":166,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":65.2},{"place":167,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":65.2},{"place":168,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":65},{"place":169,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":64.7},{"place":170,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":64.2},{"place":171,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":64.04},{"place":172,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64},{"place":173,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":64},{"place":174,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64},{"place":175,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":64},{"place":176,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":64},{"place":177,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":63.8},{"place":178,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":63.7},{"place":179,"model":"jais-3-32b","company":"g42","family":"Jais","version":"Jais 3","score":63.7},{"place":180,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":63.5},{"place":181,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.4},{"place":182,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":62.8},{"place":183,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":62.8},{"place":184,"model":"k2-horizon-32b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":62.6},{"place":185,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62},{"place":186,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.8},{"place":187,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":61.8},{"place":188,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":61.8},{"place":189,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":61.8},{"place":190,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":60.7},{"place":191,"model":"kat-coder-pro-v2.5","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":60.7},{"place":192,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":60.7},{"place":193,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":60.7},{"place":194,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":60.67},{"place":195,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.6},{"place":196,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":59.6},{"place":197,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":59.55},{"place":198,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":59.3},{"place":199,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":59.3},{"place":200,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":59.2},{"place":201,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":59},{"place":202,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":58.7},{"place":203,"model":"k2-horizon-mova-36b-a4b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":58.6},{"place":204,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":58},{"place":205,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":58},{"place":206,"model":"xing4.0-29b-a4b","company":"teleai","family":"Xing","version":"Xing4.0","score":57.5},{"place":207,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":57.3},{"place":208,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":57},{"place":209,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":57},{"place":210,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.9},{"place":211,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":56.4},{"place":212,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":55.8},{"place":213,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":55.76},{"place":214,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":55.76},{"place":215,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":55.5},{"place":216,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":55.4},{"place":217,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":55.1},{"place":218,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":55},{"place":219,"model":"flint","company":"recursive","family":"Flint","version":"Flint","score":54.9},{"place":220,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":54.8},{"place":221,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":54.2},{"place":222,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":54},{"place":223,"model":"nemotron-3.5-bolt-74b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":53.93},{"place":224,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":53.9},{"place":225,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":53.9},{"place":226,"model":"flint-nvfp4","company":"recursive","family":"Flint","version":"Flint","score":53.7},{"place":227,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.5},{"place":228,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":53.4},{"place":229,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":53.4},{"place":230,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":52.7},{"place":231,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.58},{"place":232,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":52.5},{"place":233,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":51.7},{"place":234,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":51.5},{"place":235,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":51.3},{"place":236,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.3},{"place":237,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":51.3},{"place":238,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":51.1},{"place":239,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":50.8},{"place":240,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.9},{"place":241,"model":"oxcoder-9b","company":"orionllm","family":"OxCoder","version":"OxCoder","score":49.6},{"place":242,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":49.5},{"place":243,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.2},{"place":244,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":49.2},{"place":245,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.7},{"place":246,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.6},{"place":247,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":48.3},{"place":248,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":47.2},{"place":249,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":47},{"place":250,"model":"jais-3-7b","company":"g42","family":"Jais","version":"Jais 3","score":46.4},{"place":251,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":46.2},{"place":252,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":45.2},{"place":253,"model":"tmax-27b","company":"allenai","family":"Tmax","version":"Tmax","score":44.9},{"place":254,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":44.9},{"place":255,"model":"k2-horizon-7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":44.6},{"place":256,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":44.38},{"place":257,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.2},{"place":258,"model":"k-exaone-2.0","company":"lg","family":"K-EXAONE","version":"K-EXAONE 2.0","score":43.8},{"place":259,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.5},{"place":260,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43.4},{"place":261,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":43.2},{"place":262,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":43.1},{"place":263,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":43.1},{"place":264,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":43},{"place":265,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.1},{"place":266,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":41.6},{"place":267,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.57},{"place":268,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.4},{"place":269,"model":"jais-3-3.7b","company":"g42","family":"Jais","version":"Jais 3","score":41.2},{"place":270,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":40.6},{"place":271,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":40.5},{"place":272,"model":"swe-1.6","company":"cognition","family":"SWE","version":"SWE-1.6","score":39.7},{"place":273,"model":"k2-horizon-3.7b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":39.7},{"place":274,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.7},{"place":275,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":39.7},{"place":276,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":39.61},{"place":277,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":39.3},{"place":278,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":39},{"place":279,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.9},{"place":280,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.7},{"place":281,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":38.6},{"place":282,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":38.4},{"place":283,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37.22},{"place":284,"model":"mimo-v2.6-distill-qwen-9b","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":37.1},{"place":285,"model":"ax-k2","company":"skt","family":"A.X","version":"A.X","score":36},{"place":286,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":35.96},{"place":287,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":35},{"place":288,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34.83},{"place":289,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":33.7},{"place":290,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":33.4},{"place":291,"model":"kat-coder-v2.5-dev","company":"kuaishou","family":"KAT","version":"KAT-Coder V2.5","score":32.6},{"place":292,"model":"g9v3-39a5b","company":"ai9stars","family":"G9","version":"G9v3","score":32.6},{"place":293,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":31},{"place":294,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.34},{"place":295,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":30.3},{"place":296,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30},{"place":297,"model":"lar-9b","company":"amazon","family":"LAR","version":"LAR","score":29.5},{"place":298,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":29.24},{"place":299,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.2},{"place":300,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":29.2},{"place":301,"model":"tmax-9b","company":"allenai","family":"Tmax","version":"Tmax","score":28.8},{"place":302,"model":"ling-3.0-tiny","company":"antgroup","family":"Ling","version":"Ling 3.0","score":27.7},{"place":303,"model":"kolibri-1","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":27.7},{"place":304,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.3},{"place":305,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.27},{"place":306,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27},{"place":307,"model":"granite-4.2-30b","company":"IBM","family":"Granite","version":"Granite 4.2","score":26.6},{"place":308,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.44},{"place":309,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.8},{"place":310,"model":"laguna-xs-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":24.7},{"place":311,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":24.58},{"place":312,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24},{"place":313,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":23.46},{"place":314,"model":"nemotron-labs-dory1.0-4b-4loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":22.2},{"place":315,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.7},{"place":316,"model":"mistral-small-4","company":"mistral","family":"Mistral","version":"Mistral 4","score":21.4},{"place":317,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.3},{"place":318,"model":"mistral-small-4-thinking","company":"mistral","family":"Mistral","version":"Mistral 4","score":21},{"place":319,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21},{"place":320,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":20.56},{"place":321,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":20.2},{"place":322,"model":"tmax-4b","company":"allenai","family":"Tmax","version":"Tmax","score":19.9},{"place":323,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.9},{"place":324,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":18.4},{"place":325,"model":"nemotron-labs-dory1.0-4b","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":18.1},{"place":326,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":17.4},{"place":327,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":16.1},{"place":328,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":15.17},{"place":329,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15},{"place":330,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":14.2},{"place":331,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":13.9},{"place":332,"model":"nemotron-labs-dory1.0-4b-1loop","company":"nvidia","family":"Nemotron","version":"Nemotron Labs Dory1.0","score":12.5},{"place":333,"model":"qwen3-coder-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":10.11},{"place":334,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":9.7},{"place":335,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":8.6},{"place":336,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":8.6},{"place":337,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":8.29},{"place":338,"model":"g9v3-3b","company":"ai9stars","family":"G9","version":"G9v3","score":6},{"place":339,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":4.5},{"place":340,"model":"tmax-2b","company":"allenai","family":"Tmax","version":"Tmax","score":4.2},{"place":341,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.8},{"place":342,"model":"nemotron-3-nano-4b-thinking","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":3.7},{"place":343,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":3.4},{"place":344,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":3},{"place":345,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1.9},{"place":346,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1.9},{"place":347,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":1.9},{"place":348,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":1.1},{"place":349,"model":"fanar-2-27b-instruct","company":"qcri","family":"Fanar","version":"Fanar 2.0","score":1.1},{"place":350,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":0.6},{"place":351,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.4},{"place":352,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":353,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":0},{"place":354,"model":"allam-7b-instruct-preview","company":"humain","family":"ALLaM","version":"ALLaM","score":0},{"place":355,"model":"fanar-1-9b-instruct","company":"qcri","family":"Fanar","version":"Fanar 1.0","score":0},{"place":356,"model":"granite-4.0-h-3b-ar","company":"IBM","family":"Granite","version":"Granite 4.0","score":0}]},{"id":"terminal-bench-3.0","name":"Terminal-Bench 3.0","topic":"Agentic terminal tasks","description":"Terminal-Bench 3.0: harder long-horizon command-line agent tasks scored by official verifiers.","url":"https://www.tbench.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":53,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":43.3},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":41},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":41},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":34.6},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":34.4},{"place":7,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":34.1},{"place":8,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":33.7},{"place":9,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":30},{"place":10,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":30},{"place":11,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":29.7},{"place":12,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":28.3},{"place":13,"model":"tev-320b","company":"tev","family":"Tev","version":"Tev","score":27},{"place":14,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":26},{"place":15,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":26},{"place":16,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":21.1},{"place":17,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":20.8},{"place":18,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":20},{"place":19,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":19},{"place":20,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":17.7},{"place":21,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":17.4},{"place":22,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":16},{"place":23,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":15.7},{"place":24,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":14.9},{"place":25,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":14.6},{"place":26,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":11.8},{"place":27,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":7.6},{"place":28,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":5.4},{"place":29,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":4.6},{"place":30,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":4}]},{"id":"terminal-bench-4.0","name":"Terminal-Bench 4.0","topic":"Agentic terminal tasks","description":"Terminal-Bench 4.0: complex multi-step professional tasks in a command-line interface.","url":"https://www.tbench.ai/","leaderboard":"https://www.tbench.ai/leaderboard","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 5.5","top_percent":70.6,"top_model_id":"claude-sonnet-5.5","top_generation":"Claude 5.5","top_model_base":"Claude Sonnet 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":73,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":70.6},{"place":2,"model":"claude-sonnet-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":70.6},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":66.4},{"place":4,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":65.7},{"place":5,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":61.5},{"place":6,"model":"claude-mythos-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":60.9},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":59.6},{"place":8,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":58.2},{"place":9,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":58.2},{"place":10,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":58.1},{"place":11,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":57.9},{"place":12,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":57.9},{"place":13,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":57.9},{"place":14,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":57.4},{"place":15,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":55.9},{"place":16,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":55.8},{"place":17,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":55.1},{"place":18,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":54.4},{"place":19,"model":"gpt-6.1-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":53.4},{"place":20,"model":"gpt-6.1-sol-high","company":"openai","family":"GPT","version":"GPT-6.1","score":53},{"place":21,"model":"gpt-6.1-sol-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":52.7},{"place":22,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":52.6},{"place":23,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":52.3},{"place":24,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":52},{"place":25,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":51.8},{"place":26,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":50.6},{"place":27,"model":"gpt-6.1-terra-max","company":"openai","family":"GPT","version":"GPT-6.1","score":50.3},{"place":28,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":50.3},{"place":29,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":49},{"place":30,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":47.1},{"place":31,"model":"gpt-6.1-terra-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":46.4},{"place":32,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":46.03},{"place":33,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":46},{"place":34,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":45},{"place":35,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":44.5},{"place":36,"model":"claude-sonnet-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":43},{"place":37,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":42.4},{"place":38,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":42.3},{"place":39,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":42},{"place":40,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":41.9},{"place":41,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":41.8},{"place":42,"model":"gpt-6.1-terra-high","company":"openai","family":"GPT","version":"GPT-6.1","score":41.8},{"place":43,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":39.9},{"place":44,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":39.2},{"place":45,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":39},{"place":46,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":38.1},{"place":47,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":37.9},{"place":48,"model":"veriloop-e2","company":"tsinghua","family":"VeriLoop","version":"VeriLoop E2","score":37.9},{"place":49,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":37.6},{"place":50,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":37.3},{"place":51,"model":"tev-320b","company":"tev","family":"Tev","version":"Tev","score":37},{"place":52,"model":"gpt-6.1-terra-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":35.8},{"place":53,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":34.9},{"place":54,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":33.3},{"place":55,"model":"tinfield-1","company":"badtheorylabs","family":"Tinfield","version":"Tinfield 1","score":33},{"place":56,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":32.8},{"place":57,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":31.2},{"place":58,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":31},{"place":59,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":29},{"place":60,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":29},{"place":61,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":28.8},{"place":62,"model":"claude-sonnet-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":28.8},{"place":63,"model":"swe-2","company":"cognition","family":"SWE","version":"SWE-2","score":27.3},{"place":64,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":27},{"place":65,"model":"minimax-m3.1-flash-max","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":25.25},{"place":66,"model":"gpt-6.1-terra-low","company":"openai","family":"GPT","version":"GPT-6.1","score":24.8},{"place":67,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":23.8},{"place":68,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":23.6},{"place":69,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":23.6},{"place":70,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":21.5},{"place":71,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":21.5},{"place":72,"model":"gpt-5.6-terra-max","company":"openai","family":"GPT","version":"GPT-5.6","score":21.5},{"place":73,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":20.71},{"place":74,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":20.3},{"place":75,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":20},{"place":76,"model":"claude-sonnet-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":20},{"place":77,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":19.1},{"place":78,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":19},{"place":79,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":16.4},{"place":80,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":15.15},{"place":81,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":12.6},{"place":82,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":12.4},{"place":83,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":12.4},{"place":84,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":11.2},{"place":85,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":10.3},{"place":86,"model":"swe-1.7","company":"cognition","family":"SWE","version":"SWE-1.7","score":7.6},{"place":87,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":7},{"place":88,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":6.3},{"place":89,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":3.54},{"place":90,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":3},{"place":91,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":1.6},{"place":92,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1.5},{"place":93,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1},{"place":94,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":0.5},{"place":95,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":0},{"place":96,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0},{"place":97,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":0},{"place":98,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0}]},{"id":"terminal-bench-hard","name":"Terminal-Bench Hard","topic":"Agent terminal tasks","description":"Hard subset of Terminal-Bench command-line agent tasks.","url":"https://www.tbench.ai/","leaderboard":"https://artificialanalysis.ai/evaluations/terminalbench-hard","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.4","top_percent":57.6,"top_model_id":"gpt-5.4","top_generation":"GPT-5.4","top_model_base":"GPT-5.4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":78,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":57.6},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":53.8},{"place":3,"model":"kat-coder-pro-v2","company":"kuaishou","family":"KAT","version":"KAT-Coder V2","score":46.8},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":46.2},{"place":5,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":43.2},{"place":6,"model":"gpt-5.1-high","company":"openai","family":"GPT","version":"GPT-5.1","score":43},{"place":7,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":41.7},{"place":8,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":39.4},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":39},{"place":10,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":38},{"place":11,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":37.6},{"place":12,"model":"mercury-2.5","company":"inception","family":"Mercury","version":"Mercury 2.5","score":37},{"place":13,"model":"gpt-5-codex-high","company":"openai","family":"GPT","version":"GPT-5","score":36},{"place":14,"model":"gpt-5-codex","company":"openai","family":"GPT","version":"GPT-5","score":35.5},{"place":15,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":35.4},{"place":16,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":35.4},{"place":17,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":35},{"place":18,"model":"o3","company":"openai","family":"o3","version":"o3","score":34.8},{"place":19,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":34.1},{"place":20,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":33.3},{"place":21,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33.3},{"place":22,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":33.3},{"place":23,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33},{"place":24,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":33},{"place":25,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":32.1},{"place":26,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":32},{"place":27,"model":"north-mini-code-1.0","company":"cohere","family":"North","version":"North 1.0","score":31.1},{"place":28,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":31},{"place":29,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":31},{"place":30,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":30.6},{"place":31,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":30.5},{"place":32,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":30.5},{"place":33,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":30.5},{"place":34,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":29.8},{"place":35,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":29.1},{"place":36,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":29},{"place":37,"model":"deepseek-v3.1-terminus","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":28.4},{"place":38,"model":"solar-open-2-250b","company":"upstage","family":"Solar","version":"Solar Open 2","score":28.3},{"place":39,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.8},{"place":40,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":26},{"place":41,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":25.78},{"place":42,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":25.5},{"place":43,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":25.5},{"place":44,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":25},{"place":45,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":25},{"place":46,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":25},{"place":47,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25},{"place":48,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":24.8},{"place":49,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":24.1},{"place":50,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":24.1},{"place":51,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":24},{"place":52,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":24},{"place":53,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":24},{"place":54,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":23.6},{"place":55,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":23},{"place":56,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":22.7},{"place":57,"model":"kimi-k2-0905","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":22.7},{"place":58,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":22},{"place":59,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":22},{"place":60,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":21.3},{"place":61,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":19.1},{"place":62,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":18},{"place":63,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":18},{"place":64,"model":"grok-4-fast","company":"xai","family":"Grok","version":"Grok 4","score":17.7},{"place":65,"model":"gpt-5-minimal","company":"openai","family":"GPT","version":"GPT-5","score":17.7},{"place":66,"model":"devstral-small-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":17},{"place":67,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":16},{"place":68,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":15},{"place":69,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":14.9},{"place":70,"model":"apriel-1.6-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.6","score":14},{"place":71,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":13},{"place":72,"model":"qwen3-235b-a22b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":13},{"place":73,"model":"gemini-2.5-flash-preview-09-2025","company":"google","family":"Gemini","version":"Gemini 2.5","score":13},{"place":74,"model":"magistral-medium-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":12.8},{"place":75,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":12.8},{"place":76,"model":"qwen3-235b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":12.8},{"place":77,"model":"hyperclovax-seed-think","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":11},{"place":78,"model":"gpt-oss-20b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":10},{"place":79,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":10},{"place":80,"model":"apriel-1.5-15b-thinker","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":9.9},{"place":81,"model":"qwen3-next-80b-a3b","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":9.2},{"place":82,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":8.5},{"place":83,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":6.4},{"place":84,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":6},{"place":85,"model":"llama-4-maverick","company":"meta","family":"Llama","version":"Llama 4","score":6},{"place":86,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":5.7},{"place":87,"model":"apriel-1.5-15b-thinker-self-reported","company":"servicenow","family":"Apriel","version":"Apriel 1.5","score":5.7},{"place":88,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":5.67},{"place":89,"model":"llama-nemotron-super-49b-v1.5","company":"nvidia","family":"Llama","version":"Llama Nemotron v1.5","score":5},{"place":90,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":5},{"place":91,"model":"magistral-small-1.2","company":"mistral","family":"Magistral","version":"Magistral 1.2","score":4.3},{"place":92,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":4},{"place":93,"model":"exaone-4.0-32b","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":3.5},{"place":94,"model":"command-a-reasoning-08-2025","company":"cohere","family":"Command","version":"Command","score":3},{"place":95,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":2.3},{"place":96,"model":"midm-k-2.5-pro","company":"kt","family":"Mi:dm","version":"Mi:dm K 2.5","score":2},{"place":97,"model":"qwen3-4b-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":1.4}]},{"id":"terminal-bench-lite","name":"Terminal-Bench Lite","topic":"Agent terminal tasks","description":"OpenThoughts TBLite: lighter, faster subset-style variant of Terminal-Bench 2.0 for evaluating terminal agents.","url":"https://huggingface.co/datasets/open-thoughts/OpenThoughts-TBLite","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.6-27B","top_percent":70.8,"top_model_id":"qwen3.6-27b","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 27B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":70.8},{"place":2,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":70.7},{"place":3,"model":"tmax-27b","company":"allenai","family":"Tmax","version":"Tmax","score":68.6},{"place":4,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67},{"place":5,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":63.3},{"place":6,"model":"tmax-9b","company":"allenai","family":"Tmax","version":"Tmax","score":57.2},{"place":7,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":52},{"place":8,"model":"raon-1-mini-preview","company":"krafton","family":"Raon","version":"Raon-1","score":47},{"place":9,"model":"tmax-4b","company":"allenai","family":"Tmax","version":"Tmax","score":42.6},{"place":10,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.9},{"place":11,"model":"openthinkeragent-32b","company":"openthinker","family":"OpenThinker","version":"OpenThinkerAgent","score":41.3},{"place":12,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.8},{"place":13,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":13.7},{"place":14,"model":"tmax-2b","company":"allenai","family":"Tmax","version":"Tmax","score":11.8},{"place":15,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":5.7}]},{"id":"terminal-bench-science","name":"Terminal-Bench-Science","topic":"Agentic scientific research","description":"Terminal-Bench-Science 0.1: agentic scientific research tasks in terminal environments.","url":"https://www.tbench.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":68.1,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":68.1},{"place":2,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":68.1},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":64.6},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":63.3},{"place":5,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":63.3},{"place":6,"model":"gpt-6-astra-high","company":"openai","family":"GPT","version":"GPT-6","score":62},{"place":7,"model":"gpt-6-astra-xhigh","company":"openai","family":"GPT","version":"GPT-6","score":60.9},{"place":8,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":59.9},{"place":9,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":58.7},{"place":10,"model":"gpt-6.1-terra-max","company":"openai","family":"GPT","version":"GPT-6.1","score":58.3},{"place":11,"model":"gpt-6.1-terra","company":"openai","family":"GPT","version":"GPT-6.1","score":58.3},{"place":12,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":57.6},{"place":13,"model":"gpt-6-astra-medium","company":"openai","family":"GPT","version":"GPT-6","score":57.4},{"place":14,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":57},{"place":15,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":57},{"place":16,"model":"gpt-6-astra-low","company":"openai","family":"GPT","version":"GPT-6","score":55.4},{"place":17,"model":"gpt-6.1-sol-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":53.7},{"place":18,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":52.6},{"place":19,"model":"gpt-6.1-sol-high","company":"openai","family":"GPT","version":"GPT-6.1","score":51.1},{"place":20,"model":"gpt-6.1-sol-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":47.6},{"place":21,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":43.7},{"place":22,"model":"gpt-6.1-terra-xhigh","company":"openai","family":"GPT","version":"GPT-6.1","score":43.4},{"place":23,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":40},{"place":24,"model":"gpt-6.1-terra-high","company":"openai","family":"GPT","version":"GPT-6.1","score":39.7},{"place":25,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":38.1},{"place":26,"model":"gpt-6.1-terra-medium","company":"openai","family":"GPT","version":"GPT-6.1","score":34.3},{"place":27,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":30},{"place":28,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":29},{"place":29,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":27.6},{"place":30,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":24.7},{"place":31,"model":"gpt-6.1-terra-low","company":"openai","family":"GPT","version":"GPT-6.1","score":24.3},{"place":32,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":22.4},{"place":33,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":21.4},{"place":34,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":20.6},{"place":35,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":15.7},{"place":36,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":8.1}]},{"id":"terminal-bench-terminus","name":"Terminal-Bench Terminus","topic":"Agent terminal tasks","description":"Terminal-Bench Terminus track assessing end-to-end terminal tool use.","url":"https://www.tbench.ai/","leaderboard":"","github":"https://github.com/laude-institute/terminal-bench","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":68.5,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":68.5},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":65.4},{"place":3,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":64.7},{"place":4,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":59.1},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.9},{"place":6,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":54},{"place":7,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":30.3},{"place":8,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":25},{"place":9,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.8},{"place":10,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":16.3},{"place":11,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":6.6}]},{"id":"textquests","name":"TextQuests","topic":"Text-based video games","description":"Text-based video game benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":41,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":41},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.7},{"place":3,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":37},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":36.4},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":34.2},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":31},{"place":7,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":27.8},{"place":8,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":23.2},{"place":9,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":21.2},{"place":10,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":18.3},{"place":11,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":17.6},{"place":12,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":16.4},{"place":13,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":15.1},{"place":14,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":14.4},{"place":15,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":13.1},{"place":16,"model":"qwen3-max","company":"qwen","family":"Qwen","version":"Qwen3","score":12.4},{"place":17,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":11.7},{"place":18,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":1.2}]},{"id":"textquests-harm","name":"TextQuests Harm","topic":"Harmful propensities","description":"Harmfulness evaluation on TextQuests scenarios.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Grok 4.1 Fast","top_percent":9.1,"top_model_id":"grok-4.1-fast","top_generation":"Grok 4.1","top_model_base":"Grok 4.1","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":true,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":9.1},{"place":2,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":11.7},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":15.9},{"place":4,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":16.6},{"place":5,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":16.7},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":17.1},{"place":7,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":17.5},{"place":8,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":17.8},{"place":9,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":18.2},{"place":10,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":20.3},{"place":11,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":20.5},{"place":12,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":21.4},{"place":13,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":21.6},{"place":14,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":22.8},{"place":15,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":24.3}]},{"id":"textvqa","name":"TextVQA","topic":"Text-based VQA","description":"Visual question answering that requires reading text in images.","url":"https://textvqa.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ovis2.6-80B-A3B","top_percent":91.2,"top_model_id":"ovis2.6-80b-a3b","top_generation":"Ovis 2.6","top_model_base":"Ovis2.6 80B A3B","top_model_family":"Ovis","top_company":"alibaba","top_open_source":1,"lower_is_better":false,"bench_models":194,"total_models":3854,"placements":[{"place":1,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":91.2},{"place":2,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":90.7},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.6},{"place":4,"model":"llm-jp-4-vl-9b","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":88.4},{"place":5,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":88},{"place":6,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.7},{"place":7,"model":"llm-jp-4-vl-9b-beta","company":"llm-jp","family":"LLM-jp","version":"LLM-jp-4","score":87.7},{"place":8,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":87.2},{"place":9,"model":"glm-4v-plus","company":"zai","family":"GLM","version":"GLM-4V-Plus","score":86.6},{"place":10,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":86.5},{"place":11,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":86},{"place":12,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":85.7},{"place":13,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":85.5},{"place":14,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":85.5},{"place":15,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":85.1},{"place":16,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":85},{"place":17,"model":"cogvlm2-llama3-chinese-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":85},{"place":18,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":84.99},{"place":19,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":84.7},{"place":20,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":84.7},{"place":21,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":84.4},{"place":22,"model":"manzano-30b","company":"apple","family":"Manzano","version":"Manzano","score":84.4},{"place":23,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":84.4},{"place":24,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":84.3},{"place":25,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":84.3},{"place":26,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":84.3},{"place":27,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":84.3},{"place":28,"model":"deepseek-vl2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2","score":84.2},{"place":29,"model":"cogvlm2-llama3-chat-19b","company":"zai","family":"CogVLM2","version":"CogVLM2","score":84.2},{"place":30,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":84.1},{"place":31,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.98},{"place":32,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":83.9},{"place":33,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":83.8},{"place":34,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":83.7},{"place":35,"model":"deepseek-vl2-small","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Small","score":83.4},{"place":36,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":83.4},{"place":37,"model":"jina-vlm-2.4b-20251117","company":"jina","family":"jina-VLM","version":"jina-VLM","score":83.2},{"place":38,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":83.1},{"place":39,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":83.1},{"place":40,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":83},{"place":41,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":83},{"place":42,"model":"glm-4v-9b","company":"zai","family":"GLM","version":"GLM-4V","score":83},{"place":43,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.9},{"place":44,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":82.88},{"place":45,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.8},{"place":46,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":82.7},{"place":47,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":82.5},{"place":48,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":82.4},{"place":49,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":82.3},{"place":50,"model":"gemini-1.0-ultra","company":"google","family":"Gemini","version":"Gemini 1.0","score":82.3},{"place":51,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":82.3},{"place":52,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":82.2},{"place":53,"model":"nvlm-d-72b","company":"nvidia","family":"NVLM","version":"NVLM-D","score":82.1},{"place":54,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.8},{"place":55,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":81.7},{"place":56,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":81.5},{"place":57,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":81.31},{"place":58,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":81.21},{"place":59,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.2},{"place":60,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":81.1},{"place":61,"model":"aria","company":"rhymes","family":"Aria","version":"Aria","score":81.1},{"place":62,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81},{"place":63,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.8},{"place":64,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.8},{"place":65,"model":"deepseek-vl2-tiny","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL2-Tiny","score":80.7},{"place":66,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":80.6},{"place":67,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.55},{"place":68,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":80.5},{"place":69,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":80.4},{"place":70,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":80.3},{"place":71,"model":"manzano-3b","company":"apple","family":"Manzano","version":"Manzano","score":80.1},{"place":72,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":80.1},{"place":73,"model":"bagel-14b","company":"jondurbin","family":"Bagel","version":"Bagel","score":80},{"place":74,"model":"qianfan-ocr","company":"baidu","family":"Qianfan","version":"Qianfan-OCR","score":80},{"place":75,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.9},{"place":76,"model":"minicpm-o-4.5-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":79.8},{"place":77,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":79.7},{"place":78,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":79.7},{"place":79,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":79.7},{"place":80,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":79.6},{"place":81,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":79.6},{"place":82,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":79.6},{"place":83,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":79.6},{"place":84,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.5},{"place":85,"model":"qwen-vl-max","company":"qwen","family":"Qwen","version":"Qwen-VL","score":79.5},{"place":86,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":79.3},{"place":87,"model":"mm1.5-30b","company":"apple","family":"MM1","version":"MM1.5","score":79.2},{"place":88,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":79.1},{"place":89,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":79.1},{"place":90,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79},{"place":91,"model":"qwen-vl-plus","company":"qwen","family":"Qwen","version":"Qwen-VL","score":78.9},{"place":92,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":78.8},{"place":93,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":78.8},{"place":94,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":78.7},{"place":95,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":78.7},{"place":96,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":78.7},{"place":97,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":78.5},{"place":98,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":78.3},{"place":99,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.2},{"place":100,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":78.2},{"place":101,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":78.1},{"place":102,"model":"grok-1.5v","company":"xai","family":"Grok","version":"Grok 1.5","score":78.1},{"place":103,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":78},{"place":104,"model":"blip-3o-4b","company":"salesforce","family":"BLIP","version":"BLIP-3O","score":78},{"place":105,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":78},{"place":106,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":77.9},{"place":107,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":77.8},{"place":108,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.8},{"place":109,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":77.5},{"place":110,"model":"x-omni","company":"tencent","family":"X-Omni","version":"X-Omni","score":77.5},{"place":111,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":77.4},{"place":112,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":77.4},{"place":113,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":77.4},{"place":114,"model":"minicpm-v-4.7-1b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":77.4},{"place":115,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":77.4},{"place":116,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":77.4},{"place":117,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.3},{"place":118,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":77.28},{"place":119,"model":"internlm-xcomposer2-4khd-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-4KHD","score":77.2},{"place":120,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":77.1},{"place":121,"model":"internvl3-2b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":77},{"place":122,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":76.8},{"place":123,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.8},{"place":124,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":76.7},{"place":125,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":76.7},{"place":126,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.6},{"place":127,"model":"minicpm-llama3-v2.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-Llama3-V2.5","score":76.6},{"place":128,"model":"mm1.5-3b","company":"apple","family":"MM1","version":"MM1.5","score":76.5},{"place":129,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":76.5},{"place":130,"model":"mm1.5-7b","company":"apple","family":"MM1","version":"MM1.5","score":76.5},{"place":131,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":76.4},{"place":132,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":76.1},{"place":133,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":76.06},{"place":134,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":75.7},{"place":135,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":74.9},{"place":136,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":74.6},{"place":137,"model":"gemini-pro","company":"google","family":"Gemini","version":"Gemini","score":74.6},{"place":138,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":74.4},{"place":139,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":74.4},{"place":140,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":74.3},{"place":141,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.3},{"place":142,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":74.3},{"place":143,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74.1},{"place":144,"model":"minicpm-v-2.0-3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.0","score":74.1},{"place":145,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.1},{"place":146,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":74.1},{"place":147,"model":"mini-gemini-hd-34b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini-HD","score":74.1},{"place":148,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":73.8},{"place":149,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":73.8},{"place":150,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":73.6},{"place":151,"model":"mm1-30b","company":"apple","family":"MM1","version":"MM1","score":73.5},{"place":152,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":73.5},{"place":153,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":73.4},{"place":154,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":73},{"place":155,"model":"idefics2-8b","company":"huggingface","family":"IDEFICS","version":"Idefics2","score":73},{"place":156,"model":"mm1.5-1b","company":"apple","family":"MM1","version":"MM1.5","score":72.5},{"place":157,"model":"internvl-chat-v1.2","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.2","score":72.5},{"place":158,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":72.1},{"place":159,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":72},{"place":160,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":72},{"place":161,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":72},{"place":162,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":71.8},{"place":163,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":71.7},{"place":164,"model":"step-1v-32k","company":"stepfun","family":"Step","version":"Step 1V 32K","score":71.6},{"place":165,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":71},{"place":166,"model":"phi-3-vision-128k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":70.9},{"place":167,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":70.5},{"place":168,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":70.4},{"place":169,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":70.4},{"place":170,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.3},{"place":171,"model":"phi-3-vision-4b","company":"microsoft","family":"Phi","version":"Phi-3","score":70.1},{"place":172,"model":"internlm-xcomposer2-vl-7b","company":"internlm","family":"InternLM","version":"InternLM-XComposer2-VL","score":70.1},{"place":173,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":69.7},{"place":174,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":69.5},{"place":175,"model":"llava-next-34b","company":"bytedance","family":"LLaVA","version":"LLaVA-NeXT","score":69.3},{"place":176,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":69},{"place":177,"model":"docowl-1.5-chat","company":"alibaba","family":"mPLUG","version":"DocOwl-1.5-Chat","score":68.6},{"place":178,"model":"llava-uhd-13b","company":"tsinghua","family":"LLaVA","version":"LLaVA-UHD","score":67.7},{"place":179,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":67.5},{"place":180,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":67.3},{"place":181,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67.2},{"place":182,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":67.18},{"place":183,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67},{"place":184,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.72},{"place":185,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":66.6},{"place":186,"model":"gemini-nano-2","company":"google","family":"Gemini","version":"Gemini Nano","score":65.9},{"place":187,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":65.6},{"place":188,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":64.7},{"place":189,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":64.7},{"place":190,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":64.5},{"place":191,"model":"textmonkey","company":"hust","family":"Monkey","version":"TextMonkey","score":64.3},{"place":192,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":63.8},{"place":193,"model":"emu3-8b","company":"baai","family":"Emu","version":"Emu3","score":62.9},{"place":194,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62.5},{"place":195,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":61.5},{"place":196,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":61.5},{"place":197,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":61.3},{"place":198,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":61.2},{"place":199,"model":"minicpm-v","company":"openbmb","family":"MiniCPM","version":"MiniCPM-V","score":60.6},{"place":200,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":58.7},{"place":201,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":58.4},{"place":202,"model":"deepseek-vl-1.3b","company":"deepseek","family":"DeepSeek","version":"DeepSeek-VL","score":58.4},{"place":203,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":58.2},{"place":204,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":58.2},{"place":205,"model":"ureader","company":"alibaba","family":"mPLUG","version":"UReader","score":57.6},{"place":206,"model":"mobilevlm-v2-3b","company":"meituan","family":"MobileVLM","version":"MobileVLM V2","score":57.5},{"place":207,"model":"mini-gemini-2b","company":"cuhk","family":"Mini-Gemini","version":"Mini-Gemini","score":56.2},{"place":208,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":56},{"place":209,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":53.1},{"place":210,"model":"mplug-docowl-7b","company":"alibaba","family":"mPLUG","version":"mPLUG-DocOwl","score":52.6},{"place":211,"model":"instructblip-vicuna-13b","company":"salesforce","family":"BLIP","version":"InstructBLIP","score":50.7},{"place":212,"model":"instructblip-7b","company":"salesforce","family":"InstructBLIP","version":"InstructBLIP","score":50.1},{"place":213,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":48.9},{"place":214,"model":"janus-pro-7b","company":"bytedance","family":"Janus","version":"Janus Pro","score":45.6},{"place":215,"model":"yi-vl-6b","company":"01ai","family":"Yi","version":"Yi-VL","score":45.5},{"place":216,"model":"yi-vl-34b","company":"01ai","family":"Yi","version":"Yi-VL","score":43.4},{"place":217,"model":"blip-2-vicuna-13b","company":"salesforce","family":"BLIP","version":"BLIP-2","score":42.4},{"place":218,"model":"janus-pro-1.5b","company":"bytedance","family":"Janus","version":"Janus Pro","score":41.9},{"place":219,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":39.93},{"place":220,"model":"dreamllm-7b","company":"megvii","family":"DreamLLM","version":"DreamLLM","score":34.9},{"place":221,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":34.1},{"place":222,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":32.9},{"place":223,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":28.3},{"place":224,"model":"minigpt-4-v1-7b","company":"kaust","family":"MiniGPT","version":"MiniGPT-4-v1","score":0.6}]},{"id":"theoremqa","name":"TheoremQA","topic":"Theorem-driven STEM QA","description":"Theorem-driven question answering in math, physics, EE/CS and finance.","url":"https://github.com/TIGER-AI-Lab/TheoremQA","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2305.12524","metric":"percent","stars":"","top_model":"Qwen2 72B Instruct","top_percent":44.4,"top_model_id":"qwen2-72b-instruct","top_generation":"Qwen2","top_model_base":"Qwen2 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":87,"total_models":3854,"placements":[{"place":1,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":44.4},{"place":2,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":44.1},{"place":3,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":43.1},{"place":4,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":43.1},{"place":5,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":43},{"place":6,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":42.8},{"place":7,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":42.5},{"place":8,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":42.4},{"place":9,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":40.8},{"place":10,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":40},{"place":11,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":39.6},{"place":12,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":39.4},{"place":13,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":36},{"place":14,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":35.9},{"place":15,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":35.8},{"place":16,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":34.9},{"place":17,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":34},{"place":18,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":33.5},{"place":19,"model":"qwen2-57b-a14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":33.1},{"place":20,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":32.3},{"place":21,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":32},{"place":22,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":31.1},{"place":23,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":30.9},{"place":24,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":29.6},{"place":25,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":29.5},{"place":26,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":29.3},{"place":27,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":29.3},{"place":28,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":28.9},{"place":29,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":28.8},{"place":30,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":28.8},{"place":31,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":27.4},{"place":32,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":25.3},{"place":33,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":23.9},{"place":34,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":23.8},{"place":35,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":23.4},{"place":36,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":23.2},{"place":37,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":23},{"place":38,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":22.1},{"place":39,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":22.1},{"place":40,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":22.1},{"place":41,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":21.5},{"place":42,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":21.4},{"place":43,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":20.5},{"place":44,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":19.2},{"place":45,"model":"qwen1.5-110b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":18.8},{"place":46,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":17.5},{"place":47,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":16},{"place":48,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":16},{"place":49,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":15.9},{"place":50,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":15.8},{"place":51,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":15.6},{"place":52,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":15.4},{"place":53,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":15.3},{"place":54,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":15},{"place":55,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":14.8},{"place":56,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":14.3},{"place":57,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":14.2},{"place":58,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":14.1},{"place":59,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":14.1},{"place":60,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":13.9},{"place":61,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":13.6},{"place":62,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":13.6},{"place":63,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":13.5},{"place":64,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":12.3},{"place":65,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":12.1},{"place":66,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":12},{"place":67,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":11.4},{"place":68,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":11.3},{"place":69,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":10.5},{"place":70,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":10.4},{"place":71,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":9.6},{"place":72,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":9.6},{"place":73,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":9.5},{"place":74,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":9.3},{"place":75,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":9.1},{"place":76,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":8.9},{"place":77,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":8.9},{"place":78,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":8.1},{"place":79,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":6.5},{"place":80,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":5.8},{"place":81,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":5},{"place":82,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":4.6},{"place":83,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":3.4},{"place":84,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":3.3},{"place":85,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":2.6},{"place":86,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":2.6},{"place":87,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":2.5},{"place":88,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":2.4},{"place":89,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":2.3},{"place":90,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":1.8},{"place":91,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":1.6},{"place":92,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":1.1},{"place":93,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":1},{"place":94,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":0.3}]},{"id":"tiif-bench-long","name":"TIIF-Bench Long","topic":"Text-to-image","description":"TIIF-Bench long prompt score for text-to-image generation.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Seedream 4.5","top_percent":88.52,"top_model_id":"seedream-4.5","top_generation":"Seedream","top_model_base":"Seedream 4.5","top_model_family":"Seedream","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":88.52},{"place":2,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":88.29},{"place":3,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":88.26},{"place":4,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":88.08},{"place":5,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":86.83},{"place":6,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":84.93},{"place":7,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":83.01},{"place":8,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":81.02},{"place":9,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":80.05},{"place":10,"model":"flux-1-dev","company":"black-forest-labs","family":"FLUX.1","version":"FLUX.1","score":71.78},{"place":11,"model":"bagel","company":"jondurbin","family":"Bagel","version":"Bagel","score":71.7},{"place":12,"model":"dall-e-3","company":"openai","family":"DALL-E","version":"DALL-E 3","score":70.81},{"place":13,"model":"sd3-medium","company":"stabilityai","family":"Stable Diffusion 3","version":"SD3","score":66.09},{"place":14,"model":"janus-pro","company":"bytedance","family":"Janus","version":"Janus Pro","score":65.01},{"place":15,"model":"show-o2","company":"unknown","family":"Show-o","version":"Show-o2","score":58.86},{"place":16,"model":"sd-xl","company":"stabilityai","family":"Stable Diffusion","version":"SD XL","score":42.13}]},{"id":"tiif-bench-short","name":"TIIF-Bench Short","topic":"Text-to-image","description":"TIIF-Bench short prompt score for text-to-image generation.","url":"","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Nano Banana 2.0","top_percent":91,"top_model_id":"nano-banana-2.0","top_generation":"Nano Banana","top_model_base":"Nano Banana 2.0","top_model_family":"Nano Banana","top_company":"unknown","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"nano-banana-2.0","company":"unknown","family":"Nano Banana","version":"Nano Banana","score":91},{"place":2,"model":"seedream-4.5","company":"bytedance","family":"Seedream","version":"Seedream","score":90.49},{"place":3,"model":"seedream-4.0","company":"bytedance","family":"Seedream","version":"Seedream","score":90.45},{"place":4,"model":"gpt-image-1-high","company":"openai","family":"GPT Image","version":"GPT Image 1","score":89.15},{"place":5,"model":"qwen-image","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":86.14},{"place":6,"model":"qwen-image-2512","company":"qwen","family":"Qwen-Image","version":"Qwen-Image","score":83.24},{"place":7,"model":"glm-image","company":"zai","family":"GLM","version":"GLM-Image","score":81.01},{"place":8,"model":"z-image","company":"zai","family":"Z-Image","version":"Z-Image","score":80.2},{"place":9,"model":"z-image-turbo","company":"zai","family":"Z-Image","version":"Z-Image","score":77.73},{"place":10,"model":"dall-e-3","company":"openai","family":"DALL-E","version":"DALL-E 3","score":74.96},{"place":11,"model":"bagel","company":"jondurbin","family":"Bagel","version":"Bagel","score":71.5},{"place":12,"model":"flux-1-dev","company":"black-forest-labs","family":"FLUX.1","version":"FLUX.1","score":71.09},{"place":13,"model":"sd3-medium","company":"stabilityai","family":"Stable Diffusion 3","version":"SD3","score":67.46},{"place":14,"model":"janus-pro","company":"bytedance","family":"Janus","version":"Janus Pro","score":66.5},{"place":15,"model":"show-o2","company":"unknown","family":"Show-o","version":"Show-o2","score":59.72},{"place":16,"model":"sd-xl","company":"stabilityai","family":"Stable Diffusion","version":"SD XL","score":54.96}]},{"id":"timelens-activitynet","name":"ActivityNet-TimeLens","topic":"Video temporal grounding","description":"TimeLens-Bench re-annotated ActivityNet Captions split for video temporal grounding (mIoU).","url":"https://arxiv.org/abs/2512.14698","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Keye-VL-2.0-30B-A3B","top_percent":58.5,"top_model_id":"keye-vl-2.0-30b-a3b","top_generation":"Keye-VL 2.0","top_model_base":"Keye-VL 2.0 30B A3B","top_model_family":"Keye-VL","top_company":"kuaishou","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":58.5},{"place":2,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.2},{"place":3,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":52.12},{"place":4,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.1},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.59},{"place":6,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":42.99},{"place":7,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":36.6},{"place":8,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":13.44}]},{"id":"timelens-charades","name":"Charades-TimeLens","topic":"Video temporal grounding","description":"TimeLens-Bench re-annotated Charades-STA split for video temporal grounding (mIoU).","url":"https://arxiv.org/abs/2512.14698","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Keye-VL-2.0-30B-A3B","top_percent":58.4,"top_model_id":"keye-vl-2.0-30b-a3b","top_generation":"Keye-VL 2.0","top_model_base":"Keye-VL 2.0 30B A3B","top_model_family":"Keye-VL","top_company":"kuaishou","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":58.4},{"place":2,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":50.45},{"place":3,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.1},{"place":4,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":47.8},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.77},{"place":6,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":44.26},{"place":7,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":39.29},{"place":8,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":20.29}]},{"id":"timelens-qvhighlights","name":"QVHighlights-TimeLens","topic":"Video temporal grounding","description":"TimeLens-Bench re-annotated QVHighlights split for video temporal grounding (mIoU).","url":"https://arxiv.org/abs/2512.14698","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Keye-VL-2.0-30B-A3B","top_percent":70.1,"top_model_id":"keye-vl-2.0-30b-a3b","top_generation":"Keye-VL 2.0","top_model_base":"Keye-VL 2.0 30B A3B","top_model_family":"Keye-VL","top_company":"kuaishou","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":70.1},{"place":2,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.7},{"place":3,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":65.03},{"place":4,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.6},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.08},{"place":6,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":54.63},{"place":7,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":50.52},{"place":8,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":9.02}]},{"id":"tir-bench","name":"TIR-Bench","topic":"Tool-integrated reasoning","description":"Benchmark for tool-integrated reasoning with visual models.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-397B-A17B","top_percent":62.5,"top_model_id":"qwen3.5-397b-a17b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 397B A17B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.5},{"place":2,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":61.6},{"place":3,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.8},{"place":4,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.5},{"place":5,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.2},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":47.5},{"place":7,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.6},{"place":8,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.9},{"place":9,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":32.3},{"place":10,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":29.8},{"place":11,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":29.2},{"place":12,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":27.6},{"place":13,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":24.6},{"place":14,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":22.5},{"place":15,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":21.5},{"place":16,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":18.5}]},{"id":"tldr9-plus","name":"TLDR9+","topic":"Summarization","description":"Long-form summarization benchmark with nine-domain TLDR prompts plus extended variations.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MobileLLM P1","top_percent":16.8,"top_model_id":"mobilellm-p1","top_generation":"MobileLLM","top_model_base":"MobileLLM P1","top_model_family":"MobileLLM","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":16.8},{"place":2,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":16.8}]},{"id":"tomato","name":"TOMATO","topic":"Temporal understanding","description":"Temporal ordering and motion analysis benchmark (TOMATO).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":96.02,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":42,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":96.02},{"place":2,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":93.6},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":89.02},{"place":4,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":83.02},{"place":5,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":79.5},{"place":6,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":72.5},{"place":7,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":72.44},{"place":8,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":71.9},{"place":9,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":60.8},{"place":10,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":60.8},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":60.4},{"place":12,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":59.9},{"place":13,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":57.3},{"place":14,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":56.8},{"place":15,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":55.8},{"place":16,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":53},{"place":17,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":50.3},{"place":18,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":48.6},{"place":19,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":48.3},{"place":20,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":47.4},{"place":21,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":44.9},{"place":22,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":44.1},{"place":23,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":41.85},{"place":24,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":39.8},{"place":25,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":39.6},{"place":26,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":39.6},{"place":27,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":39.1},{"place":28,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":38.68},{"place":29,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":37.3},{"place":30,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":36.2},{"place":31,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":36.05},{"place":32,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":35.7},{"place":33,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":33.2},{"place":34,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":33},{"place":35,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":32.5},{"place":36,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":31.8},{"place":37,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":31},{"place":38,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":30.9},{"place":39,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":30.66},{"place":40,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":30},{"place":41,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":29.8},{"place":42,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":26.8},{"place":43,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":24.9},{"place":44,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":24.6}]},{"id":"tomg-bench","name":"TOMG-Bench","topic":"Molecule generation","description":"Text-based open molecule generation benchmark (editing, optimization, customized generation).","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2412.14642","metric":"percent","stars":"","top_model":"GPT-5.5","top_percent":69.89,"top_model_id":"gpt-5.5","top_generation":"GPT-5.5","top_model_base":"GPT-5.5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":69.89},{"place":2,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":66.76},{"place":3,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":65.66},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":62.67},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":61.38},{"place":6,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":58.28},{"place":7,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":57.89},{"place":8,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.63},{"place":9,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.06}]},{"id":"tool-decathlon","name":"Tool-Decathlon","topic":"Agent tool-use","description":"Composite tool-use suite measuring multi-domain tool invocation success (Pass@1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.2","top_percent":43.8,"top_model_id":"gpt-5.2","top_generation":"GPT-5.2","top_model_base":"GPT-5.2","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":43.8},{"place":2,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.5},{"place":3,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.8},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.6},{"place":5,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.3},{"place":6,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":38},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":36.4},{"place":8,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":35.2},{"place":9,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.5},{"place":10,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":29},{"place":11,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.7},{"place":12,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":27.8},{"place":13,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":26.9},{"place":14,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":21.2},{"place":15,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":18.8},{"place":16,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":17.6},{"place":17,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":16},{"place":18,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":12}]},{"id":"toolace","name":"ToolACE","topic":"Tool calling","description":"ToolACE function-calling evaluation, posed as decisions.","url":"https://huggingface.co/datasets/Team-ACE/ToolACE","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-Decision-2B","top_percent":96.45,"top_model_id":"intern-decision-2b","top_generation":"Intern-Decision","top_model_base":"Intern-Decision","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":96.45},{"place":2,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":96.45},{"place":3,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":94.52},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":91.29},{"place":5,"model":"semif","company":"theoleecj","family":"SemIf","version":"SemIf","score":85.16},{"place":6,"model":"jevk5","company":"alibiserikbay","family":"JevK5","version":"JevK5","score":80.97},{"place":7,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":63.87}]},{"id":"toolathlon","name":"Toolathlon","topic":"Agentic software tasks","description":"Long-horizon, real-world software tool-use tasks.","url":"","leaderboard":"https://toolathlon.xyz/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":80.6,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":61,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.6},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":77.8},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":77.8},{"place":4,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":77.8},{"place":5,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":65.4},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":61.7},{"place":7,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":61.7},{"place":8,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":61.1},{"place":9,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":60.2},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":59.9},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":58},{"place":12,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":56.6},{"place":13,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":56.5},{"place":14,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":55.6},{"place":15,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":54.6},{"place":16,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":54.6},{"place":17,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":54.6},{"place":18,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.3},{"place":19,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":53.4},{"place":20,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":53.1},{"place":21,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.8},{"place":22,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":52.8},{"place":23,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":52.8},{"place":24,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":51.9},{"place":25,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":51.9},{"place":26,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.8},{"place":27,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":50.6},{"place":28,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":50},{"place":29,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":49.5},{"place":30,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":49.4},{"place":31,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":49.1},{"place":32,"model":"deepseek-v4-pro-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49},{"place":33,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":48.8},{"place":34,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":48.5},{"place":35,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":48.2},{"place":36,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":48.1},{"place":37,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":47.8},{"place":38,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":47.2},{"place":39,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":46.3},{"place":40,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":46.3},{"place":41,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46.3},{"place":42,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":46.3},{"place":43,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":45.7},{"place":44,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":45.1},{"place":45,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":44.8},{"place":46,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":43.5},{"place":47,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":43.5},{"place":48,"model":"deepseek-v4-flash-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":43.5},{"place":49,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":42.9},{"place":50,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":41.7},{"place":51,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":40.7},{"place":52,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40.7},{"place":53,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":39.8},{"place":54,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.9},{"place":55,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":38.9},{"place":56,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":38.3},{"place":57,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":38},{"place":58,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":36.4},{"place":59,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":35.5},{"place":60,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":35.2},{"place":61,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":35.2},{"place":62,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":33.3},{"place":63,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":33.3},{"place":64,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":32.1},{"place":65,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":27.8},{"place":66,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":26.9},{"place":67,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":16.7},{"place":68,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":10.5},{"place":69,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":3.7}]},{"id":"toolathlon-verified","name":"Toolathlon Verified","topic":"Tool use","description":"Verified version of Toolathlon (The Tool Decathlon), run via the official evaluation service; pass@1 averaged over 3 runs.","url":"","leaderboard":"https://toolathlon.xyz/","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":80.6,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":61,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":80.6},{"place":2,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":78.4},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":77.9},{"place":4,"model":"mimo-v2.6-pro-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":76.9},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":76.5},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":76.5},{"place":7,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":76.2},{"place":8,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.9},{"place":9,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":75.6},{"place":10,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":74.9},{"place":11,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":74.9},{"place":12,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":74.7},{"place":13,"model":"nex-n2.5-max","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":74.7},{"place":14,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.1},{"place":15,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":74.1},{"place":16,"model":"mimo-v2.6-flash-rl","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":73.6},{"place":17,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.5},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":73.5},{"place":19,"model":"qwen3.8-max-0902","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.3},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":73.2},{"place":21,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":73.2},{"place":22,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":73},{"place":23,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":72.8},{"place":24,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":72.5},{"place":25,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":71.4},{"place":26,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":71.2},{"place":27,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":70.8},{"place":28,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":70.7},{"place":29,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":70.4},{"place":30,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":70.3},{"place":31,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":68.5},{"place":32,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":68.5},{"place":33,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":67.9},{"place":34,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":67.1},{"place":35,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":63.5},{"place":36,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":61.1},{"place":37,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":60.1},{"place":38,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":59.9},{"place":39,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":57.1},{"place":40,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":56.8},{"place":41,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":56.2},{"place":42,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.9},{"place":43,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":55.9},{"place":44,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":55.6},{"place":45,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":54.6},{"place":46,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":54.4},{"place":47,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.8},{"place":48,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.9},{"place":49,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.9},{"place":50,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":50.6},{"place":51,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.7},{"place":52,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":49.7},{"place":53,"model":"laguna-s-2.1","company":"poolside","family":"Laguna","version":"Laguna 2.1","score":49.7},{"place":54,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":49.4},{"place":55,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":49.1},{"place":56,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":49.1},{"place":57,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":48.7},{"place":58,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":48.2},{"place":59,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":47.5},{"place":60,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":47.2},{"place":61,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":45.5},{"place":62,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":43.2},{"place":63,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":42.4},{"place":64,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":41.7},{"place":65,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":41.2},{"place":66,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.8},{"place":67,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":40.7},{"place":68,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":38.3},{"place":69,"model":"mimo-v2.6-distill-qwen-9b","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":35.2},{"place":70,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":34.3},{"place":71,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":33.4},{"place":72,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.6},{"place":73,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":27.8},{"place":74,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":26.9},{"place":75,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":25.9}]},{"id":"toolhop","name":"ToolHop","topic":"Multi-hop tool use","description":"Query-driven benchmark of 995 multi-hop tool-use queries with 3,912 locally executable tools; answer accuracy.","url":"https://arxiv.org/abs/2501.02506","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-9B","top_percent":52,"top_model_id":"qwen3.5-9b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 9B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":52},{"place":2,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":49.1},{"place":3,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":46.7},{"place":4,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":39.9}]},{"id":"toolret-decision","name":"ToolRet (decision)","topic":"Tool retrieval","description":"Rate usefulness of 32 retrieved tools per request; nDCG@10. Jev Decision Index adaptation posed as typed decisions; not comparable to the generative benchmark.","url":"https://huggingface.co/datasets/mangopy/ToolRet-Queries","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"ndcg@10","stars":"","top_model":"Clef","top_percent":69.2,"top_model_id":"clef","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":69.2},{"place":2,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":69.1},{"place":3,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":68.5},{"place":4,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":68.3},{"place":5,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":68.2},{"place":6,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":67.5},{"place":7,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":67.1},{"place":8,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":66.6},{"place":9,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":66.5},{"place":10,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":66.4},{"place":11,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":65.7},{"place":12,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":65.7},{"place":13,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":65.6},{"place":14,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":65.3},{"place":15,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":65.3},{"place":16,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":65.1},{"place":17,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":65.1},{"place":18,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":65},{"place":19,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":65},{"place":20,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":64.4},{"place":21,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":64.3},{"place":22,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":62.7},{"place":23,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":62},{"place":24,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":61.8},{"place":25,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61.4},{"place":26,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":61.2},{"place":27,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61.2},{"place":28,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":60.5},{"place":29,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59.7},{"place":30,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":58},{"place":31,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":57.2},{"place":32,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":57},{"place":33,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":52.8},{"place":34,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":49},{"place":35,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":47.4},{"place":36,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":38.2},{"place":37,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":15.7},{"place":38,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":12.8}]},{"id":"toolsandbox","name":"ToolSandbox","topic":"Tool use","description":"Apple's stateful, conversational, interactive tool-use benchmark with simulated user.","url":"https://github.com/apple/ToolSandbox","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LFM2.5 24B A2B","top_percent":80.71,"top_model_id":"lfm2.5-24b-a2b","top_generation":"LFM2.5","top_model_base":"LFM2.5 24B A2B","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":80.71},{"place":2,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":77.83},{"place":3,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.44},{"place":4,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.55},{"place":5,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":75.13},{"place":6,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75.02},{"place":7,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.51},{"place":8,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":74.13},{"place":9,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":72.09},{"place":10,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69.54},{"place":11,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":68.77},{"place":12,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":68.31},{"place":13,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65.43},{"place":14,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":65},{"place":15,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65},{"place":16,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":61.6},{"place":17,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":59.78},{"place":18,"model":"lfm2.5-vl-3b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":59.5},{"place":19,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":57.88},{"place":20,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":56.5},{"place":21,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":52.4},{"place":22,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":47.7},{"place":23,"model":"lfm2-vl-3b","company":"liquidai","family":"LFM","version":"LFM2-VL","score":26.4}]},{"id":"topiocqa","name":"TopiOCQA","topic":"Conversational QA","description":"Topic-switching open-domain conversational QA (ChatRAG-Bench subset).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Yuan3.0 Ultra","top_percent":72.4,"top_model_id":"yuan3.0-ultra","top_generation":"Yuan3.0","top_model_base":"Yuan","top_model_family":"Yuan3.0","top_company":"yuanlab","top_open_source":1,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":72.4},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":50.8},{"place":3,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":50.2},{"place":4,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":49.8},{"place":5,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":46.7},{"place":6,"model":"o3","company":"openai","family":"o3","version":"o3","score":45.9},{"place":7,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":44.7},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":42.4},{"place":9,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":38.3},{"place":10,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":30.7}]},{"id":"totaltext-f1","name":"TotalText (F1)","topic":"OCR","description":"TotalText text grounding and recognition, F1 mean.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":52,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":52},{"place":2,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":43.3},{"place":3,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":42.5},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":40.6},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":35.4},{"place":6,"model":"pp-ocrv5","company":"paddlepaddle","family":"PP-OCR","version":"PP-OCRv5","score":25.7}]},{"id":"treebench","name":"TreeBench","topic":"Reasoning with tree structures","description":"Evaluates hierarchical/tree-structured reasoning and planning capabilities in LLMs/VLMs.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2507.07999","metric":"percent","stars":"","top_model":"Seed2.1 Turbo","top_percent":71.1,"top_model_id":"seed2.1-turbo","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Turbo","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":71.1},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":71.1},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":61.5},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":60.5},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":54.6},{"place":6,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":51.4},{"place":7,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":50.1},{"place":8,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.6},{"place":9,"model":"skywork-r1v4","company":"skywork","family":"Skywork","version":"Skywork R1V4","score":48.4},{"place":10,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":45.9},{"place":11,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":45.7},{"place":12,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.7},{"place":13,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":41.5},{"place":14,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":41.3},{"place":15,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":37.5},{"place":16,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":36.8},{"place":17,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":33.8}]},{"id":"triqa","name":"TriQA","topic":"Knowledge QA","description":"Triadic question answering benchmark evaluating world knowledge and reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Mixtral 8x22B","top_percent":82.2,"top_model_id":"mixtral-8x22b","top_generation":"Mixtral","top_model_base":"Mixtral 8x22B","top_model_family":"Mixtral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":82.2},{"place":2,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":78.4},{"place":3,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":77.57},{"place":4,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":68.8}]},{"id":"triviaqa","name":"TriviaQA","topic":"Open-domain QA","description":"Open-domain question answering benchmark built from trivia and web evidence.","url":"https://nlp.cs.washington.edu/triviaqa/","leaderboard":"","github":"https://github.com/mandarjoshi90/triviaqa","paper":"https://arxiv.org/abs/1705.03551","metric":"percent","stars":"","top_model":"Nemotron-3-Super-120B-A12B-Base","top_percent":89.8,"top_model_id":"nemotron-3-super-120b-a12b-base","top_generation":"Nemotron 3","top_model_base":"Nemotron-3 Super 120B A12B Base","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":169,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":89.8},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":89.4},{"place":3,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":89.2},{"place":4,"model":"deepseek-v2-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":86.7},{"place":5,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.4},{"place":6,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.6},{"place":7,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":85.5},{"place":8,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":85.5},{"place":9,"model":"deepseek-v2-chat-sft","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":85.4},{"place":10,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85.1},{"place":11,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":85},{"place":12,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":84.5},{"place":13,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.9},{"place":14,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":83.8},{"place":15,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":83.5},{"place":16,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":83.5},{"place":17,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":83.3},{"place":18,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.3},{"place":19,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":82.9},{"place":20,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.8},{"place":21,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":82.7},{"place":22,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":82.62},{"place":23,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":82.3},{"place":24,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":82.1},{"place":25,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":81.62},{"place":26,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":81.6},{"place":27,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":81.5},{"place":28,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":81.3},{"place":29,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":80.96},{"place":30,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":80.7},{"place":31,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":80.3},{"place":32,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":80},{"place":33,"model":"mixtral-8x22b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":80},{"place":34,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":80},{"place":35,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":79.9},{"place":36,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":79.6},{"place":37,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.5},{"place":38,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":79.5},{"place":39,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":79},{"place":40,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":78.9},{"place":41,"model":"gemma-3-12b-base","company":"google","family":"Gemma","version":"Gemma 3","score":78.8},{"place":42,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":78.6},{"place":43,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":78.2},{"place":44,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.6},{"place":45,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":77.4},{"place":46,"model":"kolibri-1-base","company":"alephalpha","family":"Kolibri","version":"Kolibri 1","score":77.2},{"place":47,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":77.2},{"place":48,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":77.2},{"place":49,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":75.52},{"place":50,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":75.2},{"place":51,"model":"ministral-3-14b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":74.9},{"place":52,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.7},{"place":53,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.6},{"place":54,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":74.32},{"place":55,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":73.1},{"place":56,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":73},{"place":57,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":72.93},{"place":58,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":72.55},{"place":59,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":72.2},{"place":60,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.9},{"place":61,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":71.5},{"place":62,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":71.4},{"place":63,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":71.3},{"place":64,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":70.71},{"place":65,"model":"qwen3-14b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":70.3},{"place":66,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":69.9},{"place":67,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":69.79},{"place":68,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":69.76},{"place":69,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":69.6},{"place":70,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":69.1},{"place":71,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":69},{"place":72,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":68.9},{"place":73,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":68.9},{"place":74,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":68.5},{"place":75,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":68.2},{"place":76,"model":"ministral-3-8b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":68.1},{"place":77,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":67.3},{"place":78,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":66.88},{"place":79,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":66.24},{"place":80,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":66.2},{"place":81,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":65.61},{"place":82,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":65.6},{"place":83,"model":"deepseek-v2-lite-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":65.2},{"place":84,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":65},{"place":85,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":64.8},{"place":86,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":64.2},{"place":87,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":64},{"place":88,"model":"gemma-3-4b-base","company":"google","family":"Gemma","version":"Gemma 3","score":64},{"place":89,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":64},{"place":90,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":63.9},{"place":91,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":63.9},{"place":92,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":63.8},{"place":93,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":63.7},{"place":94,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":63.4},{"place":95,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":63.4},{"place":96,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":63.3},{"place":97,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":62.5},{"place":98,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":62.5},{"place":99,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":62},{"place":100,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":61.8},{"place":101,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":61.8},{"place":102,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":60.7},{"place":103,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":60.2},{"place":104,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":60.1},{"place":105,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":59.7},{"place":106,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":59.6},{"place":107,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":59.5},{"place":108,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":59.5},{"place":109,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":59.4},{"place":110,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":59.36},{"place":111,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":59.2},{"place":112,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":59},{"place":113,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":58.9},{"place":114,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":58},{"place":115,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":57.9},{"place":116,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":57.7},{"place":117,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":57.3},{"place":118,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":57.26},{"place":119,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":57},{"place":120,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":56.8},{"place":121,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":56.6},{"place":122,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":56.47},{"place":123,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":56.32},{"place":124,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":55.9},{"place":125,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":55.63},{"place":126,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":55.5},{"place":127,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":55.5},{"place":128,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":54.7},{"place":129,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":54.5},{"place":130,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54.4},{"place":131,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":54.24},{"place":132,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":54.2},{"place":133,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":54.1},{"place":134,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":54},{"place":135,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":53.9},{"place":136,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":53.33},{"place":137,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":53.3},{"place":138,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":53.2},{"place":139,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":53.1},{"place":140,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":53},{"place":141,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":52.51},{"place":142,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":52.47},{"place":143,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":52.44},{"place":144,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":51.94},{"place":145,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":51.6},{"place":146,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":51.4},{"place":147,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":51.33},{"place":148,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":51},{"place":149,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":50.8},{"place":150,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":48.4},{"place":151,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":48.1},{"place":152,"model":"afm-4.5b","company":"arcee","family":"AFM","version":"AFM","score":47.66},{"place":153,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":46.8},{"place":154,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":46.79},{"place":155,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":46.7},{"place":156,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":46.61},{"place":157,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":46.6},{"place":158,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":46.1},{"place":159,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":46},{"place":160,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":45.16},{"place":161,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":45.06},{"place":162,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":44.32},{"place":163,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":42.36},{"place":164,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":42.1},{"place":165,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":40.3},{"place":166,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":39.85},{"place":167,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":39.8},{"place":168,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":38.77},{"place":169,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":38.1},{"place":170,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":37.6},{"place":171,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":37.6},{"place":172,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":37.3},{"place":173,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":36.7},{"place":174,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":35.1},{"place":175,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":35},{"place":176,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":34.9},{"place":177,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":32.3},{"place":178,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":31.97},{"place":179,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":31.5},{"place":180,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":31.2},{"place":181,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":30.95},{"place":182,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":30.5},{"place":183,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":29},{"place":184,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":28.1},{"place":185,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.1},{"place":186,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":27.91},{"place":187,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":27.09},{"place":188,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":26.65},{"place":189,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":24.31},{"place":190,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":23.81},{"place":191,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":22.5},{"place":192,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":20.9},{"place":193,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":20.4},{"place":194,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":19.9},{"place":195,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":16.97},{"place":196,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":16.1},{"place":197,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":15.4},{"place":198,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":14.8},{"place":199,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":9.1},{"place":200,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":4.3},{"place":201,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":4.3},{"place":202,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.757},{"place":203,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.582}]},{"id":"triviaqa-wiki","name":"TriviaQA-Wiki","topic":"Open-domain QA","description":"TriviaQA subset answering using Wikipedia evidence.","url":"http://nlp.cs.washington.edu/triviaqa/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Llama 3.1 405B Base","top_percent":91.8,"top_model_id":"llama-3.1-405b-base","top_generation":"Llama 3.1","top_model_base":"Llama 3.1 405B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":91.8},{"place":2,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":91.8},{"place":3,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":89.8},{"place":4,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":89.7},{"place":5,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":78.5},{"place":6,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":77.6}]},{"id":"troubleshootingbench","name":"TroubleshootingBench","topic":"Biosecurity","description":"OpenAI bio eval of troubleshooting expert-written wet-lab protocols (pass@1).","url":"https://deploymentsafety.openai.com/gpt-6-1-sol","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-6 Astra","top_percent":63.46,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":63.46},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":48},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":47.96},{"place":4,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":45.3},{"place":5,"model":"gpt-6-sol-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":41.83},{"place":6,"model":"gpt-6-luna-2026-10-07","company":"openai","family":"GPT","version":"GPT-6","score":41.46},{"place":7,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":38.6}]},{"id":"trustllm","name":"TrustLLM","topic":"Safety / reliability","description":"TrustLLM benchmark for trustworthiness and safety behaviors.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-Coder-480B-A35B-Instruct","top_percent":88.4,"top_model_id":"qwen3-coder-480b-a35b-instruct","top_generation":"Qwen3","top_model_base":"Qwen3 Coder 480B A35B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":88.4},{"place":2,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":86.4},{"place":3,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.2},{"place":4,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":65}]},{"id":"truthfulqa","name":"TruthfulQA","topic":"Truthfulness / hallucination","description":"Measures whether a model imitates human falsehoods (truthfulness).","url":"https://github.com/sylinrl/TruthfulQA","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2109.07958","metric":"percent","stars":"","top_model":"SOLAR-10.7B-Instruct-v1.0","top_percent":71.43,"top_model_id":"solar-10.7b-instruct-v1.0","top_generation":"Solar Mini","top_model_base":"SOLAR-10.7B-Instruct-v1.0","top_model_family":"Solar","top_company":"upstage","top_open_source":1,"lower_is_better":false,"bench_models":169,"total_models":3854,"placements":[{"place":1,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":71.43},{"place":2,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":71.18},{"place":3,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.28},{"place":4,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.9},{"place":5,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":69.8},{"place":6,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":68.8},{"place":7,"model":"gemma-3","company":"google","family":"Gemma","version":"Gemma 3","score":68.7},{"place":8,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":68.26},{"place":9,"model":"llama-3.1-tulu-3-70b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":67.9},{"place":10,"model":"llama-3.1-tulu-3-70b","company":"allenai","family":"Llama","version":"Tulu 3","score":67.6},{"place":11,"model":"apertus-v1.5-70b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":67},{"place":12,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":66.95},{"place":13,"model":"granite-3.2-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":66.92},{"place":14,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":66.86},{"place":15,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.8},{"place":16,"model":"hermes-3-llama-3.1-70b","company":"nousresearch","family":"Hermes","version":"Hermes 3","score":66.5},{"place":17,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":66.2},{"place":18,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":66.15},{"place":19,"model":"granite-3.1-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":65.84},{"place":20,"model":"falcon-h1-34b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":65.27},{"place":21,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":64.8},{"place":22,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":64.33},{"place":23,"model":"aquilachat2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":64.3},{"place":24,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":64.26},{"place":25,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.1},{"place":26,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":63.1},{"place":27,"model":"llama-4-scout-17b","company":"meta","family":"Llama","version":"Llama 4","score":62.74},{"place":28,"model":"llama-3.1-nemotron-70b","company":"nvidia","family":"Nemotron","version":"Llama 3.1 Nemotron","score":62.6},{"place":29,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":62.43},{"place":30,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":62.41},{"place":31,"model":"yi-34b-chat","company":"01ai","family":"Yi","version":"Yi 34B Chat","score":62.4},{"place":32,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":61.9},{"place":33,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":61.84},{"place":34,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":61.84},{"place":35,"model":"yi-34b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":61.8},{"place":36,"model":"yi-34b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":61.8},{"place":37,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":61.4},{"place":38,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":61.02},{"place":39,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":60.5},{"place":40,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.5},{"place":41,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":60.4},{"place":42,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":60.36},{"place":43,"model":"falcon-h1-7b","company":"tii","family":"Falcon","version":"Falcon H1","score":59.91},{"place":44,"model":"granite-3.2-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.2","score":59.8},{"place":45,"model":"granite-3.1-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.1","score":59.79},{"place":46,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":59.6},{"place":47,"model":"bielik-11b-v2.1-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.1","score":59.35},{"place":48,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.1},{"place":49,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":59},{"place":50,"model":"granite-3.3-2b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":58.97},{"place":51,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":58.58},{"place":52,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.4},{"place":53,"model":"bielik-11b-v2.2-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.2","score":58.34},{"place":54,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":58.3},{"place":55,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":58.11},{"place":56,"model":"granite-4.0-tiny-preview","company":"IBM","family":"Granite","version":"Granite 4.0","score":58.07},{"place":57,"model":"yuan2.0-102b","company":"yuanlab","family":"Yuan","version":"Yuan2.0","score":58},{"place":58,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":57.8},{"place":59,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":57.71},{"place":60,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":57.7},{"place":61,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":57.5},{"place":62,"model":"bielik-11b-v2.3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.3","score":57.42},{"place":63,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":57.4},{"place":64,"model":"magpie-8b","company":"allenai","family":"Magpie","version":"Magpie","score":57},{"place":65,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":56.6},{"place":66,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.4},{"place":67,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":56.3},{"place":68,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":56.28},{"place":69,"model":"apertus-v1.5-8b","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":56.2},{"place":70,"model":"llama-3.1-tulu-3-8b-dpo","company":"allenai","family":"Llama","version":"Tulu 3","score":56.1},{"place":71,"model":"llama-3.1-tulu-3-70b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":55.7},{"place":72,"model":"falcon3-7b","company":"tii","family":"Falcon","version":"Falcon 3","score":55.58},{"place":73,"model":"ministral-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral","score":55.5},{"place":74,"model":"marin-8b-instruct","company":"marin","family":"Marin","version":"Marin 8B","score":55.3},{"place":75,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":55.2},{"place":76,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":55.1},{"place":77,"model":"falcon3-10b","company":"tii","family":"Falcon","version":"Falcon 3","score":55.05},{"place":78,"model":"llama-3.1-tulu-3-8b","company":"allenai","family":"Llama","version":"Tulu 3","score":55},{"place":79,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":55},{"place":80,"model":"openchat-3.5-0106-gemma","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":54.93},{"place":81,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":54.9},{"place":82,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":54.8},{"place":83,"model":"bielik-11b-v2.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.0","score":54.65},{"place":84,"model":"bielik-11b-v3.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":54.25},{"place":85,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":54.2},{"place":86,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":54.2},{"place":87,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":54},{"place":88,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54},{"place":89,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":54},{"place":90,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":53.95},{"place":91,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":53.9},{"place":92,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":53.54},{"place":93,"model":"bielik-11b-v2.6-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.6","score":53.43},{"place":94,"model":"falcon-h1-3b","company":"tii","family":"Falcon","version":"Falcon H1","score":53.19},{"place":95,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":53.19},{"place":96,"model":"bielik-11b-v2.5-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.5","score":53.17},{"place":97,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":52.99},{"place":98,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":52.5},{"place":99,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":52.49},{"place":100,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":52.06},{"place":101,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":51.9},{"place":102,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":51.8},{"place":103,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.75},{"place":104,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":51.75},{"place":105,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":51.68},{"place":106,"model":"qwen3-0.8b","company":"qwen","family":"Qwen","version":"Qwen3","score":51.65},{"place":107,"model":"meta-llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":51.65},{"place":108,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":51.1},{"place":109,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":51.1},{"place":110,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":51},{"place":111,"model":"bielik-4.5b-v3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":50.79},{"place":112,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":50.6},{"place":113,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":50.6},{"place":114,"model":"yi-6b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":50.58},{"place":115,"model":"falcon-h1-1.5b-deep","company":"tii","family":"Falcon","version":"Falcon H1","score":50.48},{"place":116,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":50.3},{"place":117,"model":"yi-6b-chat-4bits","company":"01ai","family":"Yi","version":"Yi","score":50.29},{"place":118,"model":"llama-3.2-3b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":50.27},{"place":119,"model":"falcon3-3b","company":"tii","family":"Falcon","version":"Falcon 3","score":50.06},{"place":120,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":49.9},{"place":121,"model":"yi-6b-chat-8bits","company":"01ai","family":"Yi","version":"Yi","score":49.85},{"place":122,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":49.7},{"place":123,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":49.6},{"place":124,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":49.5},{"place":125,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":49.43},{"place":126,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":49.39},{"place":127,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":49.2},{"place":128,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":49},{"place":129,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":48.98},{"place":130,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":48.9},{"place":131,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":47.85},{"place":132,"model":"bielik-11b-v3.0","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":47.65},{"place":133,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":47.43},{"place":134,"model":"eurollm-9b-instruct-2512","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":47.4},{"place":135,"model":"bielik-7b-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":47.16},{"place":136,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":47.14},{"place":137,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":47.05},{"place":138,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":46.99},{"place":139,"model":"llama-3.1-tulu-3-8b-sft","company":"allenai","family":"Llama","version":"Tulu 3","score":46.8},{"place":140,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.6},{"place":141,"model":"jamba-v0.1","company":"ai21","family":"Jamba","version":"Jamba","score":46.4},{"place":142,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":46.19},{"place":143,"model":"bielik-7b-instruct-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":46.18},{"place":144,"model":"bielik-11b-v2","company":"SpeakLeash","family":"Bielik","version":"Bielik v2","score":46.13},{"place":145,"model":"falcon-h1-1.5b","company":"tii","family":"Falcon","version":"Falcon H1","score":45.98},{"place":146,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":45.9},{"place":147,"model":"bielik-4.5b-v3","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":45.63},{"place":148,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":45.6},{"place":149,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":45.6},{"place":150,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":45.3},{"place":151,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":44.91},{"place":152,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":44.8},{"place":153,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":44.8},{"place":154,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":44.8},{"place":155,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":44.5},{"place":156,"model":"falcon-h1-0.5b-instruct","company":"tii","family":"Falcon","version":"Falcon H1","score":44.12},{"place":157,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":44},{"place":158,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":44},{"place":159,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":42.93},{"place":160,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":42.7},{"place":161,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":42.7},{"place":162,"model":"falcon3-1b","company":"tii","family":"Falcon","version":"Falcon 3","score":42.31},{"place":163,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":42.2},{"place":164,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":42.2},{"place":165,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":42.2},{"place":166,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":42.17},{"place":167,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":42.15},{"place":168,"model":"llama-3.2-1.24b-base","company":"meta","family":"Llama","version":"Llama 3.2","score":42.08},{"place":169,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":42},{"place":170,"model":"mistral-7b-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":41.76},{"place":171,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":41.4},{"place":172,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":40.5},{"place":173,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":40.2},{"place":174,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":40.2},{"place":175,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":40.1},{"place":176,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":40},{"place":177,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":39.8},{"place":178,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":39.7},{"place":179,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":39.4},{"place":180,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":39.34},{"place":181,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":38.8},{"place":182,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":38.75},{"place":183,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":37.9},{"place":184,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":37.55},{"place":185,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":36.84},{"place":186,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":36.8},{"place":187,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":36.2},{"place":188,"model":"gpt-3.5-turbo","company":"openai","family":"GPT","version":"GPT-3.5","score":34},{"place":189,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":33.1},{"place":190,"model":"gopher-280b","company":"google","family":"Gopher","version":"Gopher","score":29.5},{"place":191,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":21},{"place":192,"model":"opt-175b","company":"meta","family":"OPT","version":"175B","score":21},{"place":193,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.191},{"place":194,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.176}]},{"id":"truthfulqa-binary","name":"TruthfulQA (binary)","topic":"Truthfulness","description":"Binary-choice variant of TruthfulQA.","url":"https://github.com/sylinrl/TruthfulQA","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Jev 1.13","top_percent":92,"top_model_id":"jev-1.13","top_generation":"Jev 1.13","top_model_base":"Jev 1.13","top_model_family":"Jev","top_company":"typesafe","top_open_source":0,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":92},{"place":2,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":85.4}]},{"id":"truthfulqa-de","name":"TruthfulQA (DE)","topic":"Truthfulness / hallucination (German)","description":"German translation of the TruthfulQA benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"norm_prob_mass","stars":"","top_model":"Llama 3.3 70B Instruct","top_percent":0.174,"top_model_id":"llama-3.3-70b-instruct","top_generation":"Llama 3.3","top_model_base":"Llama 3.3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.174},{"place":2,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.17}]},{"id":"turkishmmlu","name":"TurkishMMLU","topic":"Turkish knowledge","description":"Native Turkish multiple-choice QA benchmark from Turkish curriculum exams.","url":"https://huggingface.co/datasets/AYueksel/TurkishMMLU","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2407.12402","metric":"percent","stars":"","top_model":"Qwen2.5-72B-Instruct","top_percent":76.12,"top_model_id":"qwen2.5-72b-instruct","top_generation":"Qwen2.5","top_model_base":"Qwen2.5 72B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.12},{"place":2,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":72.41},{"place":3,"model":"gpt-4o-mini","company":"openai","family":"GPT","version":"GPT-4o","score":71.19},{"place":4,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":69.22},{"place":5,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":66.89},{"place":6,"model":"qwen2.5-14b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.85},{"place":7,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":64.78},{"place":8,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":55.44},{"place":9,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":54.28},{"place":10,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":49.27},{"place":11,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":45.61},{"place":12,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":34.44}]},{"id":"tvbench","name":"TVBench","topic":"TV comprehension","description":"Benchmark for TV show video comprehension and QA.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":83.2,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":25,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.2},{"place":2,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":82.5},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.9},{"place":4,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":80.5},{"place":5,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.4},{"place":6,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":78.2},{"place":7,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":77.2},{"place":8,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":76.4},{"place":9,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":76},{"place":10,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":75},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":73},{"place":12,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":71.5},{"place":13,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.5},{"place":14,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":71.1},{"place":15,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":71},{"place":16,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":70.5},{"place":17,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":69.8},{"place":18,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":69.6},{"place":19,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.4},{"place":20,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":66.6},{"place":21,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":64.91},{"place":22,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":61.5},{"place":23,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":58.1},{"place":24,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.94},{"place":25,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":56.83},{"place":26,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":52}]},{"id":"tydiqa","name":"TydiQA","topic":"Cross-lingual QA","description":"Typologically diverse QA across languages.","url":"https://github.com/google-research-datasets/tydiqa","leaderboard":"","github":"","paper":"","metric":"percent","stars":"313","top_model":"InternLM-20B","top_percent":43.2,"top_model_id":"internlm-20b","top_generation":"InternLM","top_model_base":"InternLM 20B","top_model_family":"InternLM","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":43.2},{"place":2,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":39.8},{"place":3,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":34.3},{"place":4,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":33.2},{"place":5,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":32.7},{"place":6,"model":"llama-4-maverick-17b-128e-base","company":"meta","family":"Llama","version":"Llama 4","score":31.7},{"place":7,"model":"llama-4-maverick-base","company":"meta","family":"Llama","version":"Llama 4","score":31.7},{"place":8,"model":"llama-4-scout-17b-16e-base","company":"meta","family":"Llama","version":"Llama 4","score":31.5},{"place":9,"model":"llama-4-scout-17b-base","company":"meta","family":"Llama","version":"Llama 4","score":31.5},{"place":10,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":30.8},{"place":11,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":29.9},{"place":12,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":27.9}]},{"id":"typed-decision","name":"Typed Decision","topic":"Typed decisions","description":"Typed-decision evaluation set used in Intern-Decision model card (Laya Typed Decisions).","url":"https://huggingface.co/internlm/Intern-Decision-4B","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Intern-Decision-4B","top_percent":80.55,"top_model_id":"intern-decision-4b","top_generation":"Intern-Decision","top_model_base":"Intern-Decision","top_model_family":"Intern","top_company":"internlm","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":80.55},{"place":2,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":79.35},{"place":3,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":77.35},{"place":4,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":73.35},{"place":5,"model":"jevk5","company":"alibiserikbay","family":"JevK5","version":"JevK5","score":64.5},{"place":6,"model":"semif","company":"theoleecj","family":"SemIf","version":"SemIf","score":62.8},{"place":7,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":35.95}]},{"id":"u-artifacts","name":"U-Artifacts","topic":"Agentic coding artifacts","description":"Benchmark focusing on generated code artifacts quality.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":57.8,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":57.8},{"place":2,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":56.8},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":49.2},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":37.3},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.4}]},{"id":"ugc-videocap","name":"UGC-VideoCap","topic":"Video captioning","description":"Short-form user-generated video captioning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Glimpse","top_percent":82.66,"top_model_id":"glimpse","top_generation":"Glimpse","top_model_base":"Glimpse","top_model_family":"Glimpse","top_company":"elorian","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":82.66},{"place":2,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":80.41},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":80.32},{"place":4,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":78.33},{"place":5,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":76.35}]},{"id":"ui-vision","name":"UI-Vision","topic":"GUI grounding","description":"Desktop GUI grounding benchmark (basic, functional, spatial) for computer-use agents.","url":"","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2503.15661","metric":"percent","stars":"","top_model":"POINTS-GUI-G-8B","top_percent":49.9,"top_model_id":"points-gui-g-8b","top_generation":"POINTS-GUI-G","top_model_base":"POINTS","top_model_family":"POINTS-GUI","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"points-gui-g-8b","company":"tencent","family":"POINTS-GUI","version":"POINTS-GUI-G","score":49.9},{"place":2,"model":"mai-ui-8b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":40.7},{"place":3,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":36.8},{"place":4,"model":"mai-ui-2b","company":"tongyi","family":"MAI-UI","version":"MAI-UI","score":30.3},{"place":5,"model":"phi-ground","company":"microsoft","family":"Phi","version":"Phi","score":27.2},{"place":6,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":26.9},{"place":7,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":26.5},{"place":8,"model":"infigui-g1-7b","company":"infix-ai","family":"InfiGUI","version":"InfiGUI","score":26.1},{"place":9,"model":"ui-tars-72b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":25.5},{"place":10,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":22.3},{"place":11,"model":"infigui-g1-3b","company":"infix-ai","family":"InfiGUI","version":"InfiGUI-G1","score":22},{"place":12,"model":"ui-tars-7b","company":"bytedance","family":"UI","version":"UI","score":17.6},{"place":13,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":17.5},{"place":14,"model":"uground-v1-7b","company":"osunlp","family":"UGround","version":"UGround-V1","score":12.9},{"place":15,"model":"os-atlas-7b","company":"os-copilot","family":"OS-Atlas","version":"OS-Atlas","score":9},{"place":16,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":8.3},{"place":17,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":6.2},{"place":18,"model":"seeclick","company":"nju","family":"SeeClick","version":"SeeClick","score":5.4},{"place":19,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":1.4},{"place":20,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":0.9}]},{"id":"unimernet","name":"UniMERNet","topic":"Formula recognition","description":"UniMER-Test benchmark for universal mathematical expression recognition from images.","url":"https://github.com/opendatalab/UniMERNet","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Infinity-Parser2-Pro","top_percent":97.7,"top_model_id":"infinity-parser2-pro","top_generation":"Infinity-Parser2","top_model_base":"Infinity-Parser2 Pro","top_model_family":"Infinity-Parser","top_company":"infly","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"infinity-parser2-pro","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":97.7},{"place":2,"model":"infinity-parser2-flash","company":"infly","family":"Infinity-Parser","version":"Infinity-Parser2","score":96.5},{"place":3,"model":"mineru2.5","company":"opendatalab","family":"MinerU","version":"MinerU2.5","score":96.5},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":96.4},{"place":5,"model":"paddleocr-vl-1.5","company":"paddlepaddle","family":"PaddleOCR","version":"PaddleOCR-VL 1.5","score":95.8},{"place":6,"model":"deepseek-ocr-2","company":"deepseek","family":"DeepSeek OCR","version":"DeepSeek OCR 2","score":79.8}]},{"id":"uro-bench-pro-oral","name":"URO-Bench Pro: Oral Conversation","topic":"Spoken dialogue","description":"URO-Bench pro track, oral-conversation dimension, speech-to-speech (%).","url":"https://github.com/Ruiqi-Yan/URO-Bench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2502.17810","metric":"percent","stars":"","top_model":"Qwen3.5-Omni-Plus","top_percent":99.8,"top_model_id":"qwen3.5-omni-plus","top_generation":"Qwen3.5 Omni","top_model_base":"Qwen3.5 Omni Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":99.8},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":99.2},{"place":3,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":98.7}]},{"id":"uro-bench-pro-reasoning","name":"URO-Bench Pro: Reasoning","topic":"Spoken dialogue","description":"URO-Bench pro track, reasoning dimension, speech-to-speech (%).","url":"https://github.com/Ruiqi-Yan/URO-Bench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2502.17810","metric":"percent","stars":"","top_model":"Qwen3.5-Omni-Plus","top_percent":86.3,"top_model_id":"qwen3.5-omni-plus","top_generation":"Qwen3.5 Omni","top_model_base":"Qwen3.5 Omni Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":86.3},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":84},{"place":3,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":83.8}]},{"id":"uro-bench-pro-understanding","name":"URO-Bench Pro: Understanding","topic":"Spoken dialogue","description":"URO-Bench pro track, understanding dimension, speech-to-speech (%).","url":"https://github.com/Ruiqi-Yan/URO-Bench","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2502.17810","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":69.1,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":69.1},{"place":2,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":66.3},{"place":3,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":64.1}]},{"id":"usaco","name":"USACO","topic":"Code generation (olympiad)","description":"USA Computing Olympiad problems benchmark (307 problems); pass@1.","url":"https://princeton-nlp.github.io/USACOBench/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2404.10952","metric":"percent","stars":"","top_model":"GPT-4o-2024-05-13","top_percent":18.8,"top_model_id":"gpt-4o-2024-05-13","top_generation":"GPT-4o","top_model_base":"GPT-4o","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":18.8},{"place":2,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":12.3},{"place":3,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":12.1},{"place":4,"model":"gpt-4-1106-preview","company":"openai","family":"GPT","version":"GPT-4","score":11.1},{"place":5,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":7.8},{"place":6,"model":"deepseek-coder-v2-lite-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":6.5},{"place":7,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":4.9},{"place":8,"model":"codestral-22b","company":"mistral","family":"Codestral","version":"Codestral","score":4.6},{"place":9,"model":"deepseek-coder-33b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":4.2},{"place":10,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":3.3}]},{"id":"usamo-2026","name":"USAMO 2026","topic":"Math olympiad (proofs)","description":"2026 USA Mathematical Olympiad (6 proof problems), graded with MathArena methodology.","url":"https://matharena.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Mythos 5","top_percent":99.8,"top_model_id":"claude-mythos-5","top_generation":"Claude 5","top_model_base":"Claude Mythos 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"claude-mythos-5","company":"anthropic","family":"Claude","version":"Claude 5","score":99.8},{"place":2,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98.4},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":98.2},{"place":4,"model":"claude-mythos-preview","company":"anthropic","family":"Claude","version":"Claude Mythos Preview","score":97.6},{"place":5,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":96.7},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":95.2},{"place":7,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":92.9},{"place":8,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":79.5},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":74.4},{"place":10,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":72},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":69.3},{"place":12,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66.2},{"place":13,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":61.3},{"place":14,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":60.3},{"place":15,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":59.2},{"place":16,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":57.9},{"place":17,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":57.1},{"place":18,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":52.8},{"place":19,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":41.3},{"place":20,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":37.3},{"place":21,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":37.3}]},{"id":"v-star","name":"V*","topic":"Multimodal reasoning","description":"V* benchmark accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.6-Plus","top_percent":96.9,"top_model_id":"qwen3.6-plus","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":74,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":96.9},{"place":2,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.8},{"place":3,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":94.8},{"place":4,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":94.7},{"place":5,"model":"sensenova-mars-32b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":94.2},{"place":6,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.7},{"place":7,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":93.2},{"place":8,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.2},{"place":9,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":93},{"place":10,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.7},{"place":11,"model":"zwz-4b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":92.67},{"place":12,"model":"sensenova-mars-8b","company":"sensetime","family":"SenseNova","version":"SenseNova-MARS","score":92.2},{"place":13,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.1},{"place":14,"model":"zwz-8b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":91.1},{"place":15,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":90.58},{"place":16,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":90.2},{"place":17,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":90.1},{"place":18,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":90.1},{"place":19,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":90.1},{"place":20,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":89},{"place":21,"model":"zwz-7b","company":"antgroup","family":"ZwZ","version":"ZwZ","score":88.48},{"place":22,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":88.1},{"place":23,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88},{"place":24,"model":"skywork-r1v4","company":"skywork","family":"Skywork","version":"Skywork R1V4","score":88},{"place":25,"model":"qwen3-vl-235b-a22b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":87.96},{"place":26,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":87.4},{"place":27,"model":"smaug-nemotron-3.5-nvfp4","company":"abacusai","family":"Smaug","version":"Smaug","score":86.5},{"place":28,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.4},{"place":29,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":86.39},{"place":30,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.39},{"place":31,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":86.39},{"place":32,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":86},{"place":33,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.9},{"place":34,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":85.86},{"place":35,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":85.6},{"place":36,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":85.34},{"place":37,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.3},{"place":38,"model":"smaug-nemotron-3.5","company":"abacusai","family":"Smaug","version":"Smaug","score":85.2},{"place":39,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":84.82},{"place":40,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.3},{"place":41,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.3},{"place":42,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":83.8},{"place":43,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.8},{"place":44,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":83.25},{"place":45,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":83.25},{"place":46,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.2},{"place":47,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.2},{"place":48,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":81.7},{"place":49,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.2},{"place":50,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":81.2},{"place":51,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":81.15},{"place":52,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":80.6},{"place":53,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.6},{"place":54,"model":"qwen2.5-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":80.6},{"place":55,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.1},{"place":56,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":80.1},{"place":57,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.1},{"place":58,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":79},{"place":59,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":78.53},{"place":60,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77},{"place":61,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":75.9},{"place":62,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":75.4},{"place":63,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":75.4},{"place":64,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":75.3},{"place":65,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.9},{"place":66,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":74.3},{"place":67,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":73.9},{"place":68,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":73.8},{"place":69,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":72.8},{"place":70,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.3},{"place":71,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":71.7},{"place":72,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":70.7},{"place":73,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":70.5},{"place":74,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":70.16},{"place":75,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":70.16},{"place":76,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.6},{"place":77,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":69.1},{"place":78,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":69.1},{"place":79,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":68.1},{"place":80,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":67.5},{"place":81,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":67.5},{"place":82,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":67},{"place":83,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":66.5},{"place":84,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":63.4},{"place":85,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":61.8},{"place":86,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.6},{"place":87,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":57.6},{"place":88,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":52.7},{"place":89,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":51.8},{"place":90,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":51.3},{"place":91,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":50.8},{"place":92,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":46},{"place":93,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":41.8},{"place":94,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":37.7}]},{"id":"v-star-with-tools","name":"V* (With Tools)","topic":"Multimodal reasoning","description":"V* visual search benchmark evaluated with a Python code-interpreter tool.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.4","top_percent":98.4,"top_model_id":"gpt-5.4","top_generation":"GPT-5.4","top_model_base":"GPT-5.4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":98.4},{"place":2,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":96.9},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":96.9},{"place":4,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":96.3},{"place":5,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":95.29},{"place":6,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":89},{"place":7,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":86.9},{"place":8,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86.4}]},{"id":"vabench-point","name":"VABench-Point","topic":"Embodied reasoning","description":"VABench visual-action pointing subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Embodied-R1.5-8B","top_percent":75.7,"top_model_id":"embodied-r1.5-8b","top_generation":"Embodied-R1.5","top_model_base":"Embodied-R1.5 8B","top_model_family":"Embodied-R1","top_company":"unknown","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":75.7},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":65.3},{"place":3,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":65.2},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":64.7},{"place":5,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":60.7},{"place":6,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":60.5},{"place":7,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":60.3},{"place":8,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":53.2},{"place":9,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":47.7},{"place":10,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.3},{"place":11,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":15.8},{"place":12,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":10.6},{"place":13,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":5.3}]},{"id":"vabench-visual-trace","name":"VABench-VisualTrace","topic":"Embodied reasoning","description":"VABench visual-trace (trajectory) subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Embodied-R1.5-8B","top_percent":92.3,"top_model_id":"embodied-r1.5-8b","top_generation":"Embodied-R1.5","top_model_base":"Embodied-R1.5 8B","top_model_family":"Embodied-R1","top_company":"unknown","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":92.3},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":91.6},{"place":3,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":89.8},{"place":4,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":88.9},{"place":5,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":88.9},{"place":6,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":88.3},{"place":7,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":87.5},{"place":8,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":86.6},{"place":9,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":85.4},{"place":10,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":84.4},{"place":11,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":84.2},{"place":12,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":82.7},{"place":13,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":82.1}]},{"id":"vals-index","name":"Vals Index","topic":"Knowledge work","description":"Vals AI composite index of real-world professional/enterprise tasks (finance, legal, coding, etc.).","url":"https://www.vals.ai/","leaderboard":"https://www.vals.ai/","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":68.9,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":50,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":68.9},{"place":2,"model":"claude-sonnet-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":67.04},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":67},{"place":4,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":66.97},{"place":5,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":65.83},{"place":6,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":65.8},{"place":7,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":64.57},{"place":8,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":63.67},{"place":9,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":63.12},{"place":10,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":63.1},{"place":11,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":61.39},{"place":12,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":61.15},{"place":13,"model":"muse-wonder","company":"meta","family":"Muse","version":"Muse Wonder","score":61.06},{"place":14,"model":"muse-spark-1.3","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":58.16},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":58.01},{"place":16,"model":"gpt-6-sol","company":"openai","family":"GPT","version":"GPT-6","score":57.54},{"place":17,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":55.2},{"place":18,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":55.1},{"place":19,"model":"grok-4.7","company":"xai","family":"Grok","version":"Grok 4.7","score":54.95},{"place":20,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":54.89},{"place":21,"model":"claude-haiku-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":54.44},{"place":22,"model":"minimax-m3.1-flash-max","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":53.78},{"place":23,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":53.51},{"place":24,"model":"mimo-v2.6-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":53.23},{"place":25,"model":"muse-spark-1.3-xhigh","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":53.2},{"place":26,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":53.09},{"place":27,"model":"grok-4.6","company":"xai","family":"Grok","version":"Grok 4.6","score":52.09},{"place":28,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":51.9},{"place":29,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":51.69},{"place":30,"model":"deepseek-v4.1-flash-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":51.32},{"place":31,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":51.27},{"place":32,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":51.22},{"place":33,"model":"ember-1","company":"fireworks","family":"Ember","version":"Ember-1","score":50.94},{"place":34,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":50.3},{"place":35,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":49.94},{"place":36,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":49.35},{"place":37,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":49.29},{"place":38,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":48.66},{"place":39,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":48.27},{"place":40,"model":"deepseek-v4-flash-0731-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":47.96},{"place":41,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":47.63},{"place":42,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":46.61},{"place":43,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":44.79},{"place":44,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":44.72},{"place":45,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":44.58},{"place":46,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":38.63},{"place":47,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":36.53},{"place":48,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":33.84},{"place":49,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":33.44},{"place":50,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":33.17},{"place":51,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":28.67},{"place":52,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":25.46},{"place":53,"model":"mercury-2.5","company":"inception","family":"Mercury","version":"Mercury 2.5","score":8.86}]},{"id":"vast-stance","name":"VAST","topic":"Stance detection","description":"VAST zero-shot stance detection; macro-F1 (Jev Decision Index suite, posed as typed decisions).","url":"https://github.com/emilyallaway/zero-shot-stance","leaderboard":"https://huggingface.co/spaces/multimodalart/jev-decision-index","github":"","paper":"","metric":"f1","stars":"","top_model":"pplx-decider-v1.2","top_percent":80.2,"top_model_id":"pplx-decider-v1.2","top_generation":"v1.2","top_model_base":"pplx-decider","top_model_family":"pplx-decider","top_company":"perplexity","top_open_source":1,"lower_is_better":false,"bench_models":38,"total_models":3854,"placements":[{"place":1,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":80.2},{"place":2,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":77},{"place":3,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":76.9},{"place":4,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":74.8},{"place":5,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":73.7},{"place":6,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":73.1},{"place":7,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":70.5},{"place":8,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":69.9},{"place":9,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":69.6},{"place":10,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":68.8},{"place":11,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":64.6},{"place":12,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":60.9},{"place":13,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":59.9},{"place":14,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":59.5},{"place":15,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":57},{"place":16,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":55.7},{"place":17,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":55.4},{"place":18,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":55.4},{"place":19,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":54.8},{"place":20,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":52.2},{"place":21,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":50.9},{"place":22,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":49.6},{"place":23,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":47.7},{"place":24,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":45.3},{"place":25,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":45},{"place":26,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":44.7},{"place":27,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":44.6},{"place":28,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":42.6},{"place":29,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":42.3},{"place":30,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":40.7},{"place":31,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":40.5},{"place":32,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":40.4},{"place":33,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":39.3},{"place":34,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":39.1},{"place":35,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":38.8},{"place":36,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":35.3},{"place":37,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":34.2},{"place":38,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":28}]},{"id":"vcr-en-easy","name":"VCR (EN, easy)","topic":"Visual caption restoration","description":"Visual Caption Restoration, English easy split; exact-match accuracy of restoring partially occluded text.","url":"https://github.com/tianyu-z/VCR","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2406.06462","metric":"percent","stars":"","top_model":"InternVL2.5-78B","top_percent":95.7,"top_model_id":"internvl2.5-78b","top_generation":"InternVL2.5","top_model_base":"InternVL2.5-78B","top_model_family":"Intern","top_company":"opengvlab","top_open_source":1,"lower_is_better":false,"bench_models":27,"total_models":3854,"placements":[{"place":1,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":95.7},{"place":2,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":94.7},{"place":3,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":94.4},{"place":4,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":93.7},{"place":5,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":93.2},{"place":6,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":92.6},{"place":7,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":91.6},{"place":8,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":91.5},{"place":9,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":91.3},{"place":10,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":89.7},{"place":11,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":84.7},{"place":12,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":83.2},{"place":13,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":81.5},{"place":14,"model":"cambrian-34b","company":"nyu","family":"Cambrian","version":"Cambrian","score":79.7},{"place":15,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":74.5},{"place":16,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":73.9},{"place":17,"model":"aquila-vl-2b","company":"baai","family":"Aquila","version":"Aquila-VL","score":70},{"place":18,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":63.9},{"place":19,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":62.7},{"place":20,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":62},{"place":21,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":52},{"place":22,"model":"phi-3.5-vision-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":39.3},{"place":23,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":37.9},{"place":24,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":33.7},{"place":25,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":32.9},{"place":26,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":21.5},{"place":27,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":14.7}]},{"id":"vcrbench","name":"VCRBench","topic":"Visual commonsense reasoning","description":"Visual commonsense reasoning benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed1.8","top_percent":59.8,"top_model_id":"seed1.8","top_generation":"Seed 1.8","top_model_base":"Seed 1.8","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":59.8},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":53.4},{"place":3,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":51.8},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.4},{"place":5,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":43.04},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.7},{"place":7,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":38.2},{"place":8,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":35.98},{"place":9,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":35.4}]},{"id":"vct","name":"VCT","topic":"Virology capability (protocol troubleshooting)","description":"Virology Capabilities Test: a benchmark that measures an LLM's ability to troubleshoot complex virology laboratory protocols.","url":"","leaderboard":"https://www.virologytest.ai/","github":"","paper":"https://arxiv.org/abs/2504.16137","metric":"percent","stars":"","top_model":"Grok 4.1 (Thinking)","top_percent":61,"top_model_id":"grok-4.1-thinking","top_generation":"Grok 4.1","top_model_base":"Grok 4.1","top_model_family":"Grok","top_company":"xai","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":61},{"place":2,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":55},{"place":3,"model":"o3","company":"openai","family":"o3","version":"o3","score":43.8},{"place":4,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":42.9},{"place":5,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":41.1},{"place":6,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":39.7},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":37.6},{"place":8,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":37},{"place":9,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":36},{"place":10,"model":"o1","company":"openai","family":"o1","version":"o1","score":35.4},{"place":11,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":30.8},{"place":12,"model":"gpt-4.5","company":"openai","family":"GPT","version":"GPT-4.5","score":28.3},{"place":13,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":18.8}]},{"id":"vending-bench-2","name":"Vending-Bench 2","topic":"Long-horizon agentic tasks","description":"Long-horizon agentic task benchmark evaluating sustained goal completion.","url":"","leaderboard":"","github":"","paper":"","metric":"net_worth_mean","stars":"","top_model":"Claude Opus 4.7","top_percent":10937,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":10937},{"place":2,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":8017.59},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":6144.18},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":5787.43},{"place":5,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":5680.26},{"place":6,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":5634.41},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":5478.16},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":5478},{"place":9,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":5114.87},{"place":10,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4967},{"place":11,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":4432.12},{"place":12,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":4432},{"place":13,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":3952},{"place":14,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3839},{"place":15,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3838.74},{"place":16,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":3635},{"place":17,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":3591},{"place":18,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":2377},{"place":19,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":1473.43},{"place":20,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1198.46},{"place":21,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":1107},{"place":22,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1034},{"place":23,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":911.21},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":574},{"place":25,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":573.64},{"place":26,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":549}]},{"id":"vibe-android","name":"Vibe Android","topic":"Vibe evaluation (Android)","description":"Vibe evaluation on Android tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":92.2,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":92.2},{"place":2,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":89.7},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.5},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78.7},{"place":5,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":69.2}]},{"id":"vibe-average","name":"Vibe Average","topic":"Vibe evaluation","description":"Aggregate Vibe evaluation score.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniMax M2.1","top_percent":88.6,"top_model_id":"minimax-m2.1","top_generation":"MiniMax M2.1","top_model_base":"MiniMax M2.1","top_model_family":"MiniMax","top_company":"minimax","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":88.6},{"place":2,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.2},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":82.4},{"place":4,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":67.5},{"place":5,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":55.6},{"place":6,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":55.2},{"place":7,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":54.2},{"place":8,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":42.4},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":36.9}]},{"id":"vibe-backend","name":"Vibe Backend","topic":"Vibe evaluation (backend)","description":"Vibe evaluation on backend tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":98,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":98},{"place":2,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90.8},{"place":3,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":86.7},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78.7},{"place":5,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":67.3}]},{"id":"vibe-code-bench","name":"Vibe Code Bench","topic":"App generation","description":"Vals AI Vibe Code Bench: building complete web applications from natural-language specs.","url":"https://www.vals.ai/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 4 Argon","top_percent":91.9,"top_model_id":"gemini-4-argon","top_generation":"Gemini 4","top_model_base":"Gemini 4 Argon","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":91.9},{"place":2,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":90.3},{"place":3,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":90.3},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":89.6}]},{"id":"vibe-code-bench-v1.1","name":"Vibe Code Bench v1.1","topic":"Application building","description":"Vals AI Vibe Code Bench v1.1: build working web applications from natural-language specs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniMax M3.1 Flash (max)","top_percent":73.94,"top_model_id":"minimax-m3.1-flash-max","top_generation":"MiniMax M3.1","top_model_base":"MiniMax M3.1 Flash","top_model_family":"MiniMax","top_company":"minimax","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"minimax-m3.1-flash-max","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":73.94},{"place":2,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":72.2},{"place":3,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":19.7}]},{"id":"vibe-ios","name":"Vibe iOS","topic":"Vibe evaluation (iOS)","description":"Vibe evaluation on iOS tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":90,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":90},{"place":2,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":88},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":81.2},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":75.8},{"place":5,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":39.5}]},{"id":"vibe-simulation","name":"Vibe Simulation","topic":"Vibe evaluation (simulation)","description":"Vibe evaluation on simulation tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":89.2,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.2},{"place":2,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":87.1},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.1},{"place":5,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":77}]},{"id":"vibe-web","name":"Vibe Web","topic":"Vibe evaluation (web)","description":"Vibe evaluation on web tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MiniMax M2.1","top_percent":91.5,"top_model_id":"minimax-m2.1","top_generation":"MiniMax M2.1","top_model_base":"MiniMax M2.1","top_model_family":"MiniMax","top_company":"minimax","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":91.5},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.5},{"place":3,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":89.1},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":87.3},{"place":5,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":80.4}]},{"id":"vibeval","name":"VibeEval","topic":"Aesthetic/visual quality","description":"VLM aesthetic evaluation with GPT scores.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":76.39,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.39},{"place":2,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":69.24},{"place":3,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":68.59},{"place":4,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":64.7},{"place":5,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":60.13},{"place":6,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":54.7},{"place":7,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":47.7},{"place":8,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":47.2},{"place":9,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":44},{"place":10,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":43.6},{"place":11,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":39}]},{"id":"video-mme","name":"Video-MME","topic":"Video understanding (multimodal)","description":"Multimodal evaluation of video understanding and reasoning.","url":"https://video-mme.github.io/home_page.html","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":88.4,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88.4},{"place":2,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":87.7},{"place":3,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":85.3},{"place":4,"model":"nova-2-omni","company":"amazon","family":"Nova","version":"Nova 2","score":77.9},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":76.7},{"place":6,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76.6},{"place":7,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":75},{"place":8,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.5},{"place":9,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.4},{"place":10,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":73.3},{"place":11,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":72},{"place":12,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":71.9},{"place":13,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":71.6},{"place":14,"model":"qwen2-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":71.2},{"place":15,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":71.1},{"place":16,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":70},{"place":17,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":64},{"place":18,"model":"qwen2-vl-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":63.3},{"place":19,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.9},{"place":20,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.7},{"place":21,"model":"qwen2-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":55.6},{"place":22,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":55.3},{"place":23,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":52.1},{"place":24,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":44.7},{"place":25,"model":"smolvlm2-0.5b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":42.2},{"place":26,"model":"smolvlm2-0.256b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":33.7}]},{"id":"videoevalpro","name":"VideoEval-Pro","topic":"Video understanding","description":"Long video understanding benchmark with open-ended short-answer questions.","url":"https://arxiv.org/abs/2505.14640","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":78.4,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":78.4},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":78},{"place":3,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.6},{"place":4,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":68.8},{"place":5,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":60.4},{"place":6,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":60.1},{"place":7,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":59.9},{"place":8,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":58.6},{"place":9,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":58},{"place":10,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":55.1},{"place":11,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":54.9},{"place":12,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":54.9},{"place":13,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":51.2},{"place":14,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":51.1},{"place":15,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.5},{"place":16,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":50.3},{"place":17,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":49.8},{"place":18,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":48.1},{"place":19,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":47.8},{"place":20,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":47.2},{"place":21,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":46.5},{"place":22,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":46.2},{"place":23,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":33.51},{"place":24,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":31.57},{"place":25,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":29.09},{"place":26,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":28.7},{"place":27,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":22.11}]},{"id":"videohallucer","name":"VideoHallucer","topic":"Video hallucination","description":"Benchmark for detecting intrinsic and extrinsic hallucinations in video-language models.","url":"https://videohallucer.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":66.78,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":66.78},{"place":2,"model":"reka-edge-2603","company":"reka","family":"Reka Edge","version":"Reka Edge","score":59.57},{"place":3,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56},{"place":4,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":51.65}]},{"id":"videoholmes","name":"VideoHolmes","topic":"Video QA","description":"Video question answering benchmark focused on detective-style clues.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":68.2,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":68.2},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":67.6},{"place":3,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":67.4},{"place":4,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":67.4},{"place":5,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":67.1},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":65.9},{"place":7,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":65.6},{"place":8,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":65.5},{"place":9,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":64.3},{"place":10,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":64.2},{"place":11,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":64},{"place":12,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":63.8},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":62.4},{"place":14,"model":"mimo-v2-omni","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":59.5},{"place":15,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":59.1},{"place":16,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":58.6},{"place":17,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":58.36},{"place":18,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":51.3},{"place":19,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":50.4},{"place":20,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":46.92},{"place":21,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.3},{"place":22,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":44.96},{"place":23,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":38.05}]},{"id":"videomathqa","name":"VideoMathQA","topic":"Video math reasoning","description":"Benchmark for mathematical reasoning grounded in video content.","url":"https://arxiv.org/abs/2506.05349","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"JoyAI-VL-Interaction","top_percent":56.24,"top_model_id":"joyai-vl-interaction","top_generation":"JoyAI-VL","top_model_base":"JoyAI-VL-Interaction","top_model_family":"JoyAI-VL","top_company":"jd","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":56.24},{"place":2,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":52.7},{"place":3,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":52.05},{"place":4,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":51.05},{"place":5,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":50.76}]},{"id":"videomme","name":"VideoMME","topic":"Multimodal video evaluation","description":"Video multimodal evaluation suite (VideoMME).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":89.5,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":41,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":89.5},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":89.2},{"place":3,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":89},{"place":4,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":89},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88.4},{"place":6,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":87.8},{"place":7,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":87.7},{"place":8,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.4},{"place":9,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":87.2},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.9},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":86.7},{"place":12,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":86},{"place":13,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":85.2},{"place":14,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":83},{"place":15,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":81.2},{"place":16,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79},{"place":17,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":75},{"place":18,"model":"nemotron-3-nano-omni-30b-a3b-reasoning","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.2},{"place":19,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":71.9},{"place":20,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.4},{"place":21,"model":"penguin-vl-8b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":66.2},{"place":22,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":66},{"place":23,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":64.3},{"place":24,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":63.3},{"place":25,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.9},{"place":26,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":59.9},{"place":27,"model":"internvl3.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":58.4},{"place":28,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":58.2},{"place":29,"model":"baichuan-omni","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni","score":58.2},{"place":30,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":57.6},{"place":31,"model":"penguin-vl-2b","company":"tencent","family":"Penguin-VL","version":"Penguin-VL","score":57.4},{"place":32,"model":"vita","company":"nju","family":"VITA","version":"VITA","score":56.1},{"place":33,"model":"smolvlm2-2.2b","company":"huggingface","family":"SmolVLM","version":"SmolVLM2","score":52.1},{"place":34,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":49.4},{"place":35,"model":"gemma-3n-e2b-it","company":"google","family":"Gemma","version":"Gemma 3n","score":47},{"place":36,"model":"videollama2-7b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":46.6},{"place":37,"model":"video-llava-7b","company":"pku","family":"Video-LLaVA","version":"Video-LLaVA","score":39.9},{"place":38,"model":"llava-next-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":33.8},{"place":39,"model":"videochat2-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":33.7},{"place":40,"model":"llava-next-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT","score":33.7},{"place":41,"model":"anygpt","company":"fudan","family":"AnyGPT","version":"AnyGPT","score":29.8}]},{"id":"videomme-nosub","name":"VideoMME (w/o sub)","topic":"Video understanding","description":"Video understanding benchmark without subtitles.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":88.6,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":122,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88.6},{"place":2,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.8},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.7},{"place":4,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":85.8},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.1},{"place":6,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":84.7},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":84.7},{"place":8,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.2},{"place":9,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.2},{"place":10,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.9},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.7},{"place":12,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":83.3},{"place":13,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":83.2},{"place":14,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.8},{"place":15,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.5},{"place":16,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":82.5},{"place":17,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":81.9},{"place":18,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":81.4},{"place":19,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79},{"place":20,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79},{"place":21,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":78.9},{"place":22,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.4},{"place":23,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":78.3},{"place":24,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":77.9},{"place":25,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":77.3},{"place":26,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":77.3},{"place":27,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":77},{"place":28,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.9},{"place":29,"model":"minicpm-v-4.7-35b-a3b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.7","score":76.4},{"place":30,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":75.7},{"place":31,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":75.6},{"place":32,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":75.6},{"place":33,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":75.3},{"place":34,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":75},{"place":35,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":74.6},{"place":36,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.5},{"place":37,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":74.48},{"place":38,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":74.22},{"place":39,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":74.2},{"place":40,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":74.1},{"place":41,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":73.7},{"place":42,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":73.4},{"place":43,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":73.3},{"place":44,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.3},{"place":45,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":73.3},{"place":46,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":73},{"place":47,"model":"internvl3.5-241b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":72.9},{"place":48,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":72.7},{"place":49,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":72.44},{"place":50,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":72.4},{"place":51,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":72.1},{"place":52,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":71.96},{"place":53,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":71.9},{"place":54,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":71.9},{"place":55,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":71.9},{"place":56,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":71.9},{"place":57,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.4},{"place":58,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":71.2},{"place":59,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":71.1},{"place":60,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":70.96},{"place":61,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":70.7},{"place":62,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":70.7},{"place":63,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":70.5},{"place":64,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":70.4},{"place":65,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":70.2},{"place":66,"model":"mimo-vl-7b-rl-2508","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":70.1},{"place":67,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":69.9},{"place":68,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":69.6},{"place":69,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":69.6},{"place":70,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.3},{"place":71,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.3},{"place":72,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":69},{"place":73,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.9},{"place":74,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":68.6},{"place":75,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":68.5},{"place":76,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":68.2},{"place":77,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":68.2},{"place":78,"model":"openpangu-vl-7b","company":"huawei","family":"openPangu-VL","version":"openPangu-VL","score":68},{"place":79,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":67.9},{"place":80,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":67.8},{"place":81,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":67.4},{"place":82,"model":"oryx-1.5-32b","company":"tsinghua","family":"Oryx","version":"Oryx-1.5","score":67.3},{"place":83,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":66.9},{"place":84,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":66.9},{"place":85,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":66.3},{"place":86,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":66.2},{"place":87,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":66.2},{"place":88,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":66.1},{"place":89,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":66},{"place":90,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":65.6},{"place":91,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":65.4},{"place":92,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":65.3},{"place":93,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":65.1},{"place":94,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":65},{"place":95,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":64.9},{"place":96,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":64.7},{"place":97,"model":"videotemp-o3-7b","company":"kuaishou","family":"Keye-VL","version":"VideoTemp-o3","score":64.5},{"place":98,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":64.2},{"place":99,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":63.3},{"place":100,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":63.3},{"place":101,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":63.3},{"place":102,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":62.3},{"place":103,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":62.1},{"place":104,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":61.4},{"place":105,"model":"videollama2-72b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":61.4},{"place":106,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":60.9},{"place":107,"model":"llava-next-video-32b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT-Video","score":60.2},{"place":108,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":60.1},{"place":109,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":60},{"place":110,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":59.9},{"place":111,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":59.9},{"place":112,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":59.9},{"place":113,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":59.7},{"place":114,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":59.7},{"place":115,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":58.9},{"place":116,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":58.3},{"place":117,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":58.2},{"place":118,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.7},{"place":119,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":57},{"place":120,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":56.3},{"place":121,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":56.2},{"place":122,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":55.8},{"place":123,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":55.6},{"place":124,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":55.6},{"place":125,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":54.9},{"place":126,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":54},{"place":127,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":53.9},{"place":128,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":52.6},{"place":129,"model":"longva-7b","company":"lmms-lab","family":"LongVA","version":"LongVA","score":52.4},{"place":130,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":52.3},{"place":131,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":51.9},{"place":132,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":50.3},{"place":133,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.9},{"place":134,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":46.2},{"place":135,"model":"videochat2-hd-mistral","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":45.3},{"place":136,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":42.9},{"place":137,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":40.9}]},{"id":"videomme-sub","name":"VideoMME (w/sub)","topic":"Video understanding","description":"Video understanding benchmark with subtitles.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":90.4,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":94,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.4},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":90},{"place":3,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":89.5},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":89.5},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":89.4},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":89.3},{"place":7,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":88.4},{"place":8,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":88.4},{"place":9,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":88},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.9},{"place":11,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.8},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":87.8},{"place":13,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":87.7},{"place":14,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.5},{"place":15,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.5},{"place":16,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":87.4},{"place":17,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":87.36},{"place":18,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.3},{"place":19,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87},{"place":20,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":86.9},{"place":21,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":86.9},{"place":22,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":86.7},{"place":23,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.6},{"place":24,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":86.6},{"place":25,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":86.1},{"place":26,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":86},{"place":27,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":86},{"place":28,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":85.4},{"place":29,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":85.4},{"place":30,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.5},{"place":31,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.2},{"place":32,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.8},{"place":33,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":83.5},{"place":34,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.5},{"place":35,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.3},{"place":36,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":81.35},{"place":37,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":81.3},{"place":38,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":81.1},{"place":39,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80.97},{"place":40,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":80.7},{"place":41,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":80.5},{"place":42,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.9},{"place":43,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":77.8},{"place":44,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.7},{"place":45,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.6},{"place":46,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":77.2},{"place":47,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":76.9},{"place":48,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":76.2},{"place":49,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":76},{"place":50,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":75.96},{"place":51,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":75.8},{"place":52,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":75.7},{"place":53,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":75.7},{"place":54,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.6},{"place":55,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":75.6},{"place":56,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":75.59},{"place":57,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.2},{"place":58,"model":"oryx-1.5-32b","company":"tsinghua","family":"Oryx","version":"Oryx-1.5","score":74.9},{"place":59,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.6},{"place":60,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74},{"place":61,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":74},{"place":62,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":74},{"place":63,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":73.6},{"place":64,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":73.5},{"place":65,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":73.37},{"place":66,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":73.26},{"place":67,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":73.1},{"place":68,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":71.9},{"place":69,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":71.7},{"place":70,"model":"llava-video-7b","company":"llava","family":"LLaVA","version":"LLaVA-Video","score":69.7},{"place":71,"model":"videochat-flash-7b","company":"opengvlab","family":"VideoChat","version":"VideoChat-Flash","score":69.7},{"place":72,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":69.5},{"place":73,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":69.2},{"place":74,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":69.2},{"place":75,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":69},{"place":76,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":68.6},{"place":77,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":68.6},{"place":78,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":68.6},{"place":79,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":68.4},{"place":80,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":67.9},{"place":81,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":67.8},{"place":82,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":66.9},{"place":83,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":65.4},{"place":84,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63.8},{"place":85,"model":"minicpm-v-2_6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 2.6","score":63.6},{"place":86,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":63.6},{"place":87,"model":"gpt-4-1106-vision-preview","company":"openai","family":"GPT","version":"GPT-4","score":63.3},{"place":88,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":63.3},{"place":89,"model":"videollama2-72b","company":"alibaba","family":"VideoLLaMA","version":"VideoLLaMA 2","score":63.1},{"place":90,"model":"llava-next-video-32b","company":"llava","family":"LLaVA","version":"LLaVA-NeXT-Video","score":63},{"place":91,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":62.9},{"place":92,"model":"vila1.5-40b","company":"nvidia","family":"VILA","version":"VILA1.5","score":61.1},{"place":93,"model":"qwen2-vl-2b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":60.4},{"place":94,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":60.2},{"place":95,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":59.4},{"place":96,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":59.3},{"place":97,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":57},{"place":98,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":56.9},{"place":99,"model":"videochat2-hd-mistral","company":"opengvlab","family":"VideoChat","version":"VideoChat2","score":55.7},{"place":100,"model":"longva-7b","company":"lmms-lab","family":"LongVA","version":"LongVA","score":54.3},{"place":101,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":54.1},{"place":102,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":52.3},{"place":103,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":49.1},{"place":104,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":45.4}]},{"id":"videomme-v2","name":"Video-MME v2","topic":"Video understanding","description":"Second version of the Video-MME video multimodal evaluation suite.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":66.1,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":27,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":66.1},{"place":2,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":65.4},{"place":3,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.9},{"place":4,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":61.5},{"place":5,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":61.1},{"place":6,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":60.5},{"place":7,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":52.1},{"place":8,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":45.1},{"place":9,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":42.4},{"place":10,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":39.3},{"place":11,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":36.9},{"place":12,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.8},{"place":13,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":36.3},{"place":14,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":33.82},{"place":15,"model":"comet-60b-a12b-nvfp4","company":"multiverse","family":"Comet","version":"Comet 1.0","score":33.33},{"place":16,"model":"comet-60b-a12b-fp8","company":"multiverse","family":"Comet","version":"Comet 1.0","score":33.09},{"place":17,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":32.85},{"place":18,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":32.5},{"place":19,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":32.5},{"place":20,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":32.5},{"place":21,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":32.13},{"place":22,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":32},{"place":23,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":31.84},{"place":24,"model":"comet-60b-a12b","company":"multiverse","family":"Comet","version":"Comet 1.0","score":31.74},{"place":25,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":28.5},{"place":26,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":27.31},{"place":27,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":26.63},{"place":28,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":23.5},{"place":29,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":14.8}]},{"id":"videommmu","name":"VideoMMMU","topic":"Multimodal video understanding","description":"Video-based extension of MMMU evaluating temporal multimodal reasoning and perception across disciplines.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":88.7,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":93,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":88.7},{"place":2,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":88.3},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":88.1},{"place":4,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":88},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":87.9},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":87.6},{"place":7,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":87},{"place":8,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":86.9},{"place":9,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":86.9},{"place":10,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":86.8},{"place":11,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":86.6},{"place":12,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":86.6},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":86.4},{"place":14,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":86.4},{"place":15,"model":"gpt-5.2-extra-high","company":"openai","family":"GPT","version":"GPT-5.2","score":85.9},{"place":16,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":85.9},{"place":17,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":85.9},{"place":18,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":85.4},{"place":19,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":85.3},{"place":20,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":85.2},{"place":21,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":85.2},{"place":22,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":85},{"place":23,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":84.8},{"place":24,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.7},{"place":25,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":84.6},{"place":26,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":84.6},{"place":27,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":84.6},{"place":28,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.4},{"place":29,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.4},{"place":30,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.4},{"place":31,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":84.1},{"place":32,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84},{"place":33,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":83.7},{"place":34,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.6},{"place":35,"model":"o3","company":"openai","family":"o3","version":"o3","score":83.3},{"place":36,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":83},{"place":37,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":82.7},{"place":38,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":82.5},{"place":39,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":82.5},{"place":40,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":82.4},{"place":41,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82.3},{"place":42,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":82},{"place":43,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":81.6},{"place":44,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":81.4},{"place":45,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":81.4},{"place":46,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.2},{"place":47,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":81.11},{"place":48,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.6},{"place":49,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":80.4},{"place":50,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.4},{"place":51,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80},{"place":52,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":80},{"place":53,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":80},{"place":54,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":79.2},{"place":55,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79},{"place":56,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.9},{"place":57,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.8},{"place":58,"model":"claude-4.5-sonnet-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.8},{"place":59,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77.6},{"place":60,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":76.2},{"place":61,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":76},{"place":62,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":75.3},{"place":63,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75},{"place":64,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75},{"place":65,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":74.7},{"place":66,"model":"grok-4.1-fast","company":"xai","family":"Grok","version":"Grok 4.1","score":74.6},{"place":67,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74.1},{"place":68,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.9},{"place":69,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":70.1},{"place":70,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":69.4},{"place":71,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.2},{"place":72,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.7},{"place":73,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":67.3},{"place":74,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.3},{"place":75,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":65.2},{"place":76,"model":"joyai-vl-interaction","company":"jd","family":"JoyAI-VL","version":"JoyAI-VL","score":64.67},{"place":77,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":63},{"place":78,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":63},{"place":79,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":62.4},{"place":80,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.1},{"place":81,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":61.2},{"place":82,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":61},{"place":83,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":60.7},{"place":84,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":60.2},{"place":85,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":56.7},{"place":86,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.2},{"place":87,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":54.5},{"place":88,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":54.1},{"place":89,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":53.8},{"place":90,"model":"videotemp-o3-7b","company":"kuaishou","family":"Keye-VL","version":"VideoTemp-o3","score":53.2},{"place":91,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":53.1},{"place":92,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":53},{"place":93,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":48.9},{"place":94,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":48.78},{"place":95,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":47.4},{"place":96,"model":"moss-vl-realtime","company":"openmoss","family":"MOSS-VL","version":"MOSS-VL","score":46.67},{"place":97,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":44.3},{"place":98,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":43.3},{"place":99,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":43.2},{"place":100,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":41.9},{"place":101,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":40.2}]},{"id":"videoreasonbench","name":"VideoReasonBench","topic":"Video reasoning","description":"Video reasoning benchmark assessing temporal and causal understanding.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.0 Pro","top_percent":77.8,"top_model_id":"seed2.0-pro","top_generation":"Seed 2.0","top_model_base":"Seed 2.0 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.8},{"place":2,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":64.2},{"place":3,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":61.2},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":59.7},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":59.5},{"place":6,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":59.4},{"place":7,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":52.8},{"place":8,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":40.5},{"place":9,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":18.7}]},{"id":"videosimpleqa","name":"VideoSimpleQA","topic":"Video QA","description":"Simple question answering over short videos.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":76.4,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":76.4},{"place":2,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":76},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":72.4},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":71.9},{"place":5,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.9},{"place":6,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":71.7},{"place":7,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":71.4},{"place":8,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":70},{"place":9,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":70},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.6},{"place":11,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":67.8},{"place":12,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":67.7},{"place":13,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":66.6},{"place":14,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":59.2}]},{"id":"viewspatial-bench","name":"ViewSpatial-Bench","topic":"Spatial reasoning","description":"Multi-perspective spatial localization benchmark (camera vs. human viewpoints).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"ZDTaichu5.0-9B","top_percent":62.5,"top_model_id":"zdtaichu5.0-9b","top_generation":"ZDTaichu5.0","top_model_base":"ZDTaichu5.0 9B","top_model_family":"ZDTaichu","top_company":"taichu","top_open_source":1,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":62.5},{"place":2,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":62.5},{"place":3,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":58.1},{"place":4,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":56.6},{"place":5,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":56.4},{"place":6,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":55},{"place":7,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":54.2},{"place":8,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":52.4},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":50.36},{"place":10,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":49.8},{"place":11,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":48.3},{"place":12,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":48.2},{"place":13,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":47.3},{"place":14,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":46.14},{"place":15,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":43.9},{"place":16,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":43.23},{"place":17,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.68},{"place":18,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":40.3},{"place":19,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":39.7},{"place":20,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":39.3}]},{"id":"visdrone-det-f1","name":"VisDrone Detection (F1)","topic":"Object detection","description":"VisDrone object detection with an MLLM; F1 averaged over IoU 0.5:0.95.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":44.7,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":44.7},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":40.4},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":39.9},{"place":4,"model":"groundingdino-t","company":"idea-research","family":"GroundingDINO","version":"GroundingDINO","score":38.5},{"place":5,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":35.8},{"place":6,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.3},{"place":7,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":29.5}]},{"id":"visdrone-pointing","name":"VisDrone Pointing","topic":"Object pointing","description":"VisDrone object pointing accuracy.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":64.4,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":64.4},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":62.4},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":60.4},{"place":4,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":58.9},{"place":5,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":46.4}]},{"id":"visfactor","name":"VisFactor","topic":"Visual perception","description":"Benchmark of fundamental visual-cognition factors adapted from human psychometric perception tests.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":62.8,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":62.8},{"place":2,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":60.8},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":56.2},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":54.5},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":54},{"place":6,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":51.4},{"place":7,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":43.9},{"place":8,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":42.8},{"place":9,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":40.8},{"place":10,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":39.8},{"place":11,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":36},{"place":12,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":30.5},{"place":13,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":30.1},{"place":14,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":24.4}]},{"id":"vision2web","name":"Vision2Web","topic":"Coding (UI)","description":"Visual website generation benchmark: build working websites from visual designs/prototypes, judged on rendered result.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":79.8,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":79.8},{"place":2,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":77.8},{"place":3,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":76.5},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":76.1},{"place":5,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":75.1},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.5},{"place":7,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":69},{"place":8,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":68.2},{"place":9,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":67.6},{"place":10,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":67.5},{"place":11,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":64},{"place":12,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":62.9},{"place":13,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":62.9},{"place":14,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":62.4},{"place":15,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":62.1},{"place":16,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":59},{"place":17,"model":"ling-3.0-flash-vl","company":"antgroup","family":"Ling","version":"Ling 3.0","score":57.69},{"place":18,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":55.42},{"place":19,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":54.85},{"place":20,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":52.9},{"place":21,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":45},{"place":22,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":43.5},{"place":23,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":42.1},{"place":24,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":33.2},{"place":25,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":31}]},{"id":"vispeak","name":"ViSpeak","topic":"Video dialogue","description":"Video-grounded dialogue and description benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":89,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89},{"place":2,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":88},{"place":3,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":87},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.5},{"place":5,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":84},{"place":6,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":79},{"place":7,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":78.5},{"place":8,"model":"seed2.0-mini","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.5},{"place":9,"model":"seed-1.5-vl","company":"bytedance","family":"Seed","version":"Seed 1.5","score":77}]},{"id":"visualprobe","name":"VisualProbe","topic":"Visual search / fine-grained perception","description":"High-resolution visual search benchmark requiring iterative zoom/crop tool use (introduced with Mini-o3).","url":"https://arxiv.org/abs/2509.07969","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2509.07969","metric":"percent","stars":"","top_model":"Gemini 3 Flash","top_percent":69.9,"top_model_id":"gemini-3-flash","top_generation":"Gemini 3","top_model_base":"Gemini 3 Flash","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":69.9},{"place":2,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":65.05},{"place":3,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":64.47},{"place":4,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":53.01}]},{"id":"visualpuzzle","name":"VisualPuzzle","topic":"Visual reasoning","description":"Visual puzzle solving benchmark evaluating reasoning and pattern recognition capabilities.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":71.48,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":71.48},{"place":2,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":64.82},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":61.51},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":57.8},{"place":5,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":57.75},{"place":6,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":57.01},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":55.8},{"place":8,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":52.5}]},{"id":"visualwebbench-avg","name":"VisualWebBench","topic":"Web UI understanding","description":"Average accuracy on VisualWebBench.","url":"","leaderboard":"","github":"https://github.com/VisualWebBench/VisualWebBench","paper":"https://arxiv.org/abs/2404.05955","metric":"percent","stars":"","top_model":"Holo1.5-72B","top_percent":83.8,"top_model_id":"holo1.5-72b","top_generation":"Holo1.5","top_model_base":"Holo1.5-72B","top_model_family":"Holo","top_company":"hcompany","top_open_source":1,"lower_is_better":false,"bench_models":28,"total_models":3854,"placements":[{"place":1,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":83.8},{"place":2,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":82.6},{"place":3,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":80.2},{"place":4,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":80.2},{"place":5,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":80.2},{"place":6,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":79.7},{"place":7,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":79.3},{"place":8,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":78.5},{"place":9,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":76.3},{"place":10,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":74.1},{"place":11,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":69},{"place":12,"model":"claude-3-sonnet","company":"anthropic","family":"Claude","version":"Claude 3","score":65.8},{"place":13,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":64.8},{"place":14,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":64.6},{"place":15,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":62.7},{"place":16,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":60.9},{"place":17,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":58.9},{"place":18,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":58.5},{"place":19,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":58},{"place":20,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":54.1},{"place":21,"model":"llava-1.6-34b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":50.5},{"place":22,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":49.7},{"place":23,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":48},{"place":24,"model":"llava-1.6-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":39.4},{"place":25,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":38.1},{"place":26,"model":"llava-1.6-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.6","score":36},{"place":27,"model":"deepseek-vl-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek VL","score":28.1},{"place":28,"model":"vila-13b","company":"nvidia","family":"VILA","version":"VILA","score":27.3}]},{"id":"visulogic","name":"VisuLogic","topic":"Visual logical reasoning","description":"Logical reasoning and compositionality benchmark for visual-language models.","url":"https://visulogic-benchmark.github.io/VisuLogic/","leaderboard":"https://visulogic-benchmark.github.io/VisuLogic/","github":"https://github.com/VisuLogic-Benchmark/VisuLogic-Eval","paper":"https://arxiv.org/abs/2504.15279","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":54.3,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":47,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":54.3},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":52.9},{"place":3,"model":"perea-1.0","company":"unknown","family":"PEREA","version":"PEREA 1.0","score":52.8},{"place":4,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":52.5},{"place":5,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":47.4},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":44.8},{"place":7,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":43.5},{"place":8,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":37.6},{"place":9,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":35.9},{"place":10,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":35},{"place":11,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":34.4},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":32.8},{"place":13,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":32.6},{"place":14,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":32.2},{"place":15,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":32},{"place":16,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":31.93},{"place":17,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":31.6},{"place":18,"model":"internvl2.5-38b-rl","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":31.1},{"place":19,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":29.8},{"place":20,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":29.8},{"place":21,"model":"o3","company":"openai","family":"o3","version":"o3","score":29.5},{"place":22,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":29.4},{"place":23,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":28.5},{"place":24,"model":"skywork-r1v3-38b","company":"skywork","family":"Skywork","version":"Skywork R1V3","score":28.5},{"place":25,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":28.5},{"place":26,"model":"internvl3.5-30b-a3b-flash","company":"opengvlab","family":"InternVL","version":"InternVL3.5","score":28.4},{"place":27,"model":"doubao-1.5-vision-pro","company":"bytedance","family":"Doubao","version":"Doubao 1.5","score":28.1},{"place":28,"model":"gemini-2.0-pro","company":"google","family":"Gemini","version":"Gemini 2.0","score":28},{"place":29,"model":"qwen2.5-vl-7b-instruct-rl","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":28},{"place":30,"model":"gemini-2.0-pro-exp-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":28},{"place":31,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":27.9},{"place":32,"model":"internvl3-78b","company":"opengvlab","family":"Intern","version":"InternVL 3","score":27.7},{"place":33,"model":"ernie-4.5-vl-424b-a47b","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":27.3},{"place":34,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":27.3},{"place":35,"model":"internvl3-38b","company":"opengvlab","family":"Intern","version":"InternVL3","score":27.1},{"place":36,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":26.3},{"place":37,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":26.2},{"place":38,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":26.1},{"place":39,"model":"ernie-4.5-vl-28b-a3b","company":"baidu","family":"ERNIE","version":"ERNIE-4.5-VL","score":26},{"place":40,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":26},{"place":41,"model":"kimi-latest","company":"moonshotai","family":"Kimi","version":"Kimi","score":25.9},{"place":42,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":25.7},{"place":43,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":25.6},{"place":44,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":25.6},{"place":45,"model":"ovis2-8b","company":"alibaba","family":"Ovis","version":"Ovis2","score":25.6},{"place":46,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":25.5},{"place":47,"model":"llava-onevision-7b-si","company":"llava","family":"LLaVA","version":"LLaVA-OneVision","score":25.3},{"place":48,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":25.3},{"place":49,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":23},{"place":50,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":22.5},{"place":51,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":20},{"place":52,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":19}]},{"id":"vitabench","name":"VitaBench","topic":"Industry QA","description":"Industry-focused benchmark evaluating domain QA performance.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.5","top_percent":56.3,"top_model_id":"claude-opus-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Opus 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":66,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56.3},{"place":2,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":53.5},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":52.25},{"place":4,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":51.9},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.6},{"place":6,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":50.3},{"place":7,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":49.7},{"place":8,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":49.04},{"place":9,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":48.5},{"place":10,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":47.9},{"place":11,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.75},{"place":12,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":46},{"place":13,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":45.6},{"place":14,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":45.1},{"place":15,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":45},{"place":16,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":44.3},{"place":17,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":44.1},{"place":18,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":43.75},{"place":19,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":43.7},{"place":20,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":43},{"place":21,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":42.8},{"place":22,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":42.25},{"place":23,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":41.9},{"place":24,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.9},{"place":25,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41.8},{"place":26,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":41.75},{"place":27,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":40.9},{"place":28,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":40.3},{"place":29,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":40.25},{"place":30,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":39.25},{"place":31,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":39.1},{"place":32,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":38.8},{"place":33,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":38.75},{"place":34,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":38.2},{"place":35,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":38.2},{"place":36,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":37},{"place":37,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":37},{"place":38,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":37},{"place":39,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":36.9},{"place":40,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":36.5},{"place":41,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":36},{"place":42,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":35.63},{"place":43,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":35.6},{"place":44,"model":"o3","company":"openai","family":"o3","version":"o3","score":35.3},{"place":45,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34.25},{"place":46,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.6},{"place":47,"model":"keye-vl-2.0-30b-a3b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 2.0","score":33.1},{"place":48,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":32},{"place":49,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.9},{"place":50,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":31.6},{"place":51,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":31.5},{"place":52,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":31.5},{"place":53,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.25},{"place":54,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":30},{"place":55,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.8},{"place":56,"model":"longcat-flash-thinking","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":29.5},{"place":57,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":29.5},{"place":58,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":29.3},{"place":59,"model":"longcat-flash-thinking-2601","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":29.3},{"place":60,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":29.1},{"place":61,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":28.5},{"place":62,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":26.8},{"place":63,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":26.75},{"place":64,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":26.25},{"place":65,"model":"longcat-flash","company":"meituan","family":"LongCat","version":"LongCat-Flash","score":24.3},{"place":66,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":24.3},{"place":67,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":24.3},{"place":68,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":24},{"place":69,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":23},{"place":70,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":23},{"place":71,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":22},{"place":72,"model":"longcat-flash-lite-sparse","company":"meituan","family":"LongCat","version":"LongCat-Flash-Lite","score":21.67},{"place":73,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":21.5},{"place":74,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":21.5},{"place":75,"model":"glm-4.7-thinking","company":"zai","family":"GLM","version":"GLM 4.7","score":18.3},{"place":76,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":14.5},{"place":77,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":14.1},{"place":78,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":13.9},{"place":79,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":13.5},{"place":80,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":12.8},{"place":81,"model":"longcat-next","company":"meituan","family":"LongCat","version":"LongCat-Next","score":5.8},{"place":82,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":5.8},{"place":83,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":5}]},{"id":"vitabench-2.0","name":"VitaBench 2.0","topic":"Agentic real-world tasks","description":"VitaBench 2.0: interactive agent tasks in real-world service scenarios (v2.0, not comparable to v1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Spark-X2.6-4B","top_percent":30.8,"top_model_id":"spark-x2.6-4b","top_generation":"Spark X2.6","top_model_base":"Spark-X2.6-4B","top_model_family":"Spark","top_company":"iflytek","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"spark-x2.6-4b","company":"iflytek","family":"Spark","version":"Spark X2.6","score":30.8},{"place":2,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":25.2},{"place":3,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":18.2},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":15.6},{"place":5,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":12.4},{"place":6,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":4.8}]},{"id":"vizwiz","name":"VizWiz-VQA","topic":"Accessibility VQA","description":"Visual question answering on photos taken by blind people (VQA score).","url":"https://vizwiz.org/","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1802.08218","metric":"percent","stars":"","top_model":"Qwen-VL-Chat","top_percent":38.9,"top_model_id":"qwen-vl-chat","top_generation":"Qwen-VL","top_model_base":"Qwen-VL","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":38.9},{"place":2,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":35.2},{"place":3,"model":"instructblip-vicuna-13b","company":"salesforce","family":"BLIP","version":"InstructBLIP","score":33.4},{"place":4,"model":"flamingo-80b","company":"google","family":"Flamingo","version":"Flamingo","score":31.6},{"place":5,"model":"kosmos-1","company":"microsoft","family":"Kosmos","version":"Kosmos-1","score":29.2},{"place":6,"model":"flamingo-9b","company":"google","family":"Flamingo","version":"Flamingo","score":28.8},{"place":7,"model":"blip-2-vicuna-13b","company":"salesforce","family":"BLIP","version":"BLIP-2","score":19.6}]},{"id":"vl-rewardbench","name":"VL-RewardBench","topic":"Reward modeling (VL)","description":"Reward alignment benchmark for VLMs.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude 3.7 Sonnet","top_percent":67.4,"top_model_id":"claude-3.7-sonnet","top_generation":"Claude 3.7","top_model_base":"Claude 3.7 Sonnet","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":67.4},{"place":2,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":65},{"place":3,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":62.7},{"place":4,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":62.4},{"place":5,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":61.9},{"place":6,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":51.9},{"place":7,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":51.7},{"place":8,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":49.7},{"place":9,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":47.8},{"place":10,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":47.3},{"place":11,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":46.4},{"place":12,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":46},{"place":13,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":45.2},{"place":14,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":42.4},{"place":15,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":28.9}]},{"id":"vlabench","name":"VLABench","topic":"Embodied reasoning","description":"Language-conditioned robot manipulation reasoning benchmark (VLM track).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"PhysBrain1.5-8B","top_percent":76.4,"top_model_id":"physbrain1.5-8b","top_generation":"PhysBrain 1.5","top_model_base":"PhysBrain 1.5 8B","top_model_family":"PhysBrain","top_company":"deepcybo","top_open_source":1,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":76.4},{"place":2,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":73.4},{"place":3,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":66.3},{"place":4,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":64.7},{"place":5,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":60.3},{"place":6,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":50.9},{"place":7,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":48.7},{"place":8,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":44.8},{"place":9,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":42.4},{"place":10,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":40.9},{"place":11,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":39.9},{"place":12,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":37.6},{"place":13,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":29.1}]},{"id":"vlad","name":"VLAD","topic":"Driving scene QA","description":"Vision-language autonomous-driving QA benchmark (as reported in the Qwen-Drive-1.0 evaluation).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen-Drive-1.0-4B","top_percent":66.52,"top_model_id":"qwen-drive-1.0-4b","top_generation":"Qwen-Drive-1.0","top_model_base":"Qwen-Drive 1.0 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":66.52},{"place":2,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":65.38},{"place":3,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":58.71},{"place":4,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":57.73},{"place":5,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":56.37},{"place":6,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":54.47},{"place":7,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":50.33},{"place":8,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":33.6},{"place":9,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":9.13}]},{"id":"vlms-are-biased","name":"VLMs are Biased","topic":"Multimodal bias","description":"Evaluates whether VLMs truly 'see' vs. relying on memorized knowledge; measures bias toward non-visual priors.","url":"https://vlmsarebiased.github.io/","leaderboard":"https://vlmsarebiased.github.io/","github":"https://github.com/anvo25/vlms-are-biased","paper":"https://arxiv.org/abs/2505.23941","metric":"percent","stars":"90","top_model":"GPT-6 Astra","top_percent":84.1,"top_model_id":"gpt-6-astra","top_generation":"GPT-6","top_model_base":"GPT-6 Astra","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":84.1},{"place":2,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":38.39},{"place":3,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":36.39},{"place":4,"model":"moondream2","company":"moondream","family":"Moondream","version":"Moondream2","score":33.27},{"place":5,"model":"o4-mini","company":"openai","family":"o4","version":"o4","score":20.25},{"place":6,"model":"o3","company":"openai","family":"o3","version":"o3","score":18.5},{"place":7,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":16.62},{"place":8,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":16.59},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":16.02},{"place":10,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":13.88},{"place":11,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":13.87},{"place":12,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":13.6},{"place":13,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":12.15}]},{"id":"vlms-are-blind","name":"VLMs are Blind","topic":"Visual grounding robustness","description":"Evaluates failure modes of VLMs in grounding and perception tasks.","url":"https://vlmsareblind.github.io/","leaderboard":"","github":"https://github.com/anguyen8/vision-llms-are-blind","paper":"","metric":"percent","stars":"","top_model":"ERNIE 5.0","top_percent":91.38,"top_model_id":"ernie-5.0","top_generation":"ERNIE 5.0","top_model_base":"ERNIE 5.0","top_model_family":"ERNIE","top_company":"baidu","top_open_source":0,"lower_is_better":false,"bench_models":16,"total_models":3854,"placements":[{"place":1,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":91.38},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80.83},{"place":3,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":79.4},{"place":4,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":78},{"place":5,"model":"ernie-4.5-vl-28b-a3b-thinking","company":"baidu","family":"ERNIE","version":"ERNIE 4.5 VL","score":77.3},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.54},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":76.5},{"place":8,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":75.13},{"place":9,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":72.1},{"place":10,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":69.6},{"place":11,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":65},{"place":12,"model":"keye-vl-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL","score":61},{"place":13,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":49.8},{"place":14,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":45.89},{"place":15,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":37.4},{"place":16,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":36.8},{"place":17,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":18.6}]},{"id":"vlmsarebiased","name":"VLMsAreBiased","topic":"Multimodal bias","description":"Benchmark evaluating biases in vision-language models.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.8-Max","top_percent":88.3,"top_model_id":"qwen3.8-max","top_generation":"Qwen3.8","top_model_base":"Qwen3.8 Max","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":21,"total_models":3854,"placements":[{"place":1,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":88.3},{"place":2,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":83.6},{"place":3,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.6},{"place":4,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.4},{"place":5,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":74.8},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":74.1},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":73.5},{"place":8,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":68.3},{"place":9,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":66.1},{"place":10,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":62},{"place":11,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":61.2},{"place":12,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":59.8},{"place":13,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":50.6},{"place":14,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":49.8},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":43.8},{"place":16,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":42.8},{"place":17,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":36.6},{"place":18,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":30.2},{"place":19,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":30.2},{"place":20,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":26.5},{"place":21,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":24.3},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":21.7}]},{"id":"vlmsareblind","name":"VLMsAreBlind","topic":"Multimodal robustness","description":"Benchmark probing robustness of vision-language models to visual perturbations.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":97.5,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":97.5},{"place":2,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97},{"place":3,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":97},{"place":4,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":96.9},{"place":5,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":96.7},{"place":6,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":96.6},{"place":7,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.7},{"place":8,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":93},{"place":9,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":92.6},{"place":10,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":92.1},{"place":11,"model":"youtu-vl-4b-instruct","company":"tencent","family":"Youtu-VL","version":"Youtu-VL","score":88.9},{"place":12,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":87.2},{"place":13,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":85.5},{"place":14,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.3},{"place":15,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":84.2},{"place":16,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":80.9},{"place":17,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":79.5},{"place":18,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":75.8},{"place":19,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.8},{"place":20,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74},{"place":21,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":72.5},{"place":22,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.9},{"place":23,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":68.6},{"place":24,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":68.4},{"place":25,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":66.7},{"place":26,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.4},{"place":27,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":50}]},{"id":"voicebench-advbench","name":"VoiceBench AdvBench","topic":"VoiceBench","description":"VoiceBench adversarial safety evaluation.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"NemotronLabs VoiceChat 11B","top_percent":100,"top_model_id":"nemotronlabs-voicechat-11b","top_generation":"NemotronLabs VoiceChat","top_model_base":"NemotronLabs VoiceChat 11B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":100},{"place":2,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":100},{"place":3,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":100},{"place":4,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":99.4},{"place":5,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":99.3},{"place":6,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":99.23},{"place":7,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":99.2},{"place":8,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":99.04},{"place":9,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":98.9},{"place":10,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":98.9},{"place":11,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":98.7},{"place":12,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":98.65},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":98.1},{"place":14,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":97.69},{"place":15,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":97.31},{"place":16,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":97.2},{"place":17,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":97},{"place":18,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":96.9},{"place":19,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":88.46},{"place":20,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":57.5},{"place":21,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":44.23}]},{"id":"voicebench-alpacaeval","name":"VoiceBench AlpacaEval","topic":"VoiceBench","description":"VoiceBench evaluation on AlpacaEval instructions.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"LongCat-Flash-Omni","top_percent":98.8,"top_model_id":"longcat-flash-omni","top_generation":"LongCat-Flash-Omni","top_model_base":"LongCat-Flash-Omni","top_model_family":"LongCat","top_company":"meituan","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":98.8},{"place":2,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":96.8},{"place":3,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":96.4},{"place":4,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":96.1},{"place":5,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":95.6},{"place":6,"model":"ming-flash-omni-2.0","company":"antgroup","family":"Ming","version":"Ming 2.0","score":95.6},{"place":7,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":95.4},{"place":8,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":94.8},{"place":9,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":94.3},{"place":10,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":89.9},{"place":11,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":4.94},{"place":12,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":4.8},{"place":13,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":4.78},{"place":14,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":4.74},{"place":15,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":4.73},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.72},{"place":17,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.7},{"place":18,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":4.58},{"place":19,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":4.5},{"place":20,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":4.46},{"place":21,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":4.42},{"place":22,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":3.84},{"place":23,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":3.4},{"place":24,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":3.36}]},{"id":"voicebench-bbh","name":"VoiceBench BBH","topic":"VoiceBench","description":"VoiceBench evaluation on Big-Bench Hard prompts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":92.6,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.6},{"place":2,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":89.6},{"place":3,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.9},{"place":4,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":84.1},{"place":5,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":83},{"place":6,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":80.6},{"place":7,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":80.4},{"place":8,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":66.7},{"place":9,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":66.7},{"place":10,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":60.4},{"place":11,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":59.1},{"place":12,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":52.5},{"place":13,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":51.7}]},{"id":"voicebench-commoneval","name":"VoiceBench CommonEval","topic":"VoiceBench","description":"VoiceBench evaluation on CommonEval.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-Omni-Flash-Instruct","top_percent":91,"top_model_id":"qwen3-omni-flash-instruct","top_generation":"Qwen3","top_model_base":"Qwen3 Omni Flash","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":91},{"place":2,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.9},{"place":3,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":90.8},{"place":4,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.5},{"place":5,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":89.8},{"place":6,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.4},{"place":7,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.3},{"place":8,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":76.7},{"place":9,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":4.54},{"place":10,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":4.49},{"place":11,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.42},{"place":12,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":4.42},{"place":13,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":4.37},{"place":14,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":4.32},{"place":15,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":4.15},{"place":16,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":4.11},{"place":17,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":4.09},{"place":18,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":3.97},{"place":19,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":3.84},{"place":20,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":3.53},{"place":21,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":3.51},{"place":22,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":3.49},{"place":23,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":3.19},{"place":24,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":3},{"place":25,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":2.18},{"place":26,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":1.89},{"place":27,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":1.6}]},{"id":"voicebench-ifeval","name":"VoiceBench IFEval","topic":"VoiceBench","description":"VoiceBench instruction-following evaluation (IFEval).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":85.7,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":85.7},{"place":2,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.8},{"place":3,"model":"gpt-realtime-2.0-xhigh","company":"openai","family":"GPT","version":"GPT-realtime-2","score":83.2},{"place":4,"model":"gemini-3.1-flash-live-high","company":"google","family":"Gemini","version":"Gemini 3.1","score":82.8},{"place":5,"model":"tml-interaction-small","company":"thinkingmachines","family":"TML","version":"TML-Interaction","score":82.1},{"place":6,"model":"gpt-realtime-2.0","company":"openai","family":"GPT","version":"GPT-realtime-2","score":81.7},{"place":7,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.8},{"place":8,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.6},{"place":9,"model":"qwen3.5-omni-plus-realtime","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.3},{"place":10,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":78.52},{"place":11,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":77.99},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.83},{"place":13,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":77.8},{"place":14,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":76},{"place":15,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":75.2},{"place":16,"model":"gpt-realtime-1.5","company":"openai","family":"GPT","version":"GPT-realtime-1.5","score":68.1},{"place":17,"model":"gemini-3.1-flash-live","company":"google","family":"Gemini","version":"Gemini 3.1","score":67.6},{"place":18,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":66.81},{"place":19,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":61.1},{"place":20,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":53.5},{"place":21,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":53.5},{"place":22,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":51.5},{"place":23,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":49.25},{"place":24,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":29.8},{"place":25,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":25.34},{"place":26,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":19.3}]},{"id":"voicebench-ja-elyza","name":"VoiceBench-ja Elyza","topic":"Spoken QA (Japanese)","description":"ELYZA-tasks subset of VoiceBench-ja (spoken input), GPT-4o judge score 0-5.","url":"https://huggingface.co/datasets/sbintuitions/voicebench-ja","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Qwen2.5-Omni-3B","top_percent":2.365,"top_model_id":"qwen2.5-omni-3b","top_generation":"Qwen2.5 Omni","top_model_base":"Qwen2.5-Omni-3B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":2.365},{"place":2,"model":"lfm2.5-audio-1.5b-jp","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":2.272},{"place":3,"model":"j-moshi","company":"nu-dialogue","family":"Moshi","version":"Moshi","score":1.034},{"place":4,"model":"llm-jp-moshi-v1","company":"llm-jp","family":"Moshi","version":"Moshi","score":1}]},{"id":"voicebench-ja-m-ifeval","name":"VoiceBench-ja M-IFEval","topic":"Spoken instruction following (Japanese)","description":"M-IFEval subset of VoiceBench-ja (spoken input), scored 0-1.","url":"https://huggingface.co/datasets/sbintuitions/voicebench-ja","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"J-Moshi","top_percent":0.151,"top_model_id":"j-moshi","top_generation":"Moshi","top_model_base":"J-Moshi","top_model_family":"Moshi","top_company":"nu-dialogue","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"j-moshi","company":"nu-dialogue","family":"Moshi","version":"Moshi","score":0.151},{"place":2,"model":"lfm2.5-audio-1.5b-jp","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":0.143},{"place":3,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":0.137},{"place":4,"model":"llm-jp-moshi-v1","company":"llm-jp","family":"Moshi","version":"Moshi","score":0.11}]},{"id":"voicebench-ja-spoken-elyza","name":"VoiceBench-ja spoken_Elyza","topic":"Spoken QA (Japanese)","description":"spoken_Elyza subset of VoiceBench-ja, GPT-4o judge score 0-5.","url":"https://huggingface.co/datasets/sbintuitions/voicebench-ja","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"LFM2.5-Audio-1.5B-JP","top_percent":2.118,"top_model_id":"lfm2.5-audio-1.5b-jp","top_generation":"LFM2.5-Audio","top_model_base":"LFM2.5-Audio 1.5B JP","top_model_family":"LFM","top_company":"liquidai","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"lfm2.5-audio-1.5b-jp","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":2.118},{"place":2,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":2.094},{"place":3,"model":"llm-jp-moshi-v1","company":"llm-jp","family":"Moshi","version":"Moshi","score":1.023},{"place":4,"model":"j-moshi","company":"nu-dialogue","family":"Moshi","version":"Moshi","score":1.012}]},{"id":"voicebench-mau-v05-15-25","name":"MMAU v05.15.25","topic":"Audio reasoning","description":"Audio reasoning benchmark MMAU v05.15.25.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":82.5,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":82.5},{"place":2,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":82.2},{"place":3,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":81.9},{"place":4,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":81.8},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":81.1},{"place":6,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":80.5},{"place":7,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":80.4},{"place":8,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":79},{"place":9,"model":"realtime-venus-audio","company":"antgroup","family":"Realtime-Venus","version":"Realtime-Venus","score":78},{"place":10,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":77.6},{"place":11,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":77.6},{"place":12,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":77.5},{"place":13,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.5},{"place":14,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.4},{"place":15,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":77.2},{"place":16,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":77.2},{"place":17,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":77},{"place":18,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":76.9},{"place":19,"model":"realtime-venus-omni","company":"antgroup","family":"Realtime-Venus","version":"Realtime-Venus","score":76.9},{"place":20,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":76.9},{"place":21,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":76.6},{"place":22,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":76.5},{"place":23,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":75.4},{"place":24,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":75.2},{"place":25,"model":"mimo-audio-7b-instruct","company":"xiaomi","family":"MiMo","version":"MiMo-Audio","score":74.9},{"place":26,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":73.6},{"place":27,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.8},{"place":28,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":68.4},{"place":29,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":68.2},{"place":30,"model":"baichuan-omni-1.5","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni-1.5","score":65.6},{"place":31,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":65.5},{"place":32,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":65.2},{"place":33,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":63.5},{"place":34,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":62.5}]},{"id":"voicebench-mmsu","name":"VoiceBench MMSU","topic":"VoiceBench","description":"VoiceBench MMSU benchmark (voice modality).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":88.32,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":88.32},{"place":2,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":84.3},{"place":3,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":83},{"place":4,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":81.95},{"place":5,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":80.3},{"place":6,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":78.9},{"place":7,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":71.1},{"place":8,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":71.08},{"place":9,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69},{"place":10,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":68.4},{"place":11,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":68.1},{"place":12,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":66.1},{"place":13,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":62.17},{"place":14,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":61.7},{"place":15,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":55.29},{"place":16,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":52},{"place":17,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":46.1},{"place":18,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":33.04},{"place":19,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":31.95},{"place":20,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":24.27},{"place":21,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":24.04}]},{"id":"voicebench-mmsu-audio","name":"VoiceBench MMSU (Audio)","topic":"Audio reasoning","description":"Audio reasoning MMSU results.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"StepAudio 3 Realtime","top_percent":90.6,"top_model_id":"stepaudio-3-realtime","top_generation":"StepAudio 3","top_model_base":"StepAudio 3 Realtime","top_model_family":"Step","top_company":"stepfun","top_open_source":0,"lower_is_better":false,"bench_models":26,"total_models":3854,"placements":[{"place":1,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":90.6},{"place":2,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.6},{"place":3,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":83.3},{"place":4,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":83},{"place":5,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":82.8},{"place":6,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":82.1},{"place":7,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":81.3},{"place":8,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80.2},{"place":9,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":80},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":77.7},{"place":11,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":77},{"place":12,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":72.2},{"place":13,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.3},{"place":14,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":70.2},{"place":15,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":70.2},{"place":16,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69.1},{"place":17,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":69},{"place":18,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":67.8},{"place":19,"model":"realtime-venus-audio","company":"antgroup","family":"Realtime-Venus","version":"Realtime-Venus","score":66},{"place":20,"model":"minicpm-o-4.5","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 4.5","score":65.8},{"place":21,"model":"realtime-venus-omni","company":"antgroup","family":"Realtime-Venus","version":"Realtime-Venus","score":64.6},{"place":22,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":62.6},{"place":23,"model":"mimo-audio-7b-instruct","company":"xiaomi","family":"MiMo","version":"MiMo-Audio","score":61.7},{"place":24,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":59.9},{"place":25,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":59.3},{"place":26,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":56.8},{"place":27,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":56.5},{"place":28,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":56.4},{"place":29,"model":"baichuan-omni-1.5","company":"baichuan","family":"Baichuan","version":"Baichuan-Omni-1.5","score":50.6}]},{"id":"voicebench-openbookqa","name":"VoiceBench OpenBookQA","topic":"VoiceBench","description":"VoiceBench results on OpenBookQA prompts.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":95.16,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":13,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":95.16},{"place":2,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":95},{"place":3,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":94.3},{"place":4,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":93.41},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.3},{"place":6,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":91.4},{"place":7,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":89.7},{"place":8,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":89.2},{"place":9,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":89},{"place":10,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":87.9},{"place":11,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":83.52},{"place":12,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":83.52},{"place":13,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":72.97},{"place":14,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":61.3},{"place":15,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":56.9}]},{"id":"voicebench-sd-qa","name":"VoiceBench SD-QA","topic":"VoiceBench","description":"VoiceBench Spoken Dialogue QA results.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":90.1,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.1},{"place":2,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":90.1},{"place":3,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":84.5},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.54},{"place":5,"model":"longcat-flash-omni","company":"meituan","family":"LongCat","version":"LongCat-Flash-Omni","score":82.46},{"place":6,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":78.5},{"place":7,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":78.1},{"place":8,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":76.9},{"place":9,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":76.8},{"place":10,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":75.5},{"place":11,"model":"fun-audio-chat-8b","company":"alibaba","family":"Fun-Audio","version":"Fun-Audio-Chat","score":66.27},{"place":12,"model":"kimi-audio-7b-instruct","company":"moonshotai","family":"Kimi","version":"Kimi-Audio","score":63.12},{"place":13,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":56.4},{"place":14,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":44.94},{"place":15,"model":"step-audio-2-mini","company":"stepfun","family":"Step-Audio","version":"Step-Audio 2","score":44.85},{"place":16,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":32.6},{"place":17,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":30.92},{"place":18,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":30.56},{"place":19,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":15.64},{"place":20,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":9.31}]},{"id":"voicebench-wildvoice","name":"VoiceBench WildVoice","topic":"VoiceBench","description":"VoiceBench evaluation on WildVoice dataset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":93.4,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":14,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":93.4},{"place":2,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":92.3},{"place":3,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.1},{"place":4,"model":"gpt-4o-audio","company":"openai","family":"GPT","version":"GPT-4o","score":91.6},{"place":5,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":91.6},{"place":6,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.9},{"place":7,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":90.5},{"place":8,"model":"qwen2.5-omni","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":77.7},{"place":9,"model":"qwen2.5-omni-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":3.42},{"place":10,"model":"lfm2-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2-Audio","score":3.17},{"place":11,"model":"lfm2.5-audio-1.5b","company":"liquidai","family":"LFM","version":"LFM2.5-Audio","score":3.15},{"place":12,"model":"nemotronlabs-voicechat-11b","company":"nvidia","family":"Nemotron","version":"NemotronLabs VoiceChat","score":2.8},{"place":13,"model":"mini-omni2","company":"gpt4o-omni","family":"Mini-Omni","version":"Mini-Omni2","score":1.79},{"place":14,"model":"moshi","company":"kyutai","family":"Moshi","version":"Moshi","score":1.3}]},{"id":"vpct","name":"VPCT","topic":"Multimodal reasoning","description":"Visual perception and comprehension test.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":90,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":90},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":61},{"place":3,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":56},{"place":4,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":52},{"place":5,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":41},{"place":6,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":35}]},{"id":"vqa-rad","name":"VQA-RAD","topic":"Medical VQA","description":"Radiology visual question answering (closed-question accuracy).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MedMO-8B-Next","top_percent":86.4,"top_model_id":"medmo-8b-next","top_generation":"MedMO-Next","top_model_base":"MedMO","top_model_family":"MedMO","top_company":"mbzuai","top_open_source":1,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"medmo-8b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":86.4},{"place":2,"model":"medmo-4b-next","company":"mbzuai","family":"MedMO","version":"MedMO-Next","score":79.7},{"place":3,"model":"fleming-vl-8b","company":"ubiquant","family":"Fleming-VL","version":"Fleming-VL","score":78.4},{"place":4,"model":"lingshu-7b","company":"alibaba","family":"Lingshu","version":"Lingshu","score":77.2},{"place":5,"model":"medix-r1-8b","company":"mbzuai","family":"MediX","version":"MediX-R1","score":75.2},{"place":6,"model":"medmo-8b","company":"mbzuai","family":"MedMO","version":"MedMO","score":72.3},{"place":7,"model":"medgemma-1.5-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1.5","score":70.2},{"place":8,"model":"medgemma-4b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":69.1},{"place":9,"model":"medgemma-27b-it","company":"google","family":"MedGemma","version":"MedGemma 1","score":67.1},{"place":10,"model":"medmo-4b","company":"mbzuai","family":"MedMO","version":"MedMO","score":50.9},{"place":11,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":42.1}]},{"id":"vqav2","name":"VQAv2","topic":"Visual question answering","description":"Standard Visual Question Answering v2 benchmark on natural images.","url":"https://visualqa.org/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":89.78,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":83,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":89.78},{"place":2,"model":"reka-edge-2603","company":"reka","family":"Reka Edge","version":"Reka Edge","score":88.4},{"place":3,"model":"molmopoint-8b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":87.2},{"place":4,"model":"molmo2-8b","company":"allenai","family":"Molmo2","version":"Molmo2","score":87},{"place":5,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":86.6},{"place":6,"model":"molmo2-o-7b","company":"allenai","family":"Molmo2","version":"Molmo2","score":86.6},{"place":7,"model":"molmopoint-o-7b","company":"allenai","family":"Molmo","version":"MolmoPoint","score":86.6},{"place":8,"model":"molmo-72b","company":"allenai","family":"Molmo","version":"Molmo","score":86.5},{"place":9,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":85.6},{"place":10,"model":"molmo-7b-d","company":"allenai","family":"Molmo","version":"Molmo","score":85.6},{"place":11,"model":"plm-8b","company":"unknown","family":"PLM","version":"PLM","score":85.6},{"place":12,"model":"molmo-7b-o","company":"allenai","family":"Molmo","version":"Molmo","score":85.3},{"place":13,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":85.3},{"place":14,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":85.2},{"place":15,"model":"emu2-chat","company":"baai","family":"Emu","version":"Emu2-Chat","score":84.9},{"place":16,"model":"plm-3b","company":"unknown","family":"PLM","version":"PLM","score":84.4},{"place":17,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":84},{"place":18,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":83.9},{"place":19,"model":"cambrian-1-34b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":83.8},{"place":20,"model":"llava-onevision-72b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":83.8},{"place":21,"model":"cogagent-18b","company":"zai","family":"CogVLM","version":"CogAgent","score":83.7},{"place":22,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":83.22},{"place":23,"model":"qwen2-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":82.9},{"place":24,"model":"molmoe-1b","company":"allenai","family":"Molmo","version":"MolmoE","score":82.8},{"place":25,"model":"eagle2.5-8b","company":"unknown","family":"Eagle","version":"Eagle 2.5","score":82.4},{"place":26,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.3},{"place":27,"model":"cogvlm-17b-chat","company":"zai","family":"CogVLM","version":"CogVLM","score":82.3},{"place":28,"model":"qwen2-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2 VL","score":81.9},{"place":29,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":81.7},{"place":30,"model":"xgen-mm-interleave-4b","company":"salesforce","family":"xGen","version":"xGen-MM","score":81.5},{"place":31,"model":"cambrian-1-8b","company":"nyu","family":"Cambrian","version":"Cambrian 1","score":81.2},{"place":32,"model":"pixtral-large-2411","company":"mistral","family":"Pixtral","version":"Pixtral","score":80.9},{"place":33,"model":"fastvlm-7b","company":"apple","family":"FastVLM","version":"FastVLM","score":80.8},{"place":34,"model":"sphinx-2k","company":"shanghai-ai-lab","family":"SPHINX","version":"SPHINX","score":80.7},{"place":35,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":80.4},{"place":36,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":80.2},{"place":37,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":80.1},{"place":38,"model":"llava-1.5-13b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":80},{"place":39,"model":"zaya1-vl-8b","company":"zyphra","family":"ZAYA","version":"ZAYA1","score":80},{"place":40,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":79.82},{"place":41,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":79.7},{"place":42,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":79.5},{"place":43,"model":"qwen-vl","company":"qwen","family":"Qwen","version":"Qwen-VL","score":79.5},{"place":44,"model":"mplug-owl2","company":"alibaba","family":"mPLUG","version":"mPLUG-Owl2","score":79.4},{"place":45,"model":"unified-io-2-xxl","company":"allenai","family":"Unified-IO","version":"Unified-IO 2","score":79.4},{"place":46,"model":"keye-vl-1.5-8b","company":"kuaishou","family":"Keye-VL","version":"Keye-VL 1.5","score":79.3},{"place":47,"model":"fastvlm-1.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":79.1},{"place":48,"model":"gpt-4o-0513","company":"openai","family":"GPT","version":"GPT-4o","score":78.7},{"place":49,"model":"pixtral-12b","company":"mistral","family":"Pixtral","version":"Pixtral","score":78.6},{"place":50,"model":"llava-1.5-7b","company":"microsoft","family":"LLaVA","version":"LLaVA 1.5","score":78.5},{"place":51,"model":"internvl3.5-gpt-oss-20b-a4b","company":"opengvlab","family":"Intern","version":"InternVL3.5","score":78.4},{"place":52,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.3},{"place":53,"model":"qwen-vl-chat","company":"qwen","family":"Qwen","version":"Qwen-VL","score":78.2},{"place":54,"model":"llama-3.2v-90b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":78.1},{"place":55,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":78.1},{"place":56,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":77.8},{"place":57,"model":"shikra-13b","company":"sensetime","family":"Shikra","version":"Shikra","score":77.36},{"place":58,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":77.2},{"place":59,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":77},{"place":60,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":76.7},{"place":61,"model":"fastvlm-0.5b","company":"apple","family":"FastVLM","version":"FastVLM","score":76.3},{"place":62,"model":"paligemma-mix-3b","company":"google","family":"PaliGemma","version":"PaliGemma","score":76.3},{"place":63,"model":"phi-3.5-vision-4b","company":"microsoft","family":"Phi","version":"Phi 3.5","score":75.7},{"place":64,"model":"llama-3.2v-11b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":75.2},{"place":65,"model":"fuyu-8b","company":"adept","family":"Fuyu","version":"Fuyu","score":74.2},{"place":66,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":74.1},{"place":67,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":72.1},{"place":68,"model":"claude-3.5-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.5","score":70.7},{"place":69,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":69.4},{"place":70,"model":"claude-3-haiku","company":"anthropic","family":"Claude","version":"Claude 3","score":68.4},{"place":71,"model":"glm-4.1v-9b","company":"zai","family":"GLM","version":"GLM 4.1V","score":68.3},{"place":72,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":68.3},{"place":73,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":67.1},{"place":74,"model":"claude-3-opus","company":"anthropic","family":"Claude","version":"Claude 3","score":66.3},{"place":75,"model":"gemini-1.5-flash-8b-0827","company":"google","family":"Gemini","version":"Gemini 1.5","score":65.5},{"place":76,"model":"blip-2-vicuna-13b","company":"salesforce","family":"BLIP","version":"BLIP-2","score":65},{"place":77,"model":"minicpm-v-4.5-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.5","score":64.1},{"place":78,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":62.7},{"place":79,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":57.8},{"place":80,"model":"dreamllm-7b","company":"megvii","family":"DreamLLM","version":"DreamLLM","score":56.6},{"place":81,"model":"flamingo-80b","company":"google","family":"Flamingo","version":"Flamingo","score":56.3},{"place":82,"model":"openflamingo-v2","company":"openflamingo","family":"OpenFlamingo","version":"OpenFlamingo v2","score":53},{"place":83,"model":"flamingo-9b","company":"google","family":"Flamingo","version":"Flamingo","score":51.8},{"place":84,"model":"kosmos2","company":"microsoft","family":"Kosmos2","version":"Kosmos-2","score":51.1},{"place":85,"model":"kosmos-1","company":"microsoft","family":"Kosmos","version":"Kosmos-1","score":51},{"place":86,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":38.8},{"place":87,"model":"idefics-80b-instruct","company":"huggingface","family":"IDEFICS","version":"IDEFICS","score":37.4}]},{"id":"vsi-bench","name":"VSI-Bench","topic":"Spatial intelligence","description":"Visual spatial intelligence benchmark covering 3D reasoning and spatial inference tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Molmo2-ER","top_percent":74.5,"top_model_id":"molmo2-er","top_generation":"Molmo2","top_model_base":"Molmo2 ER 4B","top_model_family":"Molmo2","top_company":"allenai","top_open_source":1,"lower_is_better":false,"bench_models":55,"total_models":3854,"placements":[{"place":1,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":74.5},{"place":2,"model":"rynnbrain-30b-a3b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":74.5},{"place":3,"model":"rynnbrain-4b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":73.7},{"place":4,"model":"rynnbrain-8b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":71},{"place":5,"model":"rynnbrain-2b","company":"alibaba","family":"RynnBrain","version":"RynnBrain","score":70.5},{"place":6,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":65.9},{"place":7,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.8},{"place":8,"model":"mage-vl","company":"microsoft","family":"Mage","version":"Mage-VL","score":64.3},{"place":9,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.3},{"place":10,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63.2},{"place":11,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":61.9},{"place":12,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.5},{"place":13,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":61.4},{"place":14,"model":"hy-embodied-0.5-mot-2b","company":"tencent","family":"HY-Embodied","version":"HY-Embodied 0.5","score":60.5},{"place":15,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":60.3},{"place":16,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":59.8},{"place":17,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":59.69},{"place":18,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":59.4},{"place":19,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":58.9},{"place":20,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":58.4},{"place":21,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":57.9},{"place":22,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":57.5},{"place":23,"model":"pelican-vl-72b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":57.3},{"place":24,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":57.3},{"place":25,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":56.5},{"place":26,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":56.4},{"place":27,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":56.3},{"place":28,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":55.7},{"place":29,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":55.68},{"place":30,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.2},{"place":31,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":55.1},{"place":32,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":54.49},{"place":33,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.9},{"place":34,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":53.7},{"place":35,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":53.3},{"place":36,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":52.9},{"place":37,"model":"pelican-vl-7b","company":"x-humanoid","family":"Pelican-VL","version":"Pelican-VL 1.0","score":52.8},{"place":38,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":52.51},{"place":39,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":51.8},{"place":40,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":51.1},{"place":41,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":50.4},{"place":42,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":48.8},{"place":43,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":48.5},{"place":44,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":48},{"place":45,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":47.92},{"place":46,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":46.6},{"place":47,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":46.2},{"place":48,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":45.8},{"place":49,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":45.8},{"place":50,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":45},{"place":51,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":43.9},{"place":52,"model":"robobrain-2.0","company":"robobrain","family":"RoboBrain","version":"RoboBrain","score":42.7},{"place":53,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":42.5},{"place":54,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":42.42},{"place":55,"model":"robobrain-2.5-4b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":41.7},{"place":56,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":39.9},{"place":57,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":37.7},{"place":58,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":36.1},{"place":59,"model":"robobrain-2.0-7b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.0","score":36.1},{"place":60,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":32.91},{"place":61,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":31.2},{"place":62,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":30.5},{"place":63,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":27},{"place":64,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":27},{"place":65,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":26.1},{"place":66,"model":"phi-4-reasoning-vision-15b","company":"microsoft","family":"Phi","version":"Phi 4","score":25.5},{"place":67,"model":"phi-4-multimodal-instruct","company":"microsoft","family":"Phi","version":"Phi 4","score":24.09},{"place":68,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":21.3}]},{"id":"waymoqa","name":"WaymoQA","topic":"Driving scene QA","description":"Driving-scene multiple-choice QA benchmark built on Waymo data; overall accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen-Drive-1.0-4B","top_percent":74.47,"top_model_id":"qwen-drive-1.0-4b","top_generation":"Qwen-Drive-1.0","top_model_base":"Qwen-Drive 1.0 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":74.47},{"place":2,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":69.56},{"place":3,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":67.1},{"place":4,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":58.36},{"place":5,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":58.09},{"place":6,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":57.93},{"place":7,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":55.23},{"place":8,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":44.37},{"place":9,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":43.9}]},{"id":"waymoqa-safety","name":"WaymoQA (Safety)","topic":"Driving scene QA","description":"Safety-critical subset of WaymoQA; accuracy.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen-Drive-1.0-4B","top_percent":70.7,"top_model_id":"qwen-drive-1.0-4b","top_generation":"Qwen-Drive-1.0","top_model_base":"Qwen-Drive 1.0 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":70.7},{"place":2,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":66.54},{"place":3,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.46},{"place":4,"model":"cosmos-reason2-8b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason2","score":57.68},{"place":5,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":56.93},{"place":6,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":54.47},{"place":7,"model":"llava-onevision-2-8b","company":"llava","family":"LLaVA","version":"LLaVA-OneVision-2","score":49.65},{"place":8,"model":"alpamayo-1.5-10b","company":"nvidia","family":"Alpamayo","version":"Alpamayo 1.5","score":42.61},{"place":9,"model":"cosmos-reason1-7b","company":"nvidia","family":"Cosmos","version":"Cosmos Reason1","score":39.5}]},{"id":"webarena","name":"WebArena","topic":"Web agents","description":"Realistic self-hosted web environments (shopping, forums, GitLab, CMS, maps) for autonomous web agents; task success rate.","url":"https://webarena.dev/","leaderboard":"https://docs.google.com/spreadsheets/d/1M801lEpBbKSNwP-vDBkC_pF7LdyGU1f_ufZb_NWNBZQ/edit?usp=sharing","github":"","paper":"","metric":"percent","stars":"","top_model":"DeepSeek V3.2","top_percent":74.3,"top_model_id":"deepseek-v3.2","top_generation":"DeepSeek V3.2","top_model_base":"DeepSeek V3.2","top_model_family":"DeepSeek","top_company":"deepseek","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":74.3},{"place":2,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":65.6},{"place":3,"model":"holo3-122b-a10b","company":"hcompany","family":"Holo","version":"Holo3","score":64.9},{"place":4,"model":"holo3-35b-a3b","company":"hcompany","family":"Holo","version":"Holo3","score":64.8},{"place":5,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":63.4},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.1},{"place":7,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.1},{"place":8,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":51.4},{"place":9,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":14.9},{"place":10,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":13.1},{"place":11,"model":"gpt-4-0613","company":"openai","family":"GPT","version":"GPT-4","score":11.7},{"place":12,"model":"gpt-3.5-turbo-0613","company":"openai","family":"GPT","version":"GPT-3.5","score":8.87},{"place":13,"model":"qwen1.5-72b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":7.14},{"place":14,"model":"gemini-1.0-pro","company":"google","family":"Gemini","version":"Gemini 1.0","score":7.12},{"place":15,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":7.02},{"place":16,"model":"lemur-70b-chat","company":"xlang","family":"Lemur","version":"Lemur","score":5.3},{"place":17,"model":"codellama-34b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":4.06},{"place":18,"model":"agentlm-70b","company":"zai","family":"AgentLM","version":"AgentLM","score":3.81},{"place":19,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":3.32},{"place":20,"model":"agentlm-13b","company":"zai","family":"AgentLM","version":"AgentLM","score":1.6},{"place":21,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":1.39},{"place":22,"model":"agentlm-7b","company":"zai","family":"AgentLM","version":"AgentLM","score":0.74},{"place":23,"model":"codellama-7b-instruct","company":"meta","family":"CodeLlama","version":"CodeLlama","score":0}]},{"id":"webarena-verified","name":"WebArena-Verified","topic":"Web automation","description":"Verified version of the WebArena browser-use benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3","top_percent":71.6,"top_model_id":"kimi-k3","top_generation":"Kimi K3","top_model_base":"Kimi K3","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":19,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":71.6},{"place":2,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":71.3},{"place":3,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":69.7},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":67.9},{"place":5,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":67.6},{"place":6,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":67.3},{"place":7,"model":"gpt-5.4-thinking","company":"openai","family":"GPT","version":"GPT-5.4","score":67.3},{"place":8,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":66.8},{"place":9,"model":"gpt-5.2-thinking","company":"openai","family":"GPT","version":"GPT-5.2","score":65.4},{"place":10,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":64.8},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":64.3},{"place":12,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":63.4},{"place":13,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.3},{"place":14,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":55.3},{"place":15,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":48.8},{"place":16,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":37.62},{"place":17,"model":"nemotron-3.5-lightning-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":28.69},{"place":18,"model":"lfm2.5-24b-a2b","company":"liquidai","family":"LFM","version":"LFM2.5","score":26.75},{"place":19,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":25.62}]},{"id":"webclick","name":"WebClick","topic":"GUI agents","description":"Task success on the WebClick UI agent benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Holo2-235B-A22B","top_percent":94.3,"top_model_id":"holo2-235b-a22b","top_generation":"Holo2","top_model_base":"Holo2","top_model_family":"Holo","top_company":"hcompany","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"holo2-235b-a22b","company":"hcompany","family":"Holo","version":"Holo2","score":94.3},{"place":2,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":93},{"place":3,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":92.43},{"place":4,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":92.1},{"place":5,"model":"holo2-30b-a3b","company":"hcompany","family":"Holo","version":"Holo2","score":91.3},{"place":6,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":90.24},{"place":7,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":89.5},{"place":8,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":89.5},{"place":9,"model":"holo2-4b","company":"hcompany","family":"Holo","version":"Holo2","score":88.8},{"place":10,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":88.29},{"place":11,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":86.1},{"place":12,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.9},{"place":13,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.8},{"place":14,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":84.44},{"place":15,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":84.04},{"place":16,"model":"holotron-12b","company":"hcompany","family":"Holotron","version":"Holotron","score":83.8},{"place":17,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":81.45},{"place":18,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":79.35},{"place":19,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":77},{"place":20,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":76.51},{"place":21,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":71.2},{"place":22,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":18}]},{"id":"webdev-arena","name":"WebDev Arena","topic":"Web development agents","description":"Arena evaluation for autonomous web development agents.","url":"","leaderboard":"https://lmarena.ai/leaderboard/webdev","github":"","paper":"","metric":"elo","stars":"","top_model":"Claude Opus 5.5 (max)","top_percent":1807,"top_model_id":"claude-opus-5.5-max","top_generation":"Claude 5.5","top_model_base":"Claude Opus 5.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":202,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1807},{"place":2,"model":"gpt-6-astra-max","company":"openai","family":"GPT","version":"GPT-6","score":1774},{"place":3,"model":"claude-sonnet-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1769},{"place":4,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":1749},{"place":5,"model":"claude-fable-5.1-max","company":"anthropic","family":"Claude","version":"Claude 5.1","score":1742},{"place":6,"model":"muse-wonder-full","company":"meta","family":"Muse","version":"Muse Wonder","score":1726},{"place":7,"model":"claude-sonnet-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1709},{"place":8,"model":"kimi-k3.1-pro-max","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":1692},{"place":9,"model":"claude-opus-5-max","company":"anthropic","family":"Claude","version":"Claude 5","score":1691},{"place":10,"model":"gpt-6-sol-max","company":"openai","family":"GPT","version":"GPT-6","score":1681},{"place":11,"model":"gemini-4-argon-high","company":"google","family":"Gemini","version":"Gemini 4","score":1674},{"place":12,"model":"qwen3.8-max-0902","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1673},{"place":13,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1672},{"place":14,"model":"deepseek-v4.1-flash-1017-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1665},{"place":15,"model":"claude-opus-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1659},{"place":16,"model":"muse-spark-1.3-max","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1657},{"place":17,"model":"kimi-k3-max","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":1655},{"place":18,"model":"muse-wonder-max","company":"meta","family":"Muse","version":"Muse Wonder","score":1651},{"place":19,"model":"grok-4.7-xhigh","company":"xai","family":"Grok","version":"Grok 4.7","score":1638},{"place":20,"model":"mimo-v2.6-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1635},{"place":21,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":1631},{"place":22,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1629},{"place":23,"model":"mimo-v2.6-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.6","score":1625},{"place":24,"model":"claude-fable-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1624},{"place":25,"model":"glm-5.3-max","company":"zai","family":"GLM","version":"GLM 5.3","score":1623},{"place":26,"model":"muse-spark-1.3-xhigh","company":"meta","family":"Muse","version":"Muse Spark 1.3","score":1620},{"place":27,"model":"deepseek-v4.1-flash-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":1619},{"place":28,"model":"grok-4.6-high","company":"xai","family":"Grok","version":"Grok 4.6","score":1617},{"place":29,"model":"gpt-5.6-sol-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1615},{"place":30,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":1608},{"place":31,"model":"glm-5.2-max","company":"zai","family":"GLM","version":"GLM 5.2","score":1604},{"place":32,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":1591},{"place":33,"model":"gemini-3.7-flash-high","company":"google","family":"Gemini","version":"Gemini 3.7","score":1590},{"place":34,"model":"minimax-m3.1-flash","company":"minimax","family":"MiniMax","version":"MiniMax M3.1","score":1589},{"place":35,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":1588},{"place":36,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":1586},{"place":37,"model":"gemini-3.8-flash-high","company":"google","family":"Gemini","version":"Gemini 3.8","score":1585},{"place":38,"model":"deepseek-v4-pro-0813-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1582},{"place":39,"model":"deepseek-v4-flash-preview-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1582},{"place":40,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":1579},{"place":41,"model":"step-5-preview","company":"stepfun","family":"Step","version":"Step 5","score":1568},{"place":42,"model":"claude-opus-4.7-high","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1558},{"place":43,"model":"claude-opus-4.8-high","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1556},{"place":44,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":1555},{"place":45,"model":"grok-4.5","company":"xai","family":"Grok","version":"Grok 4.5","score":1553},{"place":46,"model":"claude-opus-4.6-high","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1546},{"place":47,"model":"mistral-large-4","company":"mistral","family":"Mistral","version":"Mistral Large 4","score":1545},{"place":48,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":1542},{"place":49,"model":"claude-sonnet-5","company":"anthropic","family":"Claude","version":"Claude 5","score":1541},{"place":50,"model":"claude-sonnet-5-high","company":"anthropic","family":"Claude","version":"Claude 5","score":1541},{"place":51,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":1538},{"place":52,"model":"gemini-3.6-flash-high","company":"google","family":"Gemini","version":"Gemini 3.6","score":1538},{"place":53,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1537},{"place":54,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":1536},{"place":55,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":1535},{"place":56,"model":"muse-spark-1.2-xhigh","company":"meta","family":"Muse","version":"Muse Spark","score":1533},{"place":57,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":1526},{"place":58,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":1523},{"place":59,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":1523},{"place":60,"model":"gpt-5.6-terra-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1521},{"place":61,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":1520},{"place":62,"model":"gpt-5.6-luna-xhigh","company":"openai","family":"GPT","version":"GPT-5.6","score":1519},{"place":63,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":1515},{"place":64,"model":"gpt-5.5-xhigh","company":"openai","family":"GPT","version":"GPT-5.5","score":1512},{"place":65,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":1509},{"place":66,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":1508},{"place":67,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":1506},{"place":68,"model":"gemini-3.5-flash-high","company":"google","family":"Gemini","version":"Gemini 3.5","score":1499},{"place":69,"model":"claude-opus-4.5-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1494},{"place":70,"model":"gemini-3.5-flash-medium","company":"google","family":"Gemini","version":"Gemini 3.5","score":1491},{"place":71,"model":"gpt-5.5-high","company":"openai","family":"GPT","version":"GPT-5.5","score":1487},{"place":72,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":1483},{"place":73,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":1482},{"place":74,"model":"qwen3.6-max-preview","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1482},{"place":75,"model":"mimo-v2.5-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1481},{"place":76,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":1480},{"place":77,"model":"spark-x2.6","company":"iflytek","family":"Spark","version":"Spark X2.6","score":1480},{"place":78,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1476},{"place":79,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":1473},{"place":80,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1470},{"place":81,"model":"claude-opus-4-1-20250805-thinking-16k","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1468},{"place":82,"model":"deepseek-v4-pro-preview-high","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1464},{"place":83,"model":"gpt-5.4-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1464},{"place":84,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":1462},{"place":85,"model":"claude-opus-4.1-20250805","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1458},{"place":86,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1456},{"place":87,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":1447},{"place":88,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1447},{"place":89,"model":"gpt-5.4-medium","company":"openai","family":"GPT","version":"GPT-5.4","score":1444},{"place":90,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":1440},{"place":91,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":1440},{"place":92,"model":"mimo-v2.5","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":1438},{"place":93,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1437},{"place":94,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":1436},{"place":95,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":1435},{"place":96,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":1435},{"place":97,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":1434},{"place":98,"model":"mimo-v2-pro","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1434},{"place":99,"model":"gpt-5-medium","company":"openai","family":"GPT","version":"GPT-5","score":1418},{"place":100,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":1417},{"place":101,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1415},{"place":102,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":1409},{"place":103,"model":"gpt-5.3-codex","company":"openai","family":"GPT","version":"GPT-5.3 Codex","score":1407},{"place":104,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":1406},{"place":105,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1405},{"place":106,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":1403},{"place":107,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":1401},{"place":108,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":1401},{"place":109,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1400},{"place":110,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":1398},{"place":111,"model":"nemotron-3.5-super-vl-120b-a12b-nvfp4","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":1398},{"place":112,"model":"gpt-5.4-mini-high","company":"openai","family":"GPT","version":"GPT-5.4","score":1397},{"place":113,"model":"gpt-5.1-medium","company":"openai","family":"GPT","version":"GPT-5.1","score":1396},{"place":114,"model":"claude-4.5-sonnet-thinking-32k","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1394},{"place":115,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1393},{"place":116,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1393},{"place":117,"model":"minimax-m2.5","company":"minimax","family":"MiniMax","version":"MiniMax M2.5","score":1386},{"place":118,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1385},{"place":119,"model":"gemini-3-flash-minimal","company":"google","family":"Gemini","version":"Gemini 3","score":1385},{"place":120,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":1384},{"place":121,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1383},{"place":122,"model":"claude-opus-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1383},{"place":123,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1375},{"place":124,"model":"grok-4.2-0309","company":"xai","family":"Grok","version":"Grok 4.2","score":1375},{"place":125,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":1371},{"place":126,"model":"solar-pro-4","company":"upstage","family":"Solar","version":"Solar Pro 4","score":1370},{"place":127,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":1368},{"place":128,"model":"qwen3-coder-480b-a35b","company":"qwen","family":"Qwen","version":"Qwen3","score":1367},{"place":129,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1367},{"place":130,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":1366},{"place":131,"model":"qwen3-coder","company":"qwen","family":"Qwen","version":"Qwen3","score":1366},{"place":132,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1364},{"place":133,"model":"deepseek-v3.1-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1362},{"place":134,"model":"claude-sonnet-4-20250514","company":"anthropic","family":"Claude","version":"Claude 4","score":1362},{"place":135,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1362},{"place":136,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1361},{"place":137,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":1360},{"place":138,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":1360},{"place":139,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1359},{"place":140,"model":"claude-3.7-sonnet-20250219","company":"anthropic","family":"Claude","version":"Claude 3.7","score":1358},{"place":141,"model":"grok-4.3","company":"xai","family":"Grok","version":"Grok 4.3","score":1357},{"place":142,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":1357},{"place":143,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":1355},{"place":144,"model":"laguna-m.1","company":"poolside","family":"Laguna","version":"Laguna","score":1349},{"place":145,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":1342},{"place":146,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":1341},{"place":147,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":1340},{"place":148,"model":"gpt-5.2-codex","company":"openai","family":"GPT","version":"GPT-5.2 Codex","score":1339},{"place":149,"model":"gpt-5.1-codex","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":1337},{"place":150,"model":"qwen3-coder-plus-2025-09-23","company":"qwen","family":"Qwen","version":"Qwen3","score":1332},{"place":151,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1331},{"place":152,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":1330},{"place":153,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1326},{"place":154,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1323},{"place":155,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":1316},{"place":156,"model":"laguna-xs.2","company":"poolside","family":"Laguna","version":"Laguna","score":1303},{"place":157,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":1297},{"place":158,"model":"mimo-v2-flash-thinking","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":1293},{"place":159,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":1289},{"place":160,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":1275},{"place":161,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":1272},{"place":162,"model":"mistral-medium-3.5","company":"mistral","family":"Mistral","version":"Mistral 3.5","score":1264},{"place":163,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":1256},{"place":164,"model":"kat-coder-pro-v1","company":"kuaishou","family":"KAT","version":"KAT-Coder Pro v1","score":1256},{"place":165,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1254},{"place":166,"model":"gpt-4.1-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1253},{"place":167,"model":"gpt-5.1-codex-mini","company":"openai","family":"GPT","version":"GPT-5.1 Codex","score":1244},{"place":168,"model":"qwen3.5-flash","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1244},{"place":169,"model":"grok-4.1-fast-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1242},{"place":170,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1238},{"place":171,"model":"trinity-large-thinking","company":"arcee","family":"Trinity","version":"Trinity Large","score":1238},{"place":172,"model":"mistral-large-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1232},{"place":173,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":1215},{"place":174,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":1208},{"place":175,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":1199},{"place":176,"model":"devstral-2","company":"mistral","family":"Devstral","version":"Devstral 2","score":1197},{"place":177,"model":"gpt-4.1-mini-2025-04-14","company":"openai","family":"GPT","version":"GPT-4.1","score":1193},{"place":178,"model":"granite-4.1-8b","company":"IBM","family":"Granite","version":"Granite 4.1","score":1192},{"place":179,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":1189},{"place":180,"model":"o3-2025-04-16","company":"openai","family":"o3","version":"o3","score":1186},{"place":181,"model":"mistral-medium-3","company":"mistral","family":"Mistral","version":"Mistral 3","score":1181},{"place":182,"model":"grok-4-0709","company":"xai","family":"Grok","version":"Grok 4","score":1174},{"place":183,"model":"mercury-2","company":"inception","family":"Mercury","version":"Mercury 2","score":1171},{"place":184,"model":"grok-4-fast-thinking","company":"xai","family":"Grok","version":"Grok 4","score":1160},{"place":185,"model":"grok-code-fast-1","company":"xai","family":"Grok","version":"Grok Code","score":1150},{"place":186,"model":"grok-3-preview-02-24","company":"xai","family":"Grok","version":"Grok 3","score":1143},{"place":187,"model":"o3-mini-high","company":"openai","family":"o3","version":"o3","score":1137},{"place":188,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":1133},{"place":189,"model":"minimax-m1","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":1129},{"place":190,"model":"o4-mini-2025-04-16","company":"openai","family":"o4","version":"o4","score":1118},{"place":191,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":1094},{"place":192,"model":"o3-mini","company":"openai","family":"o3","version":"o3","score":1092},{"place":193,"model":"gemini-2.0-pro-exp-02-05","company":"google","family":"Gemini","version":"Gemini 2.0","score":1090},{"place":194,"model":"devstral-medium","company":"mistral","family":"Devstral","version":"Devstral","score":1072},{"place":195,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":1045},{"place":196,"model":"o1-mini","company":"openai","family":"o1","version":"o1","score":1043},{"place":197,"model":"gemini-2.0-flash-001","company":"google","family":"Gemini","version":"Gemini 2.0","score":1040},{"place":198,"model":"gemini-2.0-flash-thinking-01-21","company":"google","family":"Gemini","version":"Gemini 2.0","score":1030},{"place":199,"model":"llama-4-maverick-17b-128e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":1027},{"place":200,"model":"gemini-2.0-flash-exp","company":"google","family":"Gemini","version":"Gemini 2.0","score":980},{"place":201,"model":"qwen2.5-max","company":"qwen","family":"Qwen","version":"Qwen2.5","score":976},{"place":202,"model":"gpt-4o-2024-11-20","company":"openai","family":"GPT","version":"GPT-4o","score":964},{"place":203,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":960},{"place":204,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":902},{"place":205,"model":"llama-4-scout-17b-16e-instruct","company":"meta","family":"Llama","version":"Llama 4","score":901},{"place":206,"model":"gemini-1.5-pro-002","company":"google","family":"Gemini","version":"Gemini 1.5","score":893},{"place":207,"model":"llama-3.1-405b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":810}]},{"id":"webquest-multiqa","name":"WebQuest-MultiQA","topic":"Web agents","description":"Multi-question web search and interaction tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-4.5V","top_percent":60.6,"top_model_id":"glm-4.5v","top_generation":"GLM 4.5V","top_model_base":"GLM 4.5V","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":60.6},{"place":2,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":59},{"place":3,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":54.7},{"place":4,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":53.4},{"place":5,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":52.8},{"place":6,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":36.5},{"place":7,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":11.1}]},{"id":"webquest-singleqa","name":"WebQuest-SingleQA","topic":"Web agents","description":"Single-question web search and interaction tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-4.6V","top_percent":79.5,"top_model_id":"glm-4.6v","top_generation":"GLM 4.6V","top_model_base":"GLM 4.6V","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":79.5},{"place":2,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":76.9},{"place":3,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":75.1},{"place":4,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":72.1},{"place":5,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":58.7},{"place":6,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":35.6},{"place":7,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":31.2}]},{"id":"websrc","name":"WebSrc","topic":"Web QA","description":"Webpage question answering (SQuAD F1).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Holo1.5-72B","top_percent":97.2,"top_model_id":"holo1.5-72b","top_generation":"Holo1.5","top_model_base":"Holo1.5-72B","top_model_family":"Holo","top_company":"hcompany","top_open_source":1,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"holo1.5-72b","company":"hcompany","family":"Holo","version":"Holo1.5","score":97.2},{"place":2,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":97},{"place":3,"model":"ui-venus-72b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":96.7},{"place":4,"model":"ui-venus-7b","company":"antgroup","family":"UI-Venus","version":"UI-Venus","score":96.6},{"place":5,"model":"mimo-vl-7b-sft","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":96.5},{"place":6,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":96},{"place":7,"model":"holo1.5-7b","company":"hcompany","family":"Holo","version":"Holo1.5","score":95.9},{"place":8,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":95.3},{"place":9,"model":"mimo-vl-7b-rl","company":"xiaomi","family":"MiMo","version":"MiMo VL","score":95.3},{"place":10,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":95},{"place":11,"model":"holo1.5-3b","company":"hcompany","family":"Holo","version":"Holo1.5","score":94.8},{"place":12,"model":"holo1-3b","company":"hcompany","family":"Holo","version":"Holo1","score":93.9},{"place":13,"model":"qwen2.5-vl-3b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":93},{"place":14,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":92.9},{"place":15,"model":"claude-3.7-sonnet","company":"anthropic","family":"Claude","version":"Claude 3.7","score":91.1},{"place":16,"model":"internvl-8b","company":"opengvlab","family":"Intern","version":"InternVL","score":91.1},{"place":17,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":89.1},{"place":18,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":89}]},{"id":"webtailbench","name":"WebTailBench","topic":"Web agents","description":"Microsoft long-tail web task benchmark (shopping, travel, comparison and other real-world tasks) introduced with Fara-7B.","url":"https://huggingface.co/datasets/microsoft/WebTailBench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"MolmoWeb-8B","top_percent":49.5,"top_model_id":"molmoweb-8b","top_generation":"MolmoWeb","top_model_base":"MolmoWeb 8B","top_model_family":"Molmo","top_company":"allenai","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"molmoweb-8b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":49.5},{"place":2,"model":"molmoweb-4b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":43.8},{"place":3,"model":"fara1.5-27b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":40.2},{"place":4,"model":"fara-7b","company":"microsoft","family":"Fara","version":"Fara","score":38.4},{"place":5,"model":"fara1.5-9b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":32.3},{"place":6,"model":"fara1.5-4b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":27.4},{"place":7,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":22.4},{"place":8,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":19.5}]},{"id":"webtestbench","name":"WebTestBench","topic":"Web testing agents","description":"Benchmark of web-app testing agents that detect defects against a checklist in live web applications.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":54,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":54},{"place":2,"model":"nex-n2.5-pro","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":52.8},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":52.3},{"place":4,"model":"nex-n2.5-mini","company":"nex-agi","family":"Nex","version":"Nex-N2.5","score":48.6}]},{"id":"webvoyager","name":"WebVoyager","topic":"Web agents","description":"Web navigation and interaction tasks for LLM agents.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"UI-Venus-2 27B","top_percent":93.4,"top_model_id":"ui-venus-2-27b","top_generation":"UI-Venus 2","top_model_base":"UI-Venus-2 27B","top_model_family":"UI-Venus","top_company":"antgroup","top_open_source":0,"lower_is_better":false,"bench_models":36,"total_models":3854,"placements":[{"place":1,"model":"ui-venus-2-27b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":93.4},{"place":2,"model":"ling-3.0-flash-vl","company":"antgroup","family":"Ling","version":"Ling 3.0","score":90.83},{"place":3,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.8},{"place":4,"model":"ui-venus-2-9b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 2","score":90.8},{"place":5,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":90.39},{"place":6,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":90.1},{"place":7,"model":"fara1.5-27b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":89.3},{"place":8,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":88.5},{"place":9,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":88},{"place":10,"model":"fara1.5-9b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":86.6},{"place":11,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":85.43},{"place":12,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":85.1},{"place":13,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.3},{"place":14,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.3},{"place":15,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":81},{"place":16,"model":"fara1.5-4b","company":"microsoft","family":"Fara","version":"Fara 1.5","score":80.8},{"place":17,"model":"holotron-12b","company":"hcompany","family":"Holotron","version":"Holotron","score":80.5},{"place":18,"model":"holo2-8b","company":"hcompany","family":"Holo","version":"Holo2","score":80.2},{"place":19,"model":"molmoweb-8b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":78.2},{"place":20,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":77.72},{"place":21,"model":"molmoweb-4b","company":"allenai","family":"Molmo","version":"MolmoWeb","score":75.2},{"place":22,"model":"fara-7b","company":"microsoft","family":"Fara","version":"Fara","score":73.5},{"place":23,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":72.64},{"place":24,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":71.8},{"place":25,"model":"glm-4.1v-9b-thinking","company":"zai","family":"GLM","version":"GLM 4.1V","score":66.8},{"place":26,"model":"ui-tars-1.5-7b","company":"bytedance","family":"UI-TARS","version":"UI-TARS","score":66.4},{"place":27,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":65.4},{"place":28,"model":"llada-ui","company":"antgroup","family":"LLaDA","version":"LLaDA-UI","score":56.9},{"place":29,"model":"ui-venus-1.5-2b","company":"antgroup","family":"UI-Venus","version":"UI-Venus 1.5","score":56.4},{"place":30,"model":"holo1-7b","company":"hcompany","family":"Holo","version":"Holo1","score":55.4},{"place":31,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":54.89},{"place":32,"model":"step-gui-4b","company":"stepfun","family":"Step-GUI","version":"Step-GUI","score":47.8},{"place":33,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.9},{"place":34,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":46.6},{"place":35,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":45.2},{"place":36,"model":"nemotron-nano-12b-v2-vl","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":35.1},{"place":37,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":11},{"place":38,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":5.25}]},{"id":"webvoyager2","name":"WebVoyager2","topic":"Web agents","description":"Web navigation and interaction tasks for LLM agents (v2).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-4.5V","top_percent":84.4,"top_model_id":"glm-4.5v","top_generation":"GLM 4.5V","top_model_base":"GLM 4.5V","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":84.4},{"place":2,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":69},{"place":3,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":34.8}]},{"id":"webwalker-qa","name":"WebWalkerQA","topic":"Web agents","description":"WebWalker tasks evaluating autonomous browsing question answering performance.","url":"","leaderboard":"","github":"","paper":"","metric":"avg@3","stars":"","top_model":"SMTL-30B","top_percent":76.5,"top_model_id":"smtl-30b","top_generation":"SMTL","top_model_base":"SMTL-30B","top_model_family":"SMTL","top_company":"oppo","top_open_source":1,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"smtl-30b","company":"oppo","family":"SMTL","version":"SMTL","score":76.5},{"place":2,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":72.2},{"place":3,"model":"o3","company":"openai","family":"o3","version":"o3","score":71.7},{"place":4,"model":"marco-deepresearch-8b","company":"alibaba","family":"Marco","version":"Marco DeepResearch","score":69.6},{"place":5,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":68.1},{"place":6,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":65.6},{"place":7,"model":"zgcm-1-7b","company":"zhongguancun","family":"ZGCM","version":"ZGCM-1","score":63.09},{"place":8,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":63},{"place":9,"model":"webexplorer-8b","company":"hkust","family":"WebExplorer","version":"WebExplorer","score":62.7},{"place":10,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":62.1},{"place":11,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":61.7},{"place":12,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":61.2},{"place":13,"model":"mirothinker-v1.0-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker-v1.0","score":61},{"place":14,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":60.6},{"place":15,"model":"webdancer-32b","company":"tongyi","family":"WebDancer","version":"WebDancer","score":47.9}]},{"id":"wemath","name":"WeMath","topic":"Math reasoning","description":"Math reasoning benchmark spanning diverse curricula and difficulty levels.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.6-Plus","top_percent":89,"top_model_id":"qwen3.6-plus","top_generation":"Qwen3.6","top_model_base":"Qwen3.6 Plus","top_model_family":"Qwen","top_company":"qwen","top_open_source":0,"lower_is_better":false,"bench_models":49,"total_models":3854,"placements":[{"place":1,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":89},{"place":2,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.9},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":86.9},{"place":4,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":84.7},{"place":5,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84},{"place":6,"model":"exaone-4.5-33b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.5","score":79.1},{"place":7,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":79},{"place":8,"model":"zdtaichu5.0-9b","company":"taichu","family":"ZDTaichu","version":"ZDTaichu5.0","score":75.9},{"place":9,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.4},{"place":10,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":75.2},{"place":11,"model":"ovis2.6-30b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":75},{"place":12,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":74.9},{"place":13,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.8},{"place":14,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":74.8},{"place":15,"model":"step3-vl-10b","company":"stepfun","family":"Step","version":"Step3-VL","score":73.03},{"place":16,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":71.6},{"place":17,"model":"ovis2.6-80b-a3b","company":"alibaba","family":"Ovis","version":"Ovis 2.6","score":70.9},{"place":18,"model":"gpt-5-mini-high","company":"openai","family":"GPT","version":"GPT-5","score":70.3},{"place":19,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":70},{"place":20,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":70},{"place":21,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":69.8},{"place":22,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":68.8},{"place":23,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.1},{"place":24,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":65.1},{"place":25,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":63.8},{"place":26,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":62.5},{"place":27,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":60},{"place":28,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":59.8},{"place":29,"model":"minicpm-v-4.6-thinking","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":54.3},{"place":30,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":50.57},{"place":31,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":50.19},{"place":32,"model":"minicpm-v-4.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM V 4.6","score":48.8},{"place":33,"model":"bagel-7b-mot","company":"bytedance","family":"BAGEL","version":"BAGEL","score":45.8},{"place":34,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":43.9},{"place":35,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":42},{"place":36,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":41.1},{"place":37,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":40.5},{"place":38,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":37.9},{"place":39,"model":"qwen3.5-0.8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.3},{"place":40,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":33.33},{"place":41,"model":"qwen2.5-vl-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":33.3},{"place":42,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":33.1},{"place":43,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":32.1},{"place":44,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":30.19},{"place":45,"model":"llada2.0-uni","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":29.3},{"place":46,"model":"llada-o","company":"gsai-ml","family":"LLaDA","version":"LLaDA-o","score":29.3},{"place":47,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":26.19},{"place":48,"model":"llada-v","company":"gsai-ml","family":"LLaDA","version":"LLaDA-V","score":24.6},{"place":49,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":23.9},{"place":50,"model":"internvl-u","company":"opengvlab","family":"InternVL","version":"InternVL-U","score":18.3},{"place":51,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":12.7},{"place":52,"model":"lfm2.5-vl-1.6b","company":"liquidai","family":"LFM","version":"LFM2.5-VL","score":12.3},{"place":53,"model":"lumina-dimoo","company":"alpha-vllm","family":"Lumina","version":"Lumina-DiMOO","score":6.2}]},{"id":"weref-f1","name":"WeRef (F1)","topic":"Referring expressions","description":"Tencent WeRef referring object detection benchmark, F1 mean.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"f1","stars":"","top_model":"WeVisOne-VL-4B","top_percent":78.7,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":78.7},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":73.2},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":51.7},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.7},{"place":5,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":50.3},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":36.7}]},{"id":"weref-rejection","name":"WeRef (Rejection)","topic":"Referring expressions","description":"Rejection rate on non-existent referents in WeRef.","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"percent","stars":"","top_model":"WeVisOne-VL-4B","top_percent":96.4,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":false,"bench_models":6,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":96.4},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":92.9},{"place":3,"model":"locateanything-3b","company":"nvidia","family":"LocateAnything","version":"LocateAnything","score":73},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":70.7},{"place":5,"model":"rex-omni-3b","company":"idea-research","family":"Rex","version":"Rex-Omni","score":43.3},{"place":6,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":18.3}]},{"id":"werefmat-category-mad","name":"WeRefMat (Category) Matting (MAD)","topic":"Image matting","description":"WeRefMat (Category): category-prompted matting; mean absolute difference x10^3 (lower is better).","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"mad","stars":"","top_model":"WeVisOne-VL-4B","top_percent":16.4,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":16.4},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":17.7}]},{"id":"werefmat-referring-mad","name":"WeRefMat (Referring) Matting (MAD)","topic":"Image matting","description":"WeRefMat (Referring): referring-expression matting; mean absolute difference x10^3 (lower is better).","url":"https://github.com/Tencent/WeVisOne-VL","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2610.31329","metric":"mad","stars":"","top_model":"WeVisOne-VL-4B","top_percent":9.8,"top_model_id":"wevisone-vl-4b","top_generation":"WeVisOne-VL","top_model_base":"WeVisOne-VL-4B","top_model_family":"WeVisOne","top_company":"tencent","top_open_source":1,"lower_is_better":true,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"wevisone-vl-4b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":9.8},{"place":2,"model":"wevisone-vl-2b","company":"tencent","family":"WeVisOne","version":"WeVisOne-VL","score":15.8}]},{"id":"wgo-bench","name":"WGO Bench","topic":"Embodied manipulation","description":"WGO Bench: end-to-end robot manipulation event understanding (Elorian-reported).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Glimpse","top_percent":42.7,"top_model_id":"glimpse","top_generation":"Glimpse","top_model_base":"Glimpse","top_model_family":"Glimpse","top_company":"elorian","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"glimpse","company":"elorian","family":"Glimpse","version":"Glimpse","score":42.7},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":39.42},{"place":3,"model":"gpt-6.1-sol","company":"openai","family":"GPT","version":"GPT-6.1","score":38.91},{"place":4,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":33.99},{"place":5,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":12.34}]},{"id":"when2call","name":"When2Call","topic":"Tool calling","description":"NVIDIA's When2Call multiple-choice test set: choose whether to answer directly, call a tool, ask for more information, or say it cannot answer.","url":"https://huggingface.co/datasets/nvidia/When2Call","leaderboard":"https://artificialanalysis.ai/evaluations/when2call","github":"","paper":"https://arxiv.org/abs/2504.18851","metric":"percent","stars":"","top_model":"d1-ultra","top_percent":92.6,"top_model_id":"d1-ultra","top_generation":"d1","top_model_base":"d1-ultra","top_model_family":"d1","top_company":"liquidai","top_open_source":0,"lower_is_better":false,"bench_models":61,"total_models":3854,"placements":[{"place":1,"model":"d1-ultra","company":"liquidai","family":"d1","version":"d1","score":92.6},{"place":2,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":90.5},{"place":3,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":90.3},{"place":4,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":89.7},{"place":5,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":89.6},{"place":6,"model":"claude-opus-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":88.1},{"place":7,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":86.8},{"place":8,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":86.6},{"place":9,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":86.6},{"place":10,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":86.4},{"place":11,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":85.7},{"place":12,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":84.5},{"place":13,"model":"celeris-1-decision","company":"celeris","family":"Celeris","version":"Celeris-1","score":83.7},{"place":14,"model":"glide","company":"fastino","family":"GLiDE","version":"GLiDE","score":83.7},{"place":15,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":83.4},{"place":16,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":82.3},{"place":17,"model":"microsoft-decision-1","company":"microsoft","family":"Microsoft-Decision","version":"Microsoft-Decision-1","score":81.9},{"place":18,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":81.2},{"place":19,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":80.8},{"place":20,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":80.7},{"place":21,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":80.6},{"place":22,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":79.6},{"place":23,"model":"claude-haiku-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":79.4},{"place":24,"model":"mercury-decide","company":"inception","family":"Mercury","version":"Mercury Decide","score":79.3},{"place":25,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":79},{"place":26,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":78.6},{"place":27,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":78.5},{"place":28,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":78.2},{"place":29,"model":"claude-haiku-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":77.6},{"place":30,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":77.6},{"place":31,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":77.5},{"place":32,"model":"d1","company":"liquidai","family":"d1","version":"d1","score":77.4},{"place":33,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":77},{"place":34,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":76.9},{"place":35,"model":"pplx-decider-v1.1-27b","company":"perplexity","family":"pplx-decider","version":"v1.1","score":76.5},{"place":36,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":76.1},{"place":37,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":75.4},{"place":38,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":75.4},{"place":39,"model":"gpt-6-luna-decisions","company":"openai","family":"GPT","version":"GPT-6","score":74.1},{"place":40,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":72.7},{"place":41,"model":"claude-haiku-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":72.6},{"place":42,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":71},{"place":43,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":68.4},{"place":44,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":66.8},{"place":45,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":64.6},{"place":46,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":64.4},{"place":47,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":62.1},{"place":48,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":61.5},{"place":49,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":60.5},{"place":50,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":59.6},{"place":51,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":57.8},{"place":52,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":56.9},{"place":53,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":51.7},{"place":54,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":49.6},{"place":55,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":49.1},{"place":56,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":46.1},{"place":57,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":40.8},{"place":58,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":40.2},{"place":59,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":38.6},{"place":60,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":33.4},{"place":61,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":11.9}]},{"id":"when2call-multi-turn","name":"When2Call Multi-Turn","topic":"Tool calling","description":"Multi-turn variant of NVIDIA's When2Call: decide when to call a tool, answer, ask for information or refuse across a conversation.","url":"https://huggingface.co/datasets/nvidia/When2Call","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Nemotron-3.5-Bolt-E4B","top_percent":63.36,"top_model_id":"nemotron-3.5-bolt-e4b","top_generation":"Nemotron 3.5","top_model_base":"Nemotron-3.5 Bolt E4B","top_model_family":"Nemotron","top_company":"nvidia","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"nemotron-3.5-bolt-e4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":63.36},{"place":2,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":62.9},{"place":3,"model":"gemma-4-e4b-it-q4-k-m","company":"google","family":"Gemma","version":"Gemma 4","score":61.12},{"place":4,"model":"nemotron-3.5-bolt-e4b-4gb","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":60.5},{"place":5,"model":"qwen3.5-4b-q4-k-m","company":"qwen","family":"Qwen","version":"Qwen3.5","score":42.88},{"place":6,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":37.85},{"place":7,"model":"nemotron-3-nano-4b-q4-k-m","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":35.96},{"place":8,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":27.7}]},{"id":"where2place","name":"Where2Place","topic":"Embodied spatial understanding","description":"Spatial free-space pointing benchmark: predict points for placement locations described in language.","url":"https://arxiv.org/abs/2406.10721","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2406.10721","metric":"percent","stars":"","top_model":"ACE-Brain-0.6-9B","top_percent":81.44,"top_model_id":"ace-brain-0.6-9b","top_generation":"ACE-Brain-0.6","top_model_base":"ACE-Brain-0.6 9B","top_model_family":"ACE-Brain","top_company":"ace-robotics","top_open_source":1,"lower_is_better":false,"bench_models":29,"total_models":3854,"placements":[{"place":1,"model":"ace-brain-0.6-9b","company":"ace-robotics","family":"ACE-Brain","version":"ACE-Brain-0.6","score":81.44},{"place":2,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":76.9},{"place":3,"model":"embodied-r1.5-8b","company":"unknown","family":"Embodied-R1","version":"Embodied-R1.5","score":75},{"place":4,"model":"cosmos3-nano","company":"nvidia","family":"Cosmos","version":"Cosmos3","score":74.4},{"place":5,"model":"gemini-3.6-flash","company":"google","family":"Gemini","version":"Gemini 3.6","score":73.4},{"place":6,"model":"rynnbrain1.1-9b","company":"alibaba","family":"RynnBrain","version":"RynnBrain1.1","score":72.7},{"place":7,"model":"physbrain1.5-8b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":72.1},{"place":8,"model":"robobrain2.5-8b","company":"baai","family":"RoboBrain","version":"RoboBrain 2.5","score":72},{"place":9,"model":"gemini-4-argon","company":"google","family":"Gemini","version":"Gemini 4","score":71.2},{"place":10,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":71.1},{"place":11,"model":"physbrain1.5-2b","company":"deepcybo","family":"PhysBrain","version":"PhysBrain 1.5","score":70.7},{"place":12,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":69},{"place":13,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":66.44},{"place":14,"model":"hy-embodied-vlm-1.0","company":"tencent","family":"HY-Embodied","version":"Hy-Embodied 1.0","score":65.4},{"place":15,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.7},{"place":16,"model":"mimo-embodied-7b","company":"xiaomi","family":"MiMo","version":"MiMo-Embodied","score":63.9},{"place":17,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63},{"place":18,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":63},{"place":19,"model":"gemini-robotics-er-1.5-thinking","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":59},{"place":20,"model":"internvl3.5-8b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":57},{"place":21,"model":"ace-brain-0.5-8b","company":"unknown","family":"ACE-Brain","version":"ACE-Brain-0.5","score":56},{"place":22,"model":"molmo2-er","company":"allenai","family":"Molmo2","version":"Molmo2","score":54},{"place":23,"model":"internvl3.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 3.5","score":53},{"place":24,"model":"gemini-robotics-er-1.5","company":"google","family":"Gemini","version":"Gemini Robotics-ER 1.5","score":48},{"place":25,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.23},{"place":26,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":45.25},{"place":27,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":37},{"place":28,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":37},{"place":29,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":33.5},{"place":30,"model":"llava-onevision-7b","company":"microsoft","family":"LLaVA","version":"LLaVA OneVision","score":19},{"place":31,"model":"molmo2-4b","company":"allenai","family":"Molmo2","version":"Molmo2","score":18}]},{"id":"wide-search","name":"WideSearch","topic":"Web search","description":"Wide web search and QA benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5.6 Sol","top_percent":86.3,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":90,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":86.3},{"place":2,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":84.6},{"place":3,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":84},{"place":4,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":83.9},{"place":5,"model":"ling-3.1-flash","company":"antgroup","family":"Ling","version":"Ling 3.1","score":83.32},{"place":6,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":83.3},{"place":7,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":83.2},{"place":8,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":82.7},{"place":9,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":82.3},{"place":10,"model":"arex-base","company":"baai","family":"AREX","version":"AREX","score":82},{"place":11,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":81.9},{"place":12,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":81.9},{"place":13,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":81.9},{"place":14,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":81.83},{"place":15,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":81.8},{"place":16,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":81.2},{"place":17,"model":"xyz-aquila-pro","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":81.2},{"place":18,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":81},{"place":19,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":80.81},{"place":20,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.8},{"place":21,"model":"ornith-1.5-397b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":80.8},{"place":22,"model":"xyz-aquila-mini","company":"xyzlab","family":"XYZ-Aquila","version":"XYZ-Aquila","score":80.8},{"place":23,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":80.8},{"place":24,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80.5},{"place":25,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":80.24},{"place":26,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":80},{"place":27,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":79.6},{"place":28,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":79.5},{"place":29,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":79},{"place":30,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":78.9},{"place":31,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":78.86},{"place":32,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":78},{"place":33,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":77.6},{"place":34,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":77.5},{"place":35,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.5},{"place":36,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":77.3},{"place":37,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":77.2},{"place":38,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":76.8},{"place":39,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.4},{"place":40,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":76.4},{"place":41,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":76.4},{"place":42,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":76.4},{"place":43,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":76.2},{"place":44,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":76.1},{"place":45,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.7},{"place":46,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":75.7},{"place":47,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":75.6},{"place":48,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":75.2},{"place":49,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":75.2},{"place":50,"model":"ornith-1.0-397b","company":"ornith","family":"Ornith","version":"1.0","score":75.2},{"place":51,"model":"ornith-1.5-122b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":75.2},{"place":52,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":74.7},{"place":53,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":74.5},{"place":54,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.4},{"place":55,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":74.3},{"place":56,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.3},{"place":57,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":74.3},{"place":58,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":74},{"place":59,"model":"ling-3.0-flash","company":"antgroup","family":"Ling","version":"Ling 3.0","score":73.6},{"place":60,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":73.5},{"place":61,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":73.3},{"place":62,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":73},{"place":63,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":72.9},{"place":64,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":72.7},{"place":65,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":72.7},{"place":66,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":72.3},{"place":67,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":71.8},{"place":68,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":71.7},{"place":69,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":70.3},{"place":70,"model":"gpt-5.4-mini","company":"openai","family":"GPT","version":"GPT-5.4","score":70.2},{"place":71,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":70.2},{"place":72,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":69.8},{"place":73,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":69.5},{"place":74,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":69.2},{"place":75,"model":"arex-turbo","company":"baai","family":"AREX","version":"AREX","score":68.5},{"place":76,"model":"beam","company":"reflection","family":"Beam","version":"Beam 1.0","score":68.5},{"place":77,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68},{"place":78,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":67.8},{"place":79,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":67.8},{"place":80,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.4},{"place":81,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":66.4},{"place":82,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":65.8},{"place":83,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":65.7},{"place":84,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":64},{"place":85,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":63.8},{"place":86,"model":"ornith-1.0-35b","company":"ornith","family":"Ornith","version":"1.0","score":63.4},{"place":87,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":62.6},{"place":88,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":62.2},{"place":89,"model":"ring-2.6-1t-xhigh","company":"antgroup","family":"Ring","version":"Ring 2.6","score":62.2},{"place":90,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":62},{"place":91,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":61.2},{"place":92,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61.1},{"place":93,"model":"quest-35b","company":"osunlp","family":"QUEST","version":"QUEST","score":60.6},{"place":94,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":60.5},{"place":95,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":60.1},{"place":96,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":59.5},{"place":97,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":59.1},{"place":98,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":57.9},{"place":99,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.1},{"place":100,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":57},{"place":101,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":56.8},{"place":102,"model":"ornith-1.0-9b","company":"ornith","family":"Ornith","version":"1.0","score":55.8},{"place":103,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":54.2},{"place":104,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":53.9},{"place":105,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":53.6},{"place":106,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.6},{"place":107,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":47.2},{"place":108,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":40.4},{"place":109,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":38.3},{"place":110,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":35.2},{"place":111,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":32.5},{"place":112,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":19.5}]},{"id":"wikiwebfacts","name":"WikiWebFacts","topic":"Russian factual knowledge","description":"Yandex 5-shot benchmark of factual knowledge in Russian.","url":"https://huggingface.co/datasets/yandex/WikiWebFacts","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"AliceAI-Foundation-80B-A3B-Base","top_percent":86.5,"top_model_id":"aliceai-foundation-80b-a3b-base","top_generation":"AliceAI-Foundation","top_model_base":"AliceAI Foundation 80B A3B","top_model_family":"AliceAI","top_company":"yandex","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"aliceai-foundation-80b-a3b-base","company":"yandex","family":"AliceAI","version":"AliceAI-Foundation","score":86.5},{"place":2,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":83.2},{"place":3,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":72.8},{"place":4,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":70.2},{"place":5,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":62.4}]},{"id":"wild-jailbreak","name":"Wild-Jailbreak","topic":"Safety / jailbreak","description":"Adversarial jailbreak benchmark evaluating refusal robustness.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-OSS 120B (high)","top_percent":98.2,"top_model_id":"gpt-oss-120b-high","top_generation":"GPT-OSS","top_model_base":"GPT-OSS 120B","top_model_family":"GPT","top_company":"openai","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":98.2},{"place":2,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":96.29},{"place":3,"model":"semif","company":"theoleecj","family":"SemIf","version":"SemIf","score":92.53},{"place":4,"model":"jevk5","company":"alibiserikbay","family":"JevK5","version":"JevK5","score":90.45},{"place":5,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":89.9},{"place":6,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":89.86},{"place":7,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.5},{"place":8,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":79.1},{"place":9,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":78.33},{"place":10,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":64.48},{"place":11,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":62.8},{"place":12,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":14.84}]},{"id":"wildbench-v2","name":"WildBench V2","topic":"Instruction following","description":"WildBench V2 human preference benchmark for instruction following and helpfulness.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Ministral 3 14B Instruct","top_percent":68.5,"top_model_id":"ministral-3-14b-instruct","top_generation":"Ministral 3","top_model_base":"Ministral 3 14B","top_model_family":"Ministral","top_company":"mistral","top_open_source":1,"lower_is_better":false,"bench_models":20,"total_models":3854,"placements":[{"place":1,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":68.5},{"place":2,"model":"ministral-3-8b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":66.8},{"place":3,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":66.3},{"place":4,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":65.33},{"place":5,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":65.1},{"place":6,"model":"yi-lightning","company":"01ai","family":"Yi","version":"Yi","score":65.1},{"place":7,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":63.2},{"place":8,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.9},{"place":9,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":59.3},{"place":10,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":57.9},{"place":11,"model":"mistral-large-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":57.4},{"place":12,"model":"ministral-3-3b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":56.8},{"place":13,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":56.8},{"place":14,"model":"mistral-small-3.1-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.1","score":55.6},{"place":15,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":55.3},{"place":16,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":54.7},{"place":17,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":51.6},{"place":18,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":49.1},{"place":19,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":49},{"place":20,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.2}]},{"id":"wildclawbench","name":"WildClawBench","topic":"Agentic tasks","description":"Agentic benchmark of in-the-wild tasks run in OpenClaw-style agent scaffolds.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.8","top_percent":68,"top_model_id":"claude-opus-4.8","top_generation":"Claude 4.8","top_model_base":"Claude Opus 4.8","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":53,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":68},{"place":2,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":67.2},{"place":3,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":67},{"place":4,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":66},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":65.6},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":63.2},{"place":7,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":62.8},{"place":8,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":62.2},{"place":9,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":61.7},{"place":10,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":61.7},{"place":11,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":61.1},{"place":12,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":60.4},{"place":13,"model":"gpt-5.6-terra","company":"openai","family":"GPT","version":"GPT-5.6","score":60},{"place":14,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":59.2},{"place":15,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":58.4},{"place":16,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.2},{"place":17,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":56.4},{"place":18,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":55},{"place":19,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":54.42},{"place":20,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":54.2},{"place":21,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":53.6},{"place":22,"model":"nex-n2-pro","company":"nex-agi","family":"Nex","version":"N2","score":53.5},{"place":23,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":52.3},{"place":24,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":52.14},{"place":25,"model":"k2-horizon-375b-a23b","company":"mbzuai","family":"K2","version":"K2-Horizon","score":50.9},{"place":26,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":50.5},{"place":27,"model":"gpt-5.6-luna","company":"openai","family":"GPT","version":"GPT-5.6","score":50.4},{"place":28,"model":"occamy-1.0","company":"accio","family":"Occamy","version":"Occamy-1.0","score":49.16},{"place":29,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":48.7},{"place":30,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":48.2},{"place":31,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":47.7},{"place":32,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":47.6},{"place":33,"model":"openpangu-2.0-pro-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":46.5},{"place":34,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":46.4},{"place":35,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":46.2},{"place":36,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":46},{"place":37,"model":"ornith-1.5-35b-a3b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":45.91},{"place":38,"model":"hy3-preview","company":"tencent","family":"HY","version":"Hy3","score":45.3},{"place":39,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":43.7},{"place":40,"model":"deepseek-v4-flash-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":43.5},{"place":41,"model":"qwen3.6-27b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":43.2},{"place":42,"model":"openpangu-2.0-pro","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":43.1},{"place":43,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":41.5},{"place":44,"model":"openpangu-2.0-flash-thinking","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":41.5},{"place":45,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":40.4},{"place":46,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":40},{"place":47,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":39.5},{"place":48,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":37.6},{"place":49,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":37.3},{"place":50,"model":"openpangu-2.0-flash","company":"huawei","family":"openPangu","version":"openPangu-2.0","score":35},{"place":51,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":34.2},{"place":52,"model":"hy-2.0-thinking","company":"tencent","family":"HY","version":"HY 2.0","score":33.7},{"place":53,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":32.87},{"place":54,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":30.73},{"place":55,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":30.31},{"place":56,"model":"minicpm5-2b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 5","score":23.9},{"place":57,"model":"granite-4.2-3b","company":"IBM","family":"Granite","version":"Granite 4.2","score":20},{"place":58,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":17},{"place":59,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":14.3},{"place":60,"model":"lfm2.5-2.6b","company":"liquidai","family":"LFM","version":"LFM2.5","score":10.2},{"place":61,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9.2},{"place":62,"model":"gemma-4-e2b-it","company":"google","family":"Gemma","version":"Gemma 4","score":8.9},{"place":63,"model":"nemotron-3-nano-4b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":8.9},{"place":64,"model":"lfm2.5-8b-a1b","company":"liquidai","family":"LFM","version":"LFM2.5","score":4.5}]},{"id":"wildguardtest","name":"WildGuardTest","topic":"Safety","description":"WildGuardTest safety benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"d1-ultra","top_percent":95.4,"top_model_id":"d1-ultra","top_generation":"d1","top_model_base":"d1-ultra","top_model_family":"d1","top_company":"liquidai","top_open_source":0,"lower_is_better":false,"bench_models":32,"total_models":3854,"placements":[{"place":1,"model":"d1-ultra","company":"liquidai","family":"d1","version":"d1","score":95.4},{"place":2,"model":"glide","company":"fastino","family":"GLiDE","version":"GLiDE","score":95.1},{"place":3,"model":"claude-haiku-5.5-high","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.8},{"place":4,"model":"pplx-decider-v1.1-27b","company":"perplexity","family":"pplx-decider","version":"v1.1","score":93.8},{"place":5,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":93.6},{"place":6,"model":"claude-opus-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.5},{"place":7,"model":"claude-opus-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.5},{"place":8,"model":"claude-haiku-5.5-medium","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.3},{"place":9,"model":"celeris-1-decision","company":"celeris","family":"Celeris","version":"Celeris-1","score":93.3},{"place":10,"model":"claude-haiku-5.5-max","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.2},{"place":11,"model":"claude-haiku-5.5-xhigh","company":"anthropic","family":"Claude","version":"Claude 5.5","score":93.1},{"place":12,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":93.1},{"place":13,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":92.8},{"place":14,"model":"claude-haiku-5.5-low","company":"anthropic","family":"Claude","version":"Claude 5.5","score":92.6},{"place":15,"model":"gpt-6.1-sol-max","company":"openai","family":"GPT","version":"GPT-6.1","score":92.5},{"place":16,"model":"gpt-6.1-sol-low","company":"openai","family":"GPT","version":"GPT-6.1","score":92},{"place":17,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":90.9},{"place":18,"model":"d1","company":"liquidai","family":"d1","version":"d1","score":90.9},{"place":19,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":90.7},{"place":20,"model":"gpt-6-luna-max","company":"openai","family":"GPT","version":"GPT-6","score":90.5},{"place":21,"model":"gpt-6-luna-medium","company":"openai","family":"GPT","version":"GPT-6","score":89.8},{"place":22,"model":"gpt-6-luna-high","company":"openai","family":"GPT","version":"GPT-6","score":88.9},{"place":23,"model":"gpt-6-luna-low","company":"openai","family":"GPT","version":"GPT-6","score":88.5},{"place":24,"model":"microsoft-decision-1","company":"microsoft","family":"Microsoft-Decision","version":"Microsoft-Decision-1","score":88.2},{"place":25,"model":"mercury-decide","company":"inception","family":"Mercury","version":"Mercury Decide","score":88},{"place":26,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":87.2},{"place":27,"model":"gpt-6-luna","company":"openai","family":"GPT","version":"GPT-6","score":87.1},{"place":28,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":86.8},{"place":29,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":85},{"place":30,"model":"gpt-6-luna-decisions","company":"openai","family":"GPT","version":"GPT-6","score":82.8},{"place":31,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":78.1},{"place":32,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":73.9}]},{"id":"wildspeech-bench","name":"WildSpeech-Bench","topic":"Spoken dialogue","description":"WildSpeech-Bench: end-to-end speech-in/speech-out evaluation on real-world spoken queries (%).","url":"https://github.com/Tencent/WildSpeech-Bench","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":77.7,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":10,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":77.7},{"place":2,"model":"stepaudio-3-realtime","company":"stepfun","family":"Step","version":"StepAudio 3","score":77.1},{"place":3,"model":"gemini-3.8-flash","company":"google","family":"Gemini","version":"Gemini 3.8","score":76.4},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":76.3},{"place":5,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":75.7},{"place":6,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":75.4},{"place":7,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":74.5},{"place":8,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":74.4},{"place":9,"model":"qwen3.8-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.8 Omni","score":74.3},{"place":10,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":73.9},{"place":11,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":73.4},{"place":12,"model":"qwen3.8-omni-flash-realtime","company":"qwen","family":"Qwen","version":"Qwen3.8","score":72.5},{"place":13,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":72.2}]},{"id":"wildvision","name":"WildVision-Bench","topic":"Multimodal chat","description":"In-the-wild multimodal chat benchmark judged against reference model (WildVision Arena).","url":"https://huggingface.co/spaces/WildVision/vision-arena","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 2.5 Pro","top_percent":90.1,"top_model_id":"gemini-2.5-pro","top_generation":"Gemini 2.5","top_model_base":"Gemini 2.5 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":90.1},{"place":2,"model":"kanana-1.5-o-9.8b-instruct-2602","company":"kakao","family":"Kanana","version":"Kanana-1.5-o","score":84.4},{"place":3,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":80.6},{"place":4,"model":"gpt-4v","company":"openai","family":"GPT","version":"GPT-4V","score":71.8},{"place":5,"model":"internvl2.5-78b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":71.4},{"place":6,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":67.4},{"place":7,"model":"internvl2.5-38b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":66.4},{"place":8,"model":"internvl2-llama-3-76b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":65.8},{"place":9,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":65.2},{"place":10,"model":"qwen2.5-omni-7b","company":"qwen","family":"Qwen","version":"Qwen2.5 Omni","score":64.2},{"place":11,"model":"internvl2-40b","company":"opengvlab","family":"Intern","version":"InternVL2","score":63.2},{"place":12,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":62.2},{"place":13,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":62},{"place":14,"model":"internvl-chat-v1.5","company":"opengvlab","family":"Intern","version":"InternVL-Chat-V1.5","score":56.6},{"place":15,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":54.4},{"place":16,"model":"internvl2.5-4b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":49.4},{"place":17,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":44.2},{"place":18,"model":"internvl2-4b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":44.2},{"place":19,"model":"internvl2.5-1b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":43.4},{"place":20,"model":"hyperclovax-seed-omni-8b","company":"naver","family":"HyperCLOVA X","version":"HyperCLOVA X","score":37.6},{"place":21,"model":"minicpm-o-2.6","company":"openbmb","family":"MiniCPM","version":"MiniCPM-o 2.6","score":36},{"place":22,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":31.8},{"place":23,"model":"internvl2-1b","company":"opengvlab","family":"Intern","version":"InternVL2","score":17.8}]},{"id":"windows-agent-arena","name":"Windows Agent Arena","topic":"GUI agents","description":"Windows OS computer-use agent benchmark (WAA), task success rate.","url":"https://microsoft.github.io/WindowsAgentArena/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"EvoCUA-32B-20260105","top_percent":56.48,"top_model_id":"evocua-32b-20260105","top_generation":"EvoCUA-20260105","top_model_base":"EvoCUA","top_model_family":"EvoCUA","top_company":"meituan","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"evocua-32b-20260105","company":"meituan","family":"EvoCUA","version":"EvoCUA-20260105","score":56.48},{"place":2,"model":"ui-tars-2","company":"bytedance","family":"UI-TARS","version":"UI-TARS-2","score":50.6},{"place":3,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":42.9},{"place":4,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":30.9}]},{"id":"winogender","name":"Winogender","topic":"Gender bias (coreference)","description":"Coreference resolution dataset for measuring gender bias.","url":"","leaderboard":"","github":"https://github.com/rudinger/winogender-schemas","paper":"","metric":"percent","stars":"","top_model":"Llama 3.3 70B Instruct","top_percent":84.3,"top_model_id":"llama-3.3-70b-instruct","top_generation":"Llama 3.3","top_model_base":"Llama 3.3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":84.3},{"place":2,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":67.9},{"place":3,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":67.9},{"place":4,"model":"tfree-hat-pretrained-7b-base","company":"alephalpha","family":"TFree","version":"TFree Hat","score":67.1}]},{"id":"winogrande","name":"WinoGrande","topic":"Coreference reasoning","description":"Large-scale adversarial Winograd Schema-style pronoun resolution.","url":"https://github.com/allenai/winogrande","leaderboard":"","github":"","paper":"","metric":"percent","stars":"99","top_model":"Clef-Flash","top_percent":97.5,"top_model_id":"clef-flash","top_generation":"Clef","top_model_base":"Clef","top_model_family":"Clef","top_company":"cloudflare","top_open_source":1,"lower_is_better":false,"bench_models":325,"total_models":3854,"placements":[{"place":1,"model":"clef-flash","company":"cloudflare","family":"Clef","version":"Clef","score":97.5},{"place":2,"model":"clef-omni","company":"cloudflare","family":"Clef","version":"Clef","score":96.7},{"place":3,"model":"vllm-sr-d3","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":95.4},{"place":4,"model":"pplx-decider-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":94},{"place":5,"model":"clef","company":"cloudflare","family":"Clef","version":"Clef","score":93.5},{"place":6,"model":"vllm-sr-d3-flash","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":92.2},{"place":7,"model":"jev-1.13","company":"typesafe","family":"Jev","version":"Jev 1.13","score":92},{"place":8,"model":"autotrust-jev-35b","company":"autotrust","family":"JEV","version":"JEV-35B","score":92},{"place":9,"model":"jev-1.14","company":"typesafe","family":"Jev","version":"Jev 1.14","score":91.1},{"place":10,"model":"autotrust-gev-26b-decide","company":"autotrust","family":"GEV","version":"GEV-26B-Decide","score":91},{"place":11,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":90.3},{"place":12,"model":"vllm-sr-d3-mini","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":90.2},{"place":13,"model":"granite-3.3-8b-base","company":"IBM","family":"Granite","version":"Granite 3.3","score":89.4},{"place":14,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":88.8},{"place":15,"model":"hunyuan-large","company":"tencent","family":"Hunyuan","version":"Hunyuan-Large","score":88.7},{"place":16,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":88.6},{"place":17,"model":"pplx-decider-flash-v1.2","company":"perplexity","family":"pplx-decider","version":"v1.2","score":88.6},{"place":18,"model":"internvl2.5-26b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":87.9},{"place":19,"model":"vllm-sr-decision-2.0-lux-9b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":87.5},{"place":20,"model":"olmo-2-1124-7b","company":"allenai","family":"OLMo","version":"OLMo 2","score":87.4},{"place":21,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":87.3},{"place":22,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":86.7},{"place":23,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":86.7},{"place":24,"model":"mimo-7b-base","company":"xiaomi","family":"MiMo","version":"MiMo 7B","score":86.5},{"place":25,"model":"instella-moe-16b-a3b-base","company":"amd","family":"Instella","version":"Instella-MoE","score":86.5},{"place":26,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":86.4},{"place":27,"model":"bespoke-nimble-9b-v3","company":"bespokelabs","family":"Bespoke-Nimble","version":"v3","score":86.4},{"place":28,"model":"internlm2_5-20b-chat","company":"internlm","family":"Intern","version":"InternLM2.5","score":86.4},{"place":29,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":86.3},{"place":30,"model":"olmo-hybrid-7b","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":86.2},{"place":31,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":86},{"place":32,"model":"glide-no-thinking","company":"fastino","family":"GLiDE","version":"GLiDE","score":86},{"place":33,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":85.9},{"place":34,"model":"deepseek-v3.1-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":85.9},{"place":35,"model":"internvl2-8b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":85.9},{"place":36,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":85.8},{"place":37,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":85.7},{"place":38,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":85.7},{"place":39,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.6},{"place":40,"model":"mimo-v2.5-pro-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":85.6},{"place":41,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":85.6},{"place":42,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":85.6},{"place":43,"model":"vllm-sr-decision-2.0-vega-27b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":85.5},{"place":44,"model":"command-r-plus-08-2024","company":"cohere","family":"Command","version":"Command","score":85.4},{"place":45,"model":"llama3.0-70b","company":"meta","family":"Llama 3.0","version":"Llama 3.0","score":85.3},{"place":46,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":85.3},{"place":47,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.3},{"place":48,"model":"llama-3-70b-base","company":"meta","family":"Llama","version":"Llama 3","score":85.3},{"place":49,"model":"glm-4.5-base","company":"zai","family":"GLM","version":"GLM 4.5","score":85.24},{"place":50,"model":"llama-3.1-405b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":85.2},{"place":51,"model":"internlm2-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":85.2},{"place":52,"model":"qwen2-72b","company":"qwen","family":"Qwen","version":"Qwen2","score":85.1},{"place":53,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":85},{"place":54,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":84.9},{"place":55,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":84.9},{"place":56,"model":"deepseek-v3-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":84.9},{"place":57,"model":"yi-1.5-34b","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":84.9},{"place":58,"model":"internlm2.5-7b-chat","company":"internlm","family":"Intern","version":"Internlm2.5","score":84.9},{"place":59,"model":"deepseek-v2-lite","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":84.8},{"place":60,"model":"deepseek-v2","company":"deepseek","family":"DeepSeek","version":"DeepSeek-V2","score":84.8},{"place":61,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":84.7},{"place":62,"model":"mimo-v2.5-base","company":"xiaomi","family":"MiMo","version":"MiMo V2.5","score":84.7},{"place":63,"model":"internlm2-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":84.7},{"place":64,"model":"qwen3.5-4b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":84.6},{"place":65,"model":"smollm3-3b-base","company":"huggingface","family":"SmolLM","version":"SmolLM3","score":84.4},{"place":66,"model":"kimi-k2-base","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":84.21},{"place":67,"model":"olmoe-1b-7b-base","company":"allenai","family":"OLMoE","version":"OLMoE","score":84.1},{"place":68,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":83.9},{"place":69,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":83.9},{"place":70,"model":"glm-4.5-air-base","company":"zai","family":"GLM","version":"GLM 4.5","score":83.82},{"place":71,"model":"mimo-v2-flash-base","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":83.8},{"place":72,"model":"mixtral-8x22b","company":"mistral","family":"Mixtral","version":"Mixtral","score":83.7},{"place":73,"model":"deepseek-coder-v2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek-Coder-V2","score":83.7},{"place":74,"model":"solar-10.7b-instruct-v1.0","company":"upstage","family":"Solar","version":"Solar Mini","score":83.58},{"place":75,"model":"qwen1.5-110b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83.5},{"place":76,"model":"internvl2.5-8b","company":"opengvlab","family":"Intern","version":"InternVL2.5","score":83.5},{"place":77,"model":"deepseek-v3.2-exp-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":83.43},{"place":78,"model":"llama-3.1-70b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":83.3},{"place":79,"model":"pplx-decider-v1-27b","company":"perplexity","family":"pplx-decider","version":"v1","score":83.3},{"place":80,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":83.2},{"place":81,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":83},{"place":82,"model":"vllm-sr-decision-2.0-nox-4b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":83},{"place":83,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":83},{"place":84,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":82.6},{"place":85,"model":"autotrust-jev-27b","company":"autotrust","family":"JEV","version":"JEV-27B","score":82.6},{"place":86,"model":"jamba-v0.1","company":"ai21","family":"Jamba","version":"Jamba","score":82.5},{"place":87,"model":"qwen1.5-72b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":82.4},{"place":88,"model":"qwen-2.5-72b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82.3},{"place":89,"model":"mistral-large-3-base","company":"mistral","family":"Mistral","version":"Mistral 3","score":82.08},{"place":90,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":82},{"place":91,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":81.9},{"place":92,"model":"command-r-08-2024","company":"cohere","family":"Command","version":"Command","score":81.5},{"place":93,"model":"kimi-linear-base","company":"moonshotai","family":"Kimi","version":"Kimi Linear","score":81.5},{"place":94,"model":"deepseek-v4-pro-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":81.5},{"place":95,"model":"qwen1.5-32b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":81.5},{"place":96,"model":"trinity-large-truebase","company":"arcee","family":"Trinity","version":"Trinity Large","score":81.45},{"place":97,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":81.2},{"place":98,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":81.1},{"place":99,"model":"qwen2.5-14b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81},{"place":100,"model":"motif-3-base","company":"motif","family":"Motif","version":"Motif 3","score":80.9},{"place":101,"model":"trinity-large-base","company":"arcee","family":"Trinity","version":"Trinity Large","score":80.82},{"place":102,"model":"qwen2.5-coder-32b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":80.8},{"place":103,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":80.4},{"place":104,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":80.2},{"place":105,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":79.95},{"place":106,"model":"vllm-sr-d3-nano","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":79.9},{"place":107,"model":"internvl2-26b","company":"opengvlab","family":"Intern","version":"InternVL 2","score":79.9},{"place":108,"model":"llama-3.1-70b","company":"meta","family":"Llama","version":"Llama 3.1","score":79.8},{"place":109,"model":"deepseek-llm-67b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":79.8},{"place":110,"model":"bielik-11b-v2.5-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.5","score":79.72},{"place":111,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.64},{"place":112,"model":"motif-2-12.7b-base","company":"motif","family":"Motif","version":"Motif 2","score":79.6},{"place":113,"model":"deepseek-v4-flash-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":79.5},{"place":114,"model":"qwen2.57b-a14b","company":"qwen","family":"Qwen","version":"Qwen2","score":79.5},{"place":115,"model":"gemma-2-9b","company":"google","family":"Gemma","version":"Gemma 2","score":79.5},{"place":116,"model":"nemotron-3-ultra-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.32},{"place":117,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":79.3},{"place":118,"model":"qwen3.5-35b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":79.24},{"place":119,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":79.16},{"place":120,"model":"step-3.5-flash-base","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":79.1},{"place":121,"model":"gemma-4-26b-a4b","company":"google","family":"Gemma","version":"Gemma 4","score":79.08},{"place":122,"model":"nemotron-3.5-super-vl-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":79.08},{"place":123,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":79},{"place":124,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":79},{"place":125,"model":"nemotron-3-super-120b-a12b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":78.93},{"place":126,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":78.9},{"place":127,"model":"deepseek-v3.2-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":78.9},{"place":128,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":78.8},{"place":129,"model":"bielik-11b-v2.6-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.6","score":78.77},{"place":130,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":78.6},{"place":131,"model":"bielik-11b-v3.0","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":78.53},{"place":132,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":78.45},{"place":133,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":78.45},{"place":134,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":78.4},{"place":135,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":78.37},{"place":136,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":78.37},{"place":137,"model":"openchat-3.5-0106-gemma","company":"openchat","family":"OpenChat","version":"OpenChat 3.5 0106","score":78.3},{"place":138,"model":"qwen3.5-2b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.3},{"place":139,"model":"mistral-7b-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":78.22},{"place":140,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":78},{"place":141,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":78},{"place":142,"model":"bielik-11b-v2","company":"SpeakLeash","family":"Bielik","version":"Bielik v2","score":77.82},{"place":143,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.74},{"place":144,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":77.7},{"place":145,"model":"llama-3-8b-base","company":"meta","family":"Llama","version":"Llama 3","score":77.4},{"place":146,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.3},{"place":147,"model":"mixtral-8x7b","company":"mistral","family":"Mixtral","version":"Mixtral","score":77.2},{"place":148,"model":"bielik-11b-v3.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3.0","score":77.19},{"place":149,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":77.19},{"place":150,"model":"qwen1.5-32b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":77.19},{"place":151,"model":"llama-3.1-8b","company":"meta","family":"Llama","version":"Llama 3.1","score":77.11},{"place":152,"model":"palm-62b","company":"google","family":"PaLM","version":"PaLM","score":77},{"place":153,"model":"palm-cont-62b","company":"google","family":"PaLM","version":"PaLM","score":77},{"place":154,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":77},{"place":155,"model":"qwen2-7b","company":"qwen","family":"Qwen","version":"Qwen2","score":77},{"place":156,"model":"falcon-40b","company":"tii","family":"Falcon","version":"Falcon","score":76.9},{"place":157,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":76.8},{"place":158,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":76.8},{"place":159,"model":"qwen2.5-coder-14b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":76.8},{"place":160,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":76.48},{"place":161,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":76.4},{"place":162,"model":"bielik-11b-v2.0-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.0","score":76.32},{"place":163,"model":"bielik-11b-v2.3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.3","score":76.24},{"place":164,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":76.2},{"place":165,"model":"internlm2-base-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":76.2},{"place":166,"model":"nemotron-3-nano-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":76.09},{"place":167,"model":"nemotron-labs-twotower-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron-Labs","score":76.09},{"place":168,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":76},{"place":169,"model":"deepseek-llm-67b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":76},{"place":170,"model":"trinity-mini-base","company":"arcee","family":"Trinity","version":"Trinity","score":75.9},{"place":171,"model":"qwen2.5-7b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.9},{"place":172,"model":"ouro-2.6b","company":"bytedance","family":"Ouro","version":"Ouro","score":75.85},{"place":173,"model":"step-3.5-flash-base-midtrain","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":75.8},{"place":174,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":75.8},{"place":175,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":75.7},{"place":176,"model":"bespoke-nimble-9b-v2","company":"bespokelabs","family":"Bespoke-Nimble","version":"v2","score":75.6},{"place":177,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":75.3},{"place":178,"model":"bielik-11b-v2.2-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.2","score":75.3},{"place":179,"model":"mistral-7b-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":75.3},{"place":180,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":75.1},{"place":181,"model":"bielik-11b-v2.1-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v2.1","score":75.06},{"place":182,"model":"internlm2-chat-20b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":75},{"place":183,"model":"chinchilla-70b","company":"google","family":"Chinchilla","version":"Chinchilla","score":74.9},{"place":184,"model":"internlm2-chat-20b","company":"internlm","family":"InternLM","version":"InternLM2","score":74.8},{"place":185,"model":"moonlight-base","company":"moonshotai","family":"Moonlight","version":"Moonlight","score":74.6},{"place":186,"model":"internlm2-base-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":74.6},{"place":187,"model":"solar-10.7b-v1.0","company":"upstage","family":"SOLAR","version":"SOLAR","score":74.6},{"place":188,"model":"meta-llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":74.51},{"place":189,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":74.4},{"place":190,"model":"autotrust-jev-9b","company":"autotrust","family":"JEV","version":"JEV-9B","score":74.4},{"place":191,"model":"phi-2","company":"microsoft","family":"Phi","version":"Phi","score":74.4},{"place":192,"model":"gemma-3-12b","company":"google","family":"Gemma","version":"Gemma 3","score":74.3},{"place":193,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":74.2},{"place":194,"model":"mistral-7b","company":"mistral","family":"Mistral","version":"Mistral","score":74},{"place":195,"model":"mistral-7b-instruct-v0.1","company":"mistral","family":"Mistral","version":"Mistral v0.1","score":73.72},{"place":196,"model":"diffusiongemma-jev","company":"unknown","family":"DiffusionGemma Jev","version":"DiffusionGemma Jev","score":73.6},{"place":197,"model":"gemma-7b","company":"google","family":"gemma-7b","version":"gemma-7b","score":73.6},{"place":198,"model":"qwen1.5-14b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":73.48},{"place":199,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":73.4},{"place":200,"model":"kev-9b","company":"jaredpalmer","family":"Kev","version":"Kev","score":73.2},{"place":201,"model":"qwen1.5-14b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":73.09},{"place":202,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":73},{"place":203,"model":"yi-9b","company":"01ai","family":"Yi","version":"Yi","score":73},{"place":204,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":72.9},{"place":205,"model":"deepseek-coder-v2-lite-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":72.9},{"place":206,"model":"qwen2.5-coder-7b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":72.9},{"place":207,"model":"aquila2-34b","company":"baai","family":"Aquila","version":"Aquila2","score":72.85},{"place":208,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":72.8},{"place":209,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":72.8},{"place":210,"model":"phi-3-medium-4k-instruct","company":"microsoft","family":"Phi","version":"Phi 3","score":72.69},{"place":211,"model":"hrm-text-1b","company":"sapient","family":"HRM","version":"HRM-Text","score":72.4},{"place":212,"model":"llama-3-8b","company":"meta","family":"Llama","version":"Llama 3","score":72.38},{"place":213,"model":"gemma-2-7b","company":"google","family":"Gemma","version":"Gemma 2","score":72.3},{"place":214,"model":"ouro-1.4b","company":"bytedance","family":"Ouro","version":"Ouro","score":72.3},{"place":215,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":72.3},{"place":216,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":72.2},{"place":217,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":72.1},{"place":218,"model":"open-llama-13b","company":"openlm-research","family":"OpenLLaMA","version":"OpenLLaMA","score":72},{"place":219,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":71.9},{"place":220,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":71.82},{"place":221,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":71.6},{"place":222,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":71.5},{"place":223,"model":"bielik-4.5b-v3","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":71.35},{"place":224,"model":"llama-tfree-hat-pretrained-7b-dpo","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":71.3},{"place":225,"model":"qwen1.5-7b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":71.3},{"place":226,"model":"yi-6b","company":"01ai","family":"Yi","version":"Yi","score":71.3},{"place":227,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":71.19},{"place":228,"model":"bielik-4.5b-v3-instruct","company":"SpeakLeash","family":"Bielik","version":"Bielik v3","score":71.19},{"place":229,"model":"xverse-13b","company":"xverse","family":"XVERSE","version":"XVERSE","score":71.1},{"place":230,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":71.1},{"place":231,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":71.07},{"place":232,"model":"mpt-30b","company":"mosaicml","family":"MPT","version":"MPT","score":71},{"place":233,"model":"vllm-sr-d3-lite","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":70.9},{"place":234,"model":"gpt-2","company":"openai","family":"GPT","version":"GPT-2","score":70.7},{"place":235,"model":"deepseek-llm-7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":70.5},{"place":236,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":70.48},{"place":237,"model":"baichuan-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan","score":70.4},{"place":238,"model":"aquila2-7b","company":"baai","family":"Aquila","version":"Aquila2","score":70.3},{"place":239,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":70.2},{"place":240,"model":"deepseek-moe-16b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":70.2},{"place":241,"model":"qwen2.5-3b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":70.17},{"place":242,"model":"gopher-280b","company":"google","family":"Gopher","version":"Gopher","score":70.1},{"place":243,"model":"llama-1-7b","company":"meta","family":"Llama","version":"Llama 1","score":70.1},{"place":244,"model":"vllm-sr-decision-2.0-sol-2b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":70.1},{"place":245,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":70},{"place":246,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.77},{"place":247,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":69.69},{"place":248,"model":"tev1-4b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":69.6},{"place":249,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":69.6},{"place":250,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":69.53},{"place":251,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":69.5},{"place":252,"model":"tigerbot-70b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":69.38},{"place":253,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":69.38},{"place":254,"model":"llama-1-65b","company":"meta","family":"Llama","version":"Llama 1","score":69.38},{"place":255,"model":"olmo-1.7-7b","company":"allenai","family":"OLMo","version":"OLMo 1.7","score":69.22},{"place":256,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":69.2},{"place":257,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":69.14},{"place":258,"model":"deepseek-moe-16b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeekMoE","score":69},{"place":259,"model":"olmoe-1b-7b","company":"allenai","family":"OLMoE","version":"OLMoE","score":68.7},{"place":260,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":68.7},{"place":261,"model":"qwen-7b","company":"qwen","family":"Qwen","version":"Qwen","score":68.6},{"place":262,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":68.59},{"place":263,"model":"internlm-7b","company":"internlm","family":"InternLM","version":"InternLM","score":68.43},{"place":264,"model":"smollm2-1.7b-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":68.4},{"place":265,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":68.4},{"place":266,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":68.35},{"place":267,"model":"intern-decision-4b","company":"internlm","family":"Intern","version":"Intern-Decision","score":68.3},{"place":268,"model":"mpt-7b","company":"mosaicml","family":"MPT","version":"MPT","score":68.3},{"place":269,"model":"llama-2-7b","company":"meta","family":"Llama","version":"Llama 2","score":68.19},{"place":270,"model":"llama-2-70b-chat","company":"meta","family":"Llama","version":"Llama 2","score":68.11},{"place":271,"model":"trinity-nano-base","company":"arcee","family":"Trinity","version":"Trinity","score":68},{"place":272,"model":"qwen1.5-7b-chat","company":"qwen","family":"Qwen","version":"Qwen1.5","score":67.72},{"place":273,"model":"baichuan2-7b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":67.5},{"place":274,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":67.5},{"place":275,"model":"apertus-v1.1-4b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":67.48},{"place":276,"model":"llama-2-70b","company":"meta","family":"Llama","version":"Llama 2","score":67.4},{"place":277,"model":"qwen2.5-coder-3b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":67.4},{"place":278,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":67.32},{"place":279,"model":"tigerbot-70b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":67.01},{"place":280,"model":"mobilemoe-l","company":"meta","family":"MobileMoE","version":"MobileMoE","score":67},{"place":281,"model":"deepseek-llm-7b-chat","company":"deepseek","family":"DeepSeek","version":"DeepSeek","score":66.9},{"place":282,"model":"bielik-7b-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":66.85},{"place":283,"model":"llama-1-33b","company":"meta","family":"Llama","version":"Llama 1","score":66.85},{"place":284,"model":"gemma-2b","company":"google","family":"Gemma","version":"gemma-2b","score":66.8},{"place":285,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":66.77},{"place":286,"model":"olmo-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo","score":66.69},{"place":287,"model":"olmo-7b","company":"allenai","family":"OLMo","version":"OLMo","score":66.54},{"place":288,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":66.3},{"place":289,"model":"falcon-7b","company":"tii","family":"Falcon","version":"Falcon","score":66.3},{"place":290,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":66.22},{"place":291,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":66.2},{"place":292,"model":"map-neo-7b-instruct","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":66.06},{"place":293,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":66},{"place":294,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":65.82},{"place":295,"model":"internlm2-chat-7b-sft","company":"internlm","family":"InternLM","version":"InternLM2","score":65.8},{"place":296,"model":"internlm2-chat-7b","company":"internlm","family":"InternLM","version":"InternLM2","score":65.8},{"place":297,"model":"bielik-7b-instruct-v0.1","company":"SpeakLeash","family":"Bielik","version":"Bielik v0.1","score":65.51},{"place":298,"model":"gemma-2-2b","company":"google","family":"Gemma","version":"Gemma 2","score":65.4},{"place":299,"model":"map-neo-7b-sft","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":65.19},{"place":300,"model":"qwen2-1.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":65},{"place":301,"model":"qwen2.5-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":65},{"place":302,"model":"amberchat","company":"llm360","family":"Amber","version":"Amber","score":64.96},{"place":303,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":64.7},{"place":304,"model":"amber-7b","company":"llm360","family":"Amber","version":"Amber","score":64.64},{"place":305,"model":"llama-1-13b","company":"meta","family":"Llama","version":"Llama 1","score":64.64},{"place":306,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":64.6},{"place":307,"model":"starcoder2-15b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":64.3},{"place":308,"model":"tigerbot-13b-base","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":64.17},{"place":309,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":64.09},{"place":310,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":64.01},{"place":311,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":64},{"place":312,"model":"deepseek-coder-7b-base-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":63.8},{"place":313,"model":"deepseek-math-7b","company":"deepseek","family":"DeepSeek Math","version":"DeepSeek Math","score":63.8},{"place":314,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":63.69},{"place":315,"model":"olmo-2-0425-1b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":63.5},{"place":316,"model":"gemma-4-e4b","company":"google","family":"Gemma","version":"Gemma 4","score":63.4},{"place":317,"model":"deepseek-coder-7b-instruct-v1.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":63.4},{"place":318,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":63.38},{"place":319,"model":"minicpm4-8b","company":"openbmb","family":"MiniCPM","version":"MiniCPM4","score":63.3},{"place":320,"model":"tigerbot-13b-chat","company":"tigerresearch","family":"TigerBot","version":"TigerBot","score":63.3},{"place":321,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":63.1},{"place":322,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":63},{"place":323,"model":"mobilellm-p1-base","company":"meta","family":"MobileLLM","version":"MobileLLM P1","score":62.83},{"place":324,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":62.75},{"place":325,"model":"mobilemoe-m","company":"meta","family":"MobileMoE","version":"MobileMoE","score":62.7},{"place":326,"model":"codellama-7b","company":"codellama","family":"CodeLlama-7B","version":"CodeLlama-7B","score":62.3},{"place":327,"model":"deepseek-coder-33b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":62},{"place":328,"model":"vllm-sr-d3-edge","company":"vllm-sr","family":"vLLM-SR d3","version":"d3","score":61.8},{"place":329,"model":"apertus-v1.1-1.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":61.72},{"place":330,"model":"chatglm3-6b","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":61.7},{"place":331,"model":"gemma-4-e2b","company":"google","family":"Gemma","version":"Gemma 4","score":61.2},{"place":332,"model":"bitcpm-cann-8b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":61.17},{"place":333,"model":"llama-3.2-1b","company":"meta","family":"Llama","version":"Llama 3.2","score":61.09},{"place":334,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":60.9},{"place":335,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":60.85},{"place":336,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":60.8},{"place":337,"model":"qwen2.5-coder-1.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":60.7},{"place":338,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":60.5},{"place":339,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":60.5},{"place":340,"model":"qwen1.5-1.8b","company":"qwen","family":"Qwen","version":"Qwen1.5","score":60.3},{"place":341,"model":"map-neo-7b","company":"m-a-p","family":"MAP-Neo","version":"MAP-Neo","score":59.83},{"place":342,"model":"codeqwen1.5-7b","company":"qwen","family":"Qwen","version":"CodeQwen1.5","score":59.8},{"place":343,"model":"gemma-2-27b","company":"google","family":"Gemma","version":"Gemma 2","score":59.7},{"place":344,"model":"mobilemoe-s","company":"meta","family":"MobileMoE","version":"MobileMoE","score":59.6},{"place":345,"model":"smollm2-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":59.4},{"place":346,"model":"huginn-3.5b","company":"tomg-umd","family":"Huginn","version":"Huginn","score":59.4},{"place":347,"model":"qwen2.5-1.5b-pretrained","company":"qwen","family":"Qwen","version":"Qwen2.5","score":59.3},{"place":348,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":59.2},{"place":349,"model":"internvl2.5-2b","company":"opengvlab","family":"Intern","version":"InternVL 2.5","score":59.1},{"place":350,"model":"gemma-3-1b-it","company":"google","family":"Gemma","version":"Gemma 3","score":58.72},{"place":351,"model":"internvl2-2b","company":"opengvlab","family":"Intern","version":"InternVL2","score":58.7},{"place":352,"model":"pythia-2.8b","company":"eleutherai","family":"Pythia","version":"Pythia","score":58.2},{"place":353,"model":"gemma-3-1b","company":"google","family":"Gemma","version":"Gemma 3","score":58.2},{"place":354,"model":"llama-1b-pretrained","company":"meta","family":"Llama","version":"Llama 1","score":57.8},{"place":355,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":57.6},{"place":356,"model":"deepseek-coder-6.7b-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":57.6},{"place":357,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":57.6},{"place":358,"model":"intern-decision-2b","company":"internlm","family":"Intern","version":"Intern-Decision","score":57.5},{"place":359,"model":"vllm-sr-decision-2.0-kai-0.6b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":57.5},{"place":360,"model":"smollm2-360m-instruct","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":57.4},{"place":361,"model":"strands-decider-2b","company":"amazon","family":"strands-decider","version":"v1-2610","score":57.4},{"place":362,"model":"deepseek-coder-6.7b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":57.1},{"place":363,"model":"starcoder2-3b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":57.1},{"place":364,"model":"starcoder2-7b","company":"bigcode","family":"StarCoder","version":"StarCoder2","score":57.1},{"place":365,"model":"apertus-v1.1-0.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":57.06},{"place":366,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":56.9},{"place":367,"model":"internlm2.5-1.8b-chat","company":"internlm","family":"InternLM","version":"InternLM2.5","score":56.9},{"place":368,"model":"qwen2-0.5b","company":"qwen","family":"Qwen","version":"Qwen2","score":56.8},{"place":369,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":56.7},{"place":370,"model":"pythia-1.4b","company":"eleutherai","family":"Pythia","version":"Pythia","score":56.6},{"place":371,"model":"internlm2-chat-1.8b","company":"internlm","family":"InternLM","version":"InternLM2","score":56.5},{"place":372,"model":"qwen2.5-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5","score":56.3},{"place":373,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":55.7},{"place":374,"model":"qwen2.5-coder-0.5b","company":"qwen","family":"Qwen","version":"Qwen2.5-Coder","score":54.8},{"place":375,"model":"smollm1-1.7b-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM1","score":54.7},{"place":376,"model":"qwen-7b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":54.2},{"place":377,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":53.9},{"place":378,"model":"pythia-410m","company":"eleutherai","family":"Pythia","version":"Pythia","score":53.4},{"place":379,"model":"deepseek-coder-1.3b-base","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":53.3},{"place":380,"model":"bitcpm-cann-1b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":53.28},{"place":381,"model":"intern-decision-0.8b","company":"internlm","family":"Intern","version":"Intern-Decision","score":53.1},{"place":382,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":53},{"place":383,"model":"bitcpm-cann-3b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":52.96},{"place":384,"model":"pythia-1b","company":"eleutherai","family":"Pythia","version":"Pythia","score":52.9},{"place":385,"model":"llama-3.2-3b","company":"meta","family":"Llama","version":"Llama 3.2","score":52.4},{"place":386,"model":"gemma-3-270m-it","company":"google","family":"Gemma","version":"Gemma 3","score":52.3},{"place":387,"model":"tev1-0.8b-experimental","company":"togethercomputer","family":"Tev1","version":"Tev1","score":52.2},{"place":388,"model":"gemma-3-pt-270m","company":"google","family":"Gemma","version":"Gemma 3","score":52},{"place":389,"model":"vllm-sr-decision-2.0-eos-0.8b","company":"vllm-sr","family":"vLLM-SR Decision","version":"Decision 2.0","score":51.8},{"place":390,"model":"mobilellm-p1","company":"meta","family":"MobileLLM","version":"MobileLLM","score":51.7},{"place":391,"model":"bitcpm-cann-0.5b","company":"openbmb","family":"MiniCPM","version":"BitCPM-CANN","score":51.54},{"place":392,"model":"llama-2-7b-chat","company":"meta","family":"Llama","version":"Llama 2","score":51.5},{"place":393,"model":"chatglm3-6b-base","company":"zai","family":"ChatGLM","version":"ChatGLM3","score":51.4},{"place":394,"model":"smollm2-135m-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":51.3},{"place":395,"model":"smollm2-135m-pretrained","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":51.3},{"place":396,"model":"minicpm4-0.5b","company":"openbmb","family":"MiniCPM","version":"MiniCPM 4","score":51.07},{"place":397,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":50.9},{"place":398,"model":"mistral-7b-instruct-v0.2","company":"mistral","family":"Mistral","version":"Mistral v0.2","score":50.8},{"place":399,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":50.8},{"place":400,"model":"gliner2.5-decide","company":"fastino","family":"GLiNER","version":"GLiNER2.5","score":50.7},{"place":401,"model":"laya","company":"convaiinnovations","family":"Laya","version":"Laya","score":50.5},{"place":402,"model":"baichuan2-7b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":49.9},{"place":403,"model":"pythia-160m","company":"eleutherai","family":"Pythia","version":"Pythia","score":49.7},{"place":404,"model":"pythia-70m","company":"eleutherai","family":"Pythia","version":"Pythia","score":49.2},{"place":405,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.749},{"place":406,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.697}]},{"id":"winogrande-de","name":"WinoGrande (DE)","topic":"Coreference reasoning (German)","description":"German translation of the WinoGrande pronoun resolution benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"norm_log_acc","stars":"","top_model":"Llama-3_1-70B-TFree-HAT-SFT","top_percent":0.793,"top_model_id":"llama-3_1-70b-tfree-hat-sft","top_generation":"Llama TFree HAT","top_model_base":"Llama 3.1 70B TFree HAT","top_model_family":"Llama TFree HAT","top_company":"alephalpha","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":0.793},{"place":2,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":0.761}]},{"id":"wmdp-bio","name":"WMDP Bio","topic":"Biosecurity knowledge","description":"Weapons of Mass Destruction Proxy benchmark for biosecurity, measuring hazardous biological knowledge without info hazards.","url":"https://www.wmdp.ai/","leaderboard":"","github":"https://github.com/centerforaisafety/wmdp","paper":"https://arxiv.org/abs/2403.03218","metric":"percent","stars":"","top_model":"Zephyr 7B","top_percent":63.7,"top_model_id":"zephyr-7b","top_generation":"Zephyr","top_model_base":"Zephyr 7B","top_model_family":"Zephyr","top_company":"huggingface","top_open_source":1,"lower_is_better":true,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"zephyr-7b","company":"huggingface","family":"Zephyr","version":"Zephyr","score":63.7},{"place":2,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":87},{"place":3,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":87}]},{"id":"wmdp-chem","name":"WMDP Chem","topic":"Chemical security knowledge","description":"WMDP benchmark for chemical security, evaluating knowledge relevant to chemical weapons development.","url":"https://www.wmdp.ai/","leaderboard":"","github":"https://github.com/centerforaisafety/wmdp","paper":"https://arxiv.org/abs/2403.03218","metric":"percent","stars":"","top_model":"Zephyr 7B","top_percent":45.8,"top_model_id":"zephyr-7b","top_generation":"Zephyr","top_model_base":"Zephyr 7B","top_model_family":"Zephyr","top_company":"huggingface","top_open_source":1,"lower_is_better":true,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"zephyr-7b","company":"huggingface","family":"Zephyr","version":"Zephyr","score":45.8},{"place":2,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":83},{"place":3,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":84}]},{"id":"wmdp-cyber","name":"WMDP Cyber","topic":"Cybersecurity knowledge","description":"WMDP benchmark for cybersecurity, assessing knowledge that could aid in cyber weapons development.","url":"https://www.wmdp.ai/","leaderboard":"","github":"https://github.com/centerforaisafety/wmdp","paper":"https://arxiv.org/abs/2403.03218","metric":"percent","stars":"","top_model":"Zephyr 7B","top_percent":44,"top_model_id":"zephyr-7b","top_generation":"Zephyr","top_model_base":"Zephyr 7B","top_model_family":"Zephyr","top_company":"huggingface","top_open_source":1,"lower_is_better":true,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"zephyr-7b","company":"huggingface","family":"Zephyr","version":"Zephyr","score":44},{"place":2,"model":"grok-4","company":"xai","family":"Grok","version":"Grok 4","score":79},{"place":3,"model":"grok-4.1-thinking","company":"xai","family":"Grok","version":"Grok 4.1","score":84}]},{"id":"wmt16","name":"WMT16 En–De","topic":"Machine translation","description":"WMT16 English–German translation benchmark (news).","url":"https://www.statmt.org/wmt16/translation-task.html","leaderboard":"","github":"","paper":"","metric":"bleu","stars":"","top_model":"Llama 3.3 70B Instruct","top_percent":38.841,"top_model_id":"llama-3.3-70b-instruct","top_generation":"Llama 3.3","top_model_base":"Llama 3.3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":38.841},{"place":2,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":37.38}]},{"id":"wmt16-instruct","name":"WMT16 En–De (Instruct)","topic":"Machine translation","description":"Instruction-tuned evaluation on the WMT16 English–German translation set.","url":"","leaderboard":"","github":"","paper":"","metric":"bleu","stars":"","top_model":"Llama 3.3 70B Instruct","top_percent":37.912,"top_model_id":"llama-3.3-70b-instruct","top_generation":"Llama 3.3","top_model_base":"Llama 3.3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":37.912},{"place":2,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":37.614}]},{"id":"wmt20-en-ja","name":"WMT20 En-Ja","topic":"Machine translation","description":"WMT20 English-to-Japanese news translation (Swallow eval, BLEU).","url":"https://swallow-llm.github.io/leaderboard/","leaderboard":"","github":"","paper":"","metric":"bleu","stars":"","top_model":"GPT-OSS-Swallow-120B-SFT-v0.1","top_percent":27,"top_model_id":"gpt-oss-swallow-120b-sft-v0.1","top_generation":"GPT-OSS-Swallow v0.1","top_model_base":"GPT-OSS-Swallow","top_model_family":"Swallow","top_company":"tokyotech","top_open_source":1,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":27},{"place":2,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":26.7},{"place":3,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":26.6},{"place":4,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":26.3},{"place":5,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":26},{"place":6,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":25.5},{"place":7,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":25.4},{"place":8,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":25.2},{"place":9,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":25.1},{"place":10,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":25.1},{"place":11,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":25},{"place":12,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":24.9},{"place":13,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":24.8},{"place":14,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":24.3},{"place":15,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":24.3},{"place":16,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":24.2},{"place":17,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":23.9},{"place":18,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":23.8},{"place":19,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":23.5},{"place":20,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":23.2},{"place":21,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":23.2},{"place":22,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":23.1},{"place":23,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":22.8},{"place":24,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":22.6},{"place":25,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":20.9},{"place":26,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":17.4},{"place":27,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":17.3},{"place":28,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":17},{"place":29,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":13.1},{"place":30,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":12.4},{"place":31,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":9.6}]},{"id":"wmt20-ja-en","name":"WMT20 Ja-En","topic":"Machine translation","description":"WMT20 Japanese-to-English news translation (Swallow eval, BLEU).","url":"https://swallow-llm.github.io/leaderboard/","leaderboard":"","github":"","paper":"","metric":"bleu","stars":"","top_model":"GPT-5 mini","top_percent":23.9,"top_model_id":"gpt-5-mini","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":23.9},{"place":2,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":23.8},{"place":3,"model":"qwen3-swallow-32b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":23.5},{"place":4,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":23.4},{"place":5,"model":"qwen3-swallow-30b-a3b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":22.9},{"place":6,"model":"llama-3.1-swallow-8b-instruct-v0.5","company":"tokyotech","family":"Swallow","version":"Llama 3.1 Swallow v0.5","score":22.2},{"place":7,"model":"gpt-oss-swallow-120b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":22.1},{"place":8,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":22},{"place":9,"model":"gpt-oss-swallow-20b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":22},{"place":10,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":22},{"place":11,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":21.9},{"place":12,"model":"qwen3-swallow-30b-a3b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":21.9},{"place":13,"model":"qwen3-swallow-32b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":21.9},{"place":14,"model":"gpt-oss-swallow-120b-sft-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":21.6},{"place":15,"model":"qwen3-swallow-32b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":21.6},{"place":16,"model":"abeja-qwq32b-reasoning-japanese-v1.0","company":"abeja","family":"ABEJA","version":"v1.0","score":21.5},{"place":17,"model":"qwen3-swallow-8b-cpt-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":21.5},{"place":18,"model":"gpt-oss-swallow-20b-rl-v0.1","company":"tokyotech","family":"Swallow","version":"GPT-OSS-Swallow v0.1","score":21.3},{"place":19,"model":"qwen3-swallow-30b-a3b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":21.3},{"place":20,"model":"gpt-oss-20b-medium","company":"openai","family":"GPT","version":"GPT-OSS","score":20.8},{"place":21,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":20.7},{"place":22,"model":"qwq-bakeneko-32b","company":"rinna","family":"Bakeneko","version":"QwQ Bakeneko","score":20.7},{"place":23,"model":"qwen3-30b-a3b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":20.6},{"place":24,"model":"qwen3-swallow-8b-sft-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":20.5},{"place":25,"model":"qwen3-swallow-8b-rl-v0.2","company":"tokyotech","family":"Swallow","version":"Qwen3-Swallow v0.2","score":20.4},{"place":26,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":20.2},{"place":27,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":19.7},{"place":28,"model":"qwen3-8b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":19.3},{"place":29,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":18.6},{"place":30,"model":"deepseek-r1-distill-llama-8b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":14.4},{"place":31,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":14.3}]},{"id":"wmt24-plus-plus","name":"WMT24++","topic":"Machine translation","description":"Extended WMT 2024 evaluation across multiple language pairs.","url":"https://arxiv.org/abs/2502.12404v1","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-235B-A22B-Thinking-2507","top_percent":94.7,"top_model_id":"qwen3-235b-a22b-thinking-2507","top_generation":"Qwen3","top_model_base":"Qwen3 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":70,"total_models":3854,"placements":[{"place":1,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":94.7},{"place":2,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":93.6},{"place":3,"model":"k-exaone","company":"lg","family":"K-EXAONE","version":"K-EXAONE","score":90.5},{"place":4,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":90},{"place":5,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":88.89},{"place":6,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.84},{"place":7,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":87.6},{"place":8,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.8},{"place":9,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.8},{"place":10,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.7},{"place":11,"model":"nemotron-3-super-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.67},{"place":12,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":86.3},{"place":13,"model":"nvidia-nemotron-3-nano-30b-a3b-bf16","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":86.2},{"place":14,"model":"qwen3.8-flash-next","company":"qwen","family":"Qwen","version":"Qwen3.8","score":86.2},{"place":15,"model":"glm-5.3-flash","company":"zai","family":"GLM","version":"GLM 5.3","score":86.1},{"place":16,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.9},{"place":17,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.9},{"place":18,"model":"qwen3.7-max","company":"qwen","family":"Qwen","version":"Qwen3.7","score":85.8},{"place":19,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.6},{"place":20,"model":"deepseek-v4-flash-0731","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":85.5},{"place":21,"model":"nemotron-labs-3-puzzle-75b-a9b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":85.2},{"place":22,"model":"nemotron-3.5-super-vl-120b-a12b","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":84.8},{"place":23,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":84.6},{"place":24,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":84.6},{"place":25,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":84.5},{"place":26,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":84.4},{"place":27,"model":"translategemma-27b-it","company":"google","family":"TranslateGemma","version":"TranslateGemma","score":84.4},{"place":28,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":84.3},{"place":29,"model":"nemotron-cascade-2-30b-a3b","company":"nvidia","family":"Nemotron Cascade","version":"Nemotron Cascade 2","score":84.1},{"place":30,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.7},{"place":31,"model":"gemma-3-27b","company":"google","family":"Gemma","version":"Gemma 3","score":83.65},{"place":32,"model":"eurollm-22b","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":83.62},{"place":33,"model":"translategemma-12b-it","company":"google","family":"TranslateGemma","version":"TranslateGemma","score":83.5},{"place":34,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":83.2},{"place":35,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":83.1},{"place":36,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":82.8},{"place":37,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":82.7},{"place":38,"model":"nemotron-3-ultra","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":82.7},{"place":39,"model":"llama-3.3-70b","company":"meta","family":"Llama","version":"Llama 3.3","score":82.28},{"place":40,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":82.2},{"place":41,"model":"glm-5","company":"zai","family":"GLM","version":"GLM 5","score":82.1},{"place":42,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":81.96},{"place":43,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.9},{"place":44,"model":"glm-5.1","company":"zai","family":"GLM","version":"GLM 5.1","score":81.8},{"place":45,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":81.69},{"place":46,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":81.6},{"place":47,"model":"gemma-3-12b-it","company":"google","family":"Gemma","version":"Gemma 3","score":81.6},{"place":48,"model":"command-a-plus-05-2026","company":"cohere","family":"Command","version":"Command A+","score":81},{"place":49,"model":"exaone-4.0-32b-thinking","company":"lg","family":"EXAONE","version":"EXAONE 4.0","score":80.8},{"place":50,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":80.7},{"place":51,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":80.7},{"place":52,"model":"translategemma-4b-it","company":"google","family":"TranslateGemma","version":"TranslateGemma","score":80.1},{"place":53,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":79.7},{"place":54,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.9},{"place":55,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":78.8},{"place":56,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":78.3},{"place":57,"model":"qwen3-max-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":77.6},{"place":58,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":77.6},{"place":59,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77.6},{"place":60,"model":"gemma-3-4b-it","company":"google","family":"Gemma","version":"Gemma 3","score":77.2},{"place":61,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":76.38},{"place":62,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":76.3},{"place":63,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":75.8},{"place":64,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":74.4},{"place":65,"model":"command-a-reasoning-08-2025","company":"cohere","family":"Command","version":"Command","score":73},{"place":66,"model":"mistral-3.2-24b","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":72.81},{"place":67,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":72.6},{"place":68,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":69.3},{"place":69,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":67.8},{"place":70,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":66.6},{"place":71,"model":"qwen3-4b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":58.9},{"place":72,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":57.4},{"place":73,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":53.4},{"place":74,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":49.2},{"place":75,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":45.8},{"place":76,"model":"tiny-aya-global","company":"cohere","family":"Aya","version":"Aya","score":45.4},{"place":77,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":40.9},{"place":78,"model":"gemma-3-4b","company":"google","family":"Gemma","version":"Gemma 3","score":40.5},{"place":79,"model":"qwen3-1.7b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":39.3},{"place":80,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":32.6},{"place":81,"model":"ministral-3-3b-base","company":"mistral","family":"Ministral","version":"Ministral 3","score":30.4},{"place":82,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":27.2},{"place":83,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":26.9}]},{"id":"wod-e2e","name":"WOD-E2E (RFS)","topic":"Driving planning","description":"Waymo Open Dataset end-to-end driving challenge on long-tail scenarios; score = Rater Feedback Score (RFS, 0-10) on the test split.","url":"https://waymo.com/open/challenges/2025/e2e-driving/","leaderboard":"","github":"","paper":"","metric":"score","stars":"","top_model":"Qwen-Drive-1.0-4B RL","top_percent":7.91,"top_model_id":"qwen-drive-1.0-4b-rl","top_generation":"Qwen-Drive-1.0","top_model_base":"Qwen-Drive 1.0 4B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"qwen-drive-1.0-4b-rl","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":7.91},{"place":2,"model":"mindvla-u1","company":"liauto","family":"MindVLA","version":"MindVLA-U1","score":7.87},{"place":3,"model":"qwen-drive-1.0-4b","company":"qwen","family":"Qwen","version":"Qwen-Drive-1.0","score":7.78},{"place":4,"model":"autovla","company":"ucla","family":"AutoVLA","version":"AutoVLA","score":7.56}]},{"id":"workbench","name":"WorkBench","topic":"Agentic tool use","description":"Workplace agent benchmark: tasks over simulated email, calendar, CRM, analytics and project-management tools; scored by task completion (outcome-based).","url":"https://arxiv.org/abs/2405.00823","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemma 4 E4B IT","top_percent":46.1,"top_model_id":"gemma-4-e4b-it","top_generation":"Gemma 4","top_model_base":"Gemma 4 E4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.1},{"place":2,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":45.1},{"place":3,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":44.6},{"place":4,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.7}]},{"id":"workbuddy-bench","name":"WorkBuddy Bench","topic":"Office assistant agents","description":"Agentic benchmark of workplace-assistant (WorkBuddy) tasks such as documents, spreadsheets and messaging.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Muse Glimmer 30B","top_percent":45.85,"top_model_id":"muse-glimmer-30b","top_generation":"Muse Glimmer","top_model_base":"Muse Glimmer","top_model_family":"Muse","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":12,"total_models":3854,"placements":[{"place":1,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":45.85},{"place":2,"model":"neohorse-1-9b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":40.15},{"place":3,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.6},{"place":4,"model":"granite-4.2-8b","company":"IBM","family":"Granite","version":"Granite 4.2","score":35.07},{"place":5,"model":"neohorse-1-4b","company":"tokenrhythm","family":"NeoHorse","version":"NeoHorse-1","score":34.41},{"place":6,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":33.37},{"place":7,"model":"gemma-4-12b-it","company":"google","family":"Gemma","version":"Gemma 4","score":29.65},{"place":8,"model":"ornith-1.5-9b","company":"ornith","family":"Ornith","version":"Ornith-1.5","score":29.29},{"place":9,"model":"spark-x2.5-4b","company":"iflytek","family":"Spark","version":"Spark X2.5","score":26.47},{"place":10,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":24.62},{"place":11,"model":"nanbeige4.2-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.2","score":21.03},{"place":12,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":11.65}]},{"id":"workspacebench","name":"Workspace Bench","topic":"Agentic office work","description":"Workspace Bench: OpenClaw-style workspace tasks with large heterogeneous file dependencies (100-task setting).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 5","top_percent":75,"top_model_id":"claude-opus-5","top_generation":"Claude 5","top_model_base":"Claude Opus 5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":15,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":75},{"place":2,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":68.2},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":68},{"place":4,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":67.4},{"place":5,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":66.1},{"place":6,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":65.8},{"place":7,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":65.4},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":65.3},{"place":9,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":65},{"place":10,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":65},{"place":11,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":63.5},{"place":12,"model":"hy4-preview","company":"tencent","family":"HY","version":"Hy4","score":60.2},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.7},{"place":14,"model":"hy3","company":"tencent","family":"HY","version":"Hy3","score":58.2},{"place":15,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":58.2},{"place":16,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":56},{"place":17,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":55.1},{"place":18,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":54.7},{"place":19,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":53},{"place":20,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":32.8}]},{"id":"workspacebench-lite","name":"Workspace Bench Lite","topic":"Agentic office work","description":"Lite subset of Workspace Bench: workspace tasks with heterogeneous file dependencies.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-5.3","top_percent":71.7,"top_model_id":"glm-5.3","top_generation":"GLM 5.3","top_model_base":"GLM-5.3","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":71.7},{"place":2,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":70.1},{"place":3,"model":"atria-dawn","company":"internlm","family":"Atria","version":"Atria Dawn","score":70},{"place":4,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":68.7},{"place":5,"model":"atria-dawn-preview","company":"internlm","family":"Atria","version":"Atria Dawn","score":68.2},{"place":6,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":64.9},{"place":7,"model":"deepseek-v4-pro-0813","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.1},{"place":8,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":60.5}]},{"id":"worldbench","name":"WorldBench","topic":"Visual knowledge","description":"Benchmark of real-world visual knowledge and recognition.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":67.6,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":67.6},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":63.7},{"place":3,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":62.9},{"place":4,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":58.4},{"place":5,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":52.9}]},{"id":"worldtravel2-multimodal","name":"WorldTravel2 (multi-modal)","topic":"Travel planning (multimodal)","description":"WorldTravel2 benchmark multimodal track.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3 Pro","top_percent":47.2,"top_model_id":"gemini-3-pro","top_generation":"Gemini 3","top_model_base":"Gemini 3 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":47.2},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":47.2},{"place":3,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":45.9},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":41.3},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":36}]},{"id":"worldtravel2-text","name":"WorldTravel2 (text)","topic":"Travel planning (text)","description":"WorldTravel2 benchmark text-only track.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":56.4,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":56.4},{"place":2,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":53.3},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":53.3},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":52.1},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":44.5}]},{"id":"worldvqa","name":"WorldVQA","topic":"World knowledge VQA","description":"Visual question answering requiring world knowledge and commonsense reasoning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":65.4,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":30,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":65.4},{"place":2,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":61.1},{"place":3,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":56.7},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":56.1},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":54},{"place":6,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":53.5},{"place":7,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":53.2},{"place":8,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":53},{"place":9,"model":"gemini-3.5-flash","company":"google","family":"Gemini","version":"Gemini 3.5","score":51.9},{"place":10,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":51},{"place":11,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":50.63},{"place":12,"model":"seed2.0-lite-0428","company":"bytedance","family":"Seed","version":"Seed 2.0","score":50.2},{"place":13,"model":"seed2.0-pro","company":"bytedance","family":"Seed","version":"Seed 2.0","score":49.9},{"place":14,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":49.4},{"place":15,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":48.6},{"place":16,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":47.4},{"place":17,"model":"gemini-3-flash","company":"google","family":"Gemini","version":"Gemini 3","score":46.5},{"place":18,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":46.3},{"place":19,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":45.9},{"place":20,"model":"ling-3.0-flash-vl","company":"antgroup","family":"Ling","version":"Ling 3.0","score":45.67},{"place":21,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":45.1},{"place":22,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":44.4},{"place":23,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":44.3},{"place":24,"model":"seed2.0-lite","company":"bytedance","family":"Seed","version":"Seed 2.0","score":44},{"place":25,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":43.9},{"place":26,"model":"gemini-3.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.5","score":42.83},{"place":27,"model":"dots3-note-preview","company":"rednote","family":"dots","version":"dots3","score":42.7},{"place":28,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":41.8},{"place":29,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":39.1},{"place":30,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":38.5},{"place":31,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":36.8},{"place":32,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":35.9},{"place":33,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":35.5},{"place":34,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":34.6},{"place":35,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":33.9},{"place":36,"model":"qwen3.6-plus","company":"qwen","family":"Qwen","version":"Qwen3.6","score":33.6},{"place":37,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":30.2},{"place":38,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":28},{"place":39,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":23.5},{"place":40,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":22.87},{"place":41,"model":"inkling-small","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":16.2}]},{"id":"worldvqa-with-tools","name":"WorldVQA (With Tools)","topic":"Visual world knowledge","description":"WorldVQA evaluated with tool access in an agent harness.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Step 3.7 Flash","top_percent":58.1,"top_model_id":"step-3.7-flash","top_generation":"Step 3.7 Flash","top_model_base":"Step 3.7 Flash","top_model_family":"Step","top_company":"stepfun","top_open_source":1,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":58.1},{"place":2,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":55.98},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":54.58},{"place":4,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":51},{"place":5,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":49.4},{"place":6,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":47.81},{"place":7,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":18}]},{"id":"writingbench","name":"WritingBench","topic":"Writing quality","description":"General-purpose writing quality benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3-235B-A22B-Thinking-2507","top_percent":88.3,"top_model_id":"qwen3-235b-a22b-thinking-2507","top_generation":"Qwen3","top_model_base":"Qwen3 235B A22B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":43,"total_models":3854,"placements":[{"place":1,"model":"qwen3-235b-a22b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":88.3},{"place":2,"model":"qwen3-next-80b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":87.3},{"place":3,"model":"gpt-oss-120b","company":"openai","family":"GPT","version":"GPT-OSS","score":86.5},{"place":4,"model":"qwen3-omni-flash-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.9},{"place":5,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.5},{"place":6,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85.5},{"place":7,"model":"qwen3-omni-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.5},{"place":8,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":85.3},{"place":9,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":85.2},{"place":10,"model":"qwen3-vl-30b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":85.2},{"place":11,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":85.2},{"place":12,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":85},{"place":13,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84.7},{"place":14,"model":"qwen3-next-80b-a3b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 Next","score":84.6},{"place":15,"model":"gemini-2.5-flash-thinking","company":"google","family":"Gemini","version":"Gemini 2.5","score":83.9},{"place":16,"model":"longcat-2.0","company":"meituan","family":"LongCat","version":"LongCat-2.0","score":83.8},{"place":17,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":83.8},{"place":18,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":83.7},{"place":19,"model":"nemotron-3-nano-30b-a3b","company":"nvidia","family":"Nemotron","version":"Nemotron 3","score":83.7},{"place":20,"model":"qwen3-4b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":83.4},{"place":21,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":83.1},{"place":22,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":83},{"place":23,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":82.6},{"place":24,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.6},{"place":25,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":82.5},{"place":26,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":80.5},{"place":27,"model":"qwen-3-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":80.3},{"place":28,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":79.5},{"place":29,"model":"snowdon-1.1-small","company":"tri-fair-lab","family":"Snowdon","version":"Snowdon-1.1","score":79.3},{"place":30,"model":"glm-4.7-flash","company":"zai","family":"GLM","version":"GLM 4.7","score":79.2},{"place":31,"model":"gpt-oss-20b","company":"openai","family":"GPT","version":"GPT-OSS","score":79.1},{"place":32,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":79},{"place":33,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":78.7},{"place":34,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":77},{"place":35,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":75.7},{"place":36,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":75.5},{"place":37,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":75.4},{"place":38,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":71.4},{"place":39,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":71.4},{"place":40,"model":"mistral-small-3.2-24b-instruct","company":"mistral","family":"Mistral","version":"Mistral 3.2","score":70.3},{"place":41,"model":"solar-open-100b","company":"upstage","family":"Solar","version":"Solar Open","score":7.51},{"place":42,"model":"glm-4.5-air","company":"zai","family":"GLM","version":"GLM 4.5","score":7.4},{"place":43,"model":"gpt-oss-120b-high","company":"openai","family":"GPT","version":"GPT-OSS","score":6.61},{"place":44,"model":"gpt-oss-120b-medium","company":"gpt-oss","family":"GPT-OSS","version":"GPT-OSS","score":6.55}]},{"id":"wsc","name":"WSC","topic":"Coreference reasoning","description":"Classic Winograd Schema Challenge measuring commonsense coreference.","url":"https://cs.nyu.edu/faculty/davise/papers/WinogradSchemas/WS.html","leaderboard":"","github":"","paper":"https://arxiv.org/abs/1109.1334","metric":"percent","stars":"","top_model":"Hairuo","top_percent":100,"top_model_id":"hairuo","top_generation":"Hairuo","top_model_base":"Hairuo","top_model_family":"Hairuo","top_company":"generic","top_open_source":1,"lower_is_better":false,"bench_models":54,"total_models":3854,"placements":[{"place":1,"model":"hairuo","company":"generic","family":"Hairuo","version":"Hairuo","score":100},{"place":2,"model":"vega-v2","company":"jd","family":"Vega","version":"Vega v2","score":98.6},{"place":3,"model":"ernie-3.0","company":"baidu","family":"ERNIE","version":"ERNIE 3.0","score":97.3},{"place":4,"model":"turing-nlr-v5","company":"microsoft","family":"Turing","version":"Turing NLR v5","score":97.3},{"place":5,"model":"st-moe-32b","company":"google","family":"ST","version":"ST-MoE-32B","score":96.6},{"place":6,"model":"t5-plus-udg-single-model-google-brain","company":"google","family":"T5","version":"T5 + UDG, Single Model (Google Brain)","score":96.6},{"place":7,"model":"palm-540b","company":"google","family":"PaLM","version":"PaLM","score":95.9},{"place":8,"model":"deberta-turingnlrv4","company":"microsoft","family":"DeBERTa","version":"DeBERTa / TuringNLRv4","score":95.9},{"place":9,"model":"frozen-t5-1.1-plus-spot","company":"google","family":"Frozen","version":"Frozen T5 1.1 + SPoT","score":93.8},{"place":10,"model":"t5","company":"google","family":"T5","version":"T5","score":93.8},{"place":11,"model":"pai-albert","company":"alibaba","family":"PAI","version":"PAI Albert","score":93.2},{"place":12,"model":"nezha-plus","company":"huawei","family":"NEZHA","version":"NEZHA-Plus","score":93.2},{"place":13,"model":"gemma-3-pt-27b","company":"google","family":"Gemma","version":"Gemma 3","score":91.9},{"place":14,"model":"roberta-ensemble","company":"tencent","family":"RoBERTa","version":"RoBERTa (ensemble)","score":91.8},{"place":15,"model":"roberta-mtl-adv","company":"zhuiyi","family":"RoBERTa","version":"RoBERTa-mtl-adv","score":91.8},{"place":16,"model":"roberta-icets","company":"infosys","family":"RoBERTa","version":"RoBERTa-iCETS","score":89},{"place":17,"model":"roberta","company":"meta","family":"RoBERTa","version":"RoBERTa","score":89},{"place":18,"model":"ipet-albert-few-shot-32-examples","company":"lmu","family":"iPET","version":"iPET (ALBERT) - Few-Shot (32 Examples)","score":88.4},{"place":19,"model":"fsl-plus-plus-albert-few-shot-32-examples","company":"unknown","family":"FSL++(ALBERT)","version":"FSL++(ALBERT)-Few-Shot(32 Examples)","score":88.4},{"place":20,"model":"olmo-2-32b-base","company":"allenai","family":"OLMo","version":"OLMo 2","score":86.8},{"place":21,"model":"adapet-albert-few-shot","company":"unc","family":"ADAPET","version":"ADAPET (ALBERT) - few-shot","score":85.6},{"place":22,"model":"nemotron-nano-12b-v2-base","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":85.4},{"place":23,"model":"install-albert-few-shot-32examples","company":"casia","family":"INSTALL(ALBERT)","version":"INSTALL(ALBERT)-few-shot(32examples)","score":84.9},{"place":24,"model":"marin-32b-bison","company":"marin","family":"Marin","version":"Marin 32B","score":82.4},{"place":25,"model":"qwen2.5-32b-base","company":"qwen","family":"Qwen","version":"Qwen2.5","score":81},{"place":26,"model":"gpt-3","company":"openai","family":"GPT","version":"GPT-3","score":80.1},{"place":27,"model":"marin-32b-mantis","company":"marin","family":"Marin","version":"Marin 32B","score":79.5},{"place":28,"model":"ailabs-team-transformers","company":"unknown","family":"AILabs","version":"AILabs Team, Transformers","score":78.8},{"place":29,"model":"text-to-text-petl","company":"berkeley","family":"Text","version":"Text to Text PETL","score":74},{"place":30,"model":"snorkel-superglue-v1.9","company":"stanford","family":"Snorkel","version":"Snorkel [SuperGLUE v1.9]","score":72.6},{"place":31,"model":"baichuan2-13b-chat","company":"baichuan","family":"Baichuan","version":"Baichuan 2","score":71.2},{"place":32,"model":"orion-14b-chat","company":"orionstarai","family":"Orion","version":"Orion","score":71.2},{"place":33,"model":"orion-14b-base","company":"orionstarai","family":"Orion","version":"Orion","score":70.2},{"place":34,"model":"internlm-20b","company":"internlm","family":"InternLM","version":"InternLM","score":68.3},{"place":35,"model":"llama-2-13b-chat","company":"meta","family":"Llama","version":"Llama 2","score":68.3},{"place":36,"model":"select-step-by-step","company":"unknown","family":"select","version":"select-step-by-step","score":67.8},{"place":37,"model":"llama-2-13b","company":"meta","family":"Llama","version":"Llama 2","score":66.3},{"place":38,"model":"skywork-13b-base","company":"skywork","family":"Skywork","version":"Skywork","score":66.3},{"place":39,"model":"baichuan2-13b-base","company":"baichuan","family":"Baichuan","version":"Baichuan2","score":66.3},{"place":40,"model":"qwen-14b","company":"qwen","family":"Qwen","version":"Qwen","score":66.3},{"place":41,"model":"qwen-14b-chat","company":"qwen","family":"Qwen","version":"Qwen","score":66.3},{"place":42,"model":"bort-alexa-ai","company":"amazon","family":"Bort","version":"Bort (Alexa AI)","score":65.8},{"place":43,"model":"bert-plus-plus","company":"nyu","family":"BERT++","version":"BERT++","score":64.4},{"place":44,"model":"warp-albert-xxl-v2-few-shot-32-examples","company":"yerevann","family":"WARP","version":"WARP (ALBERT-XXL-V2) - Few-Shot (32 Examples)","score":63.7},{"place":45,"model":"internlm-chat-20b","company":"internlm","family":"InternLM","version":"InternLM","score":61.5},{"place":46,"model":"bert-mtl","company":"ibm","family":"BERT","version":"BERT-mtl","score":61},{"place":47,"model":"pythia-410m","company":"eleutherai","family":"Pythia","version":"Pythia","score":47.1},{"place":48,"model":"pythia-1.4b","company":"eleutherai","family":"Pythia","version":"Pythia","score":44.2},{"place":49,"model":"pythia-6.9b","company":"eleutherai","family":"Pythia","version":"Pythia","score":44.2},{"place":50,"model":"pythia-12b","company":"eleutherai","family":"Pythia","version":"Pythia","score":39.4},{"place":51,"model":"pythia-2.8b","company":"eleutherai","family":"Pythia","version":"Pythia","score":38.5},{"place":52,"model":"pythia-70m","company":"eleutherai","family":"Pythia","version":"Pythia","score":36.5},{"place":53,"model":"pythia-160m","company":"eleutherai","family":"Pythia","version":"Pythia","score":36.5},{"place":54,"model":"pythia-1b","company":"eleutherai","family":"Pythia","version":"Pythia","score":36.5}]},{"id":"wtq","name":"WikiTableQuestions","topic":"Table QA","description":"WikiTableQuestions (MMTab subset, image tables).","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":79.6,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":79.6},{"place":2,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":79.3},{"place":3,"model":"yuan3.0-ultra","company":"yuanlab","family":"Yuan3.0","version":"Yuan3.0","score":77.9},{"place":4,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":76},{"place":5,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":69.8},{"place":6,"model":"gpt-5.1","company":"openai","family":"GPT","version":"GPT-5.1","score":60.8},{"place":7,"model":"internlm-xcomposer2.5","company":"internlm","family":"InternLM","version":"InternLM-XComposer2.5","score":53.6}]},{"id":"xbench-deepsearch","name":"xBench-DeepSearch","topic":"Agentic research","description":"Evaluates multi-hop deep research workflows on xBench DeepSearch tasks.","url":"","leaderboard":"","github":"","paper":"","metric":"avg@3","stars":"","top_model":"GPT-5 (high)","top_percent":77.9,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":42,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":77.9},{"place":2,"model":"gpt-5-thinking","company":"openai","family":"GPT","version":"GPT-5","score":77.8},{"place":3,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":77.8},{"place":4,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":77.8},{"place":5,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":77.1},{"place":6,"model":"toolmind-web-3b","company":"boss","family":"Nanbeige","version":"ToolMind-Web","score":75.1},{"place":7,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":75},{"place":8,"model":"websailor-v2-30b-a3b","company":"tongyi","family":"WebSailor","version":"WebSailor-V2","score":73.7},{"place":9,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":73.1},{"place":10,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":72.4},{"place":11,"model":"minimax-m2","company":"minimax","family":"MiniMax","version":"MiniMax M2","score":72},{"place":12,"model":"webleaper-30b-a3b","company":"tongyi","family":"WebLeaper","version":"WebLeaper","score":72},{"place":13,"model":"deepseek-v3.1","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.1","score":71},{"place":14,"model":"deepseek-v3.2-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":71},{"place":15,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":71},{"place":16,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":71},{"place":17,"model":"glm-4.5","company":"zai","family":"GLM","version":"GLM 4.5","score":70},{"place":18,"model":"glm-4.6","company":"zai","family":"GLM","version":"GLM 4.6","score":70},{"place":19,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":70},{"place":20,"model":"kimi-researcher","company":"moonshotai","family":"Kimi","version":"Kimi Researcher","score":69},{"place":21,"model":"o3","company":"openai","family":"o3","version":"o3","score":67},{"place":22,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":66},{"place":23,"model":"glm-5.2","company":"zai","family":"GLM","version":"GLM 5.2","score":65.8},{"place":24,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":65},{"place":25,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":64.8},{"place":26,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":64.6},{"place":27,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":62.2},{"place":28,"model":"apodex-1.0-mini","company":"apodex","family":"Apodex","version":"Apodex 1.0","score":61.8},{"place":29,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":61.4},{"place":30,"model":"kimi-k2-0905-preview","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":61},{"place":31,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":60.6},{"place":32,"model":"bigbang-v1","company":"endless-frontier","family":"BigBang","version":"BigBang-V1","score":58.4},{"place":33,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":57.2},{"place":34,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":56},{"place":35,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":52.4},{"place":36,"model":"asearcher-web-qwq-v2","company":"antgroup","family":"ASearcher","version":"ASearcher","score":51.1},{"place":37,"model":"step-3.7-flash","company":"stepfun","family":"Step","version":"Step 3.7 Flash","score":50.8},{"place":38,"model":"kimi-k2","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":50},{"place":39,"model":"webdancer-32b","company":"tongyi","family":"WebDancer","version":"WebDancer","score":38.3},{"place":40,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":32.6},{"place":41,"model":"youtu-llm-2b","company":"tencent","family":"Youtu-LLM","version":"Youtu-LLM","score":19.5},{"place":42,"model":"qwen3-4b","company":"qwen","family":"Qwen","version":"Qwen3","score":18.4},{"place":43,"model":"smollm3-3b","company":"huggingface","family":"SmolLM","version":"SmollM3","score":13.9},{"place":44,"model":"qwen3-1.7b","company":"qwen","family":"Qwen","version":"Qwen3","score":11.7}]},{"id":"xbench-deepsearch-2025.05","name":"xBench-DeepSearch (2025.05)","topic":"Agentic research","description":"xBench DeepSearch benchmark May 2025 snapshot.","url":"","leaderboard":"","github":"","paper":"","metric":"avg@3","stars":"","top_model":"Step-3.5 Flash 20260204","top_percent":83.7,"top_model_id":"step-3.5-flash-20260204","top_generation":"Step 3.5 Flash","top_model_base":"Step 3.5 Flash","top_model_family":"Step","top_company":"stepfun","top_open_source":1,"lower_is_better":false,"bench_models":31,"total_models":3854,"placements":[{"place":1,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":83.7},{"place":2,"model":"marco-deepresearch-8b","company":"alibaba","family":"Marco","version":"Marco DeepResearch","score":82},{"place":3,"model":"smtl-30b","company":"oppo","family":"SMTL","version":"SMTL","score":82},{"place":4,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":78},{"place":5,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":77.8},{"place":6,"model":"mirothinker-v1.0-72b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":77.8},{"place":7,"model":"mirothinker-v1.5-235b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":77.1},{"place":8,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":76.7},{"place":9,"model":"re-trac-4b","company":"microsoft","family":"RE-TRAC","version":"RE-TRAC","score":76.6},{"place":10,"model":"kimi-k2-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":76},{"place":11,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":75},{"place":12,"model":"dr-venus-4b-rl","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":74.7},{"place":13,"model":"openseeker-v1-30b-sft","company":"polarseeker","family":"OpenSeeker","version":"OpenSeeker-v1","score":74},{"place":14,"model":"websailor-v2-30b-a3b","company":"tongyi","family":"WebSailor","version":"WebSailor-V2","score":73.7},{"place":15,"model":"mirothinker-v1.5-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.5","score":73.1},{"place":16,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":72},{"place":17,"model":"mirothinker-v1.0-30b","company":"miromind","family":"MiroThinker","version":"MiroThinker-v1.0","score":70.6},{"place":18,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":70},{"place":19,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":69.3},{"place":20,"model":"dr-venus-4b-sft","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":69},{"place":21,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":68.7},{"place":22,"model":"o3","company":"openai","family":"o3","version":"o3","score":67},{"place":23,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":64.6},{"place":24,"model":"deepminer-32b-rl","company":"alibaba","family":"DeepMiner","version":"DeepMiner","score":62},{"place":25,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":60.6},{"place":26,"model":"webexplorer-8b","company":"hkust","family":"WebExplorer","version":"WebExplorer","score":53.7},{"place":27,"model":"offseeker-8b-dpo","company":"offseeker","family":"OffSeeker","version":"OffSeeker","score":49},{"place":28,"model":"offseeker-8b-sft","company":"offseeker","family":"OffSeeker","version":"OffSeeker","score":48},{"place":29,"model":"deepdive-9b-rl","company":"zai","family":"DeepDive","version":"DeepDive","score":38},{"place":30,"model":"deepdive-9b-sft","company":"zai","family":"DeepDive","version":"DeepDive","score":35},{"place":31,"model":"websailor-7b","company":"tongyi","family":"WebSailor","version":"WebSailor","score":34.3}]},{"id":"xbench-deepsearch-2025.10","name":"xBench-DeepSearch (2025.10)","topic":"Agentic research","description":"xBench DeepSearch benchmark October 2025 snapshot.","url":"","leaderboard":"","github":"","paper":"","metric":"avg@3","stars":"","top_model":"Kimi-K2.6 Thinking","top_percent":90,"top_model_id":"kimi-k2.6-thinking","top_generation":"Kimi K2.6","top_model_base":"Kimi K2.6","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":1,"lower_is_better":false,"bench_models":37,"total_models":3854,"placements":[{"place":1,"model":"kimi-k2.6-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":90},{"place":2,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":90},{"place":3,"model":"agents-a1-4b","company":"internlm","family":"Agents-A1","version":"Agents-A1","score":90},{"place":4,"model":"kimi-k2.6","company":"moonshotai","family":"Kimi","version":"Kimi K2.6","score":90},{"place":5,"model":"agents-a1","company":"internlm","family":"Agents","version":"A1","score":86},{"place":6,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":84},{"place":7,"model":"nex-n2-mini","company":"nex-agi","family":"Nex","version":"N2","score":82},{"place":8,"model":"deepseek-v4-pro","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":80},{"place":9,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":77},{"place":10,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":75},{"place":11,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":75},{"place":12,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":73},{"place":13,"model":"mirothinker-h1","company":"miromind","family":"MiroThinker","version":"MiroThinker H1","score":72},{"place":14,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":71},{"place":15,"model":"arex-base","company":"baai","family":"AREX","version":"AREX","score":71},{"place":16,"model":"deepseek-v4-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":69},{"place":17,"model":"mirothinker-1.7","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":62},{"place":18,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":61},{"place":19,"model":"mirothinker-1.7-mini","company":"miromind","family":"MiroThinker","version":"MiroThinker 1.7","score":57.2},{"place":20,"model":"arex-turbo","company":"baai","family":"AREX","version":"AREX","score":57},{"place":21,"model":"step-3.5-flash-20260204","company":"stepfun","family":"Step","version":"Step 3.5 Flash","score":56.3},{"place":22,"model":"deepseek-v3.2","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":55.7},{"place":23,"model":"tongyi-deepresearch","company":"tongyi","family":"Tongyi","version":"Tongyi","score":55},{"place":24,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":53},{"place":25,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":53},{"place":26,"model":"glm-4.7","company":"zai","family":"GLM","version":"GLM 4.7","score":52.3},{"place":27,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.3},{"place":28,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":46},{"place":29,"model":"mimo-v2-flash","company":"xiaomi","family":"MiMo","version":"MiMo V2","score":44},{"place":30,"model":"minimax-m2.1","company":"minimax","family":"MiniMax","version":"MiniMax M2.1","score":43},{"place":31,"model":"marco-deepresearch-8b","company":"alibaba","family":"Marco","version":"Marco DeepResearch","score":42},{"place":32,"model":"dr-venus-4b-rl","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":40.7},{"place":33,"model":"nanbeige4.1-3b","company":"boss","family":"Nanbeige","version":"Nanbeige4.1","score":39},{"place":34,"model":"toolmind-web-3b","company":"boss","family":"Nanbeige","version":"ToolMind-Web","score":37},{"place":35,"model":"dr-venus-4b-sft","company":"antgroup","family":"DR-Venus","version":"DR-Venus","score":35.3},{"place":36,"model":"agentcpm-explore","company":"openbmb","family":"AgentCPM","version":"AgentCPM","score":34},{"place":37,"model":"mirothinker-v1.0-8b","company":"miromind","family":"MiroThinker","version":"MiroThinker v1.0","score":34},{"place":38,"model":"webexplorer-8b","company":"hkust","family":"WebExplorer","version":"WebExplorer","score":23}]},{"id":"xcopa","name":"XCOPA","topic":"Cross-lingual commonsense causal reasoning","description":"Multilingual extension of COPA causal commonsense reasoning in 11 languages.","url":"https://huggingface.co/datasets/cambridgeltl/xcopa","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Zhipu GLM 4-9B-Chat","top_percent":80.1,"top_model_id":"glm-4-9b-chat","top_generation":"GLM 4","top_model_base":"GLM 4 9B","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":22,"total_models":3854,"placements":[{"place":1,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":80.1},{"place":2,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":73.3},{"place":3,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":69.9},{"place":4,"model":"apertus-v1.5-70b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":68},{"place":5,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":65.6},{"place":6,"model":"apertus-v1.5-8b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":64.9},{"place":7,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":64.1},{"place":8,"model":"apertus-v1.1-4b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":63.82},{"place":9,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":63.8},{"place":10,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":62.5},{"place":11,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":62.1},{"place":12,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":61.82},{"place":13,"model":"eurollm-22b-base","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":61.3},{"place":14,"model":"apertus-v1.1-1.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":59.76},{"place":15,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":59.5},{"place":16,"model":"marin-32b-base","company":"marin","family":"Marin","version":"Marin 32B","score":58.6},{"place":17,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":58.35},{"place":18,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":57},{"place":19,"model":"apertus-v1.1-0.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":55.49},{"place":20,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":55.1},{"place":21,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":54.96},{"place":22,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":53.51}]},{"id":"xdev-bench-hard","name":"xdev-bench-hard","topic":"Cybersecurity","description":"Moonshot internal offensive-security / exploit-development benchmark; problems solved (pass@3).","url":"https://www.kimi.ai/blog/kimi-k3-1-pro","leaderboard":"","github":"","paper":"","metric":"pass@3","stars":"","top_model":"GPT-5.6 Sol","top_percent":100,"top_model_id":"gpt-5.6-sol","top_generation":"GPT-5.6","top_model_base":"GPT-5.6 Sol","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":100},{"place":2,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":85.7},{"place":3,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":81},{"place":4,"model":"glm-5.3","company":"zai","family":"GLM","version":"GLM 5.3","score":57.1},{"place":5,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":33.3}]},{"id":"xlrs-bench","name":"XLRS-Bench","topic":"Remote sensing","description":"Remote sensing benchmark for evaluating multimodal AI on satellite and aerial imagery.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Gemini 3.1 Pro","top_percent":54.27,"top_model_id":"gemini-3.1-pro","top_generation":"Gemini 3.1","top_model_base":"Gemini 3.1 Pro","top_model_family":"Gemini","top_company":"google","top_open_source":0,"lower_is_better":false,"bench_models":18,"total_models":3854,"placements":[{"place":1,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":54.27},{"place":2,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":52.8},{"place":3,"model":"intern-s2-preview-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":51.97},{"place":4,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":51.84},{"place":5,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":51.8},{"place":6,"model":"intern-s2-397b","company":"internlm","family":"Intern","version":"Intern-S2","score":51.38},{"place":7,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":51.2},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":50.96},{"place":9,"model":"intern-s2-preview","company":"internlm","family":"Intern","version":"Intern-S2","score":50.71},{"place":10,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":50.4},{"place":11,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":50.11},{"place":12,"model":"kimi-k2.7-code","company":"moonshotai","family":"Kimi","version":"Kimi K2.7","score":49.9},{"place":13,"model":"gemini-3.1-flash-lite","company":"google","family":"Gemini","version":"Gemini 3.1","score":49.29},{"place":14,"model":"intern-s1-pro","company":"internlm","family":"Intern","version":"Intern-S1","score":48.41},{"place":15,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":46.92},{"place":16,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":46.4},{"place":17,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":45.42},{"place":18,"model":"claude-4.5-haiku","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.86},{"place":19,"model":"gpt-5.4-nano","company":"openai","family":"GPT","version":"GPT-5.4","score":42.71}]},{"id":"xnli","name":"XNLI","topic":"Cross-lingual NLI","description":"Cross-lingual natural language inference benchmark (MultiNLI translated into 15 languages).","url":"https://huggingface.co/datasets/facebook/xnli","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Decider 4B (Mapika)","top_percent":88.6,"top_model_id":"mapika-decider-4b","top_generation":"Decider","top_model_base":"Decider","top_model_family":"Decider","top_company":"mapika","top_open_source":1,"lower_is_better":false,"bench_models":24,"total_models":3854,"placements":[{"place":1,"model":"mapika-decider-4b","company":"mapika","family":"Decider","version":"Decider","score":88.6},{"place":2,"model":"d1-3b","company":"liquidai","family":"d1","version":"d1","score":85},{"place":3,"model":"mapika-decider-2b","company":"mapika","family":"Decider","version":"Decider","score":85},{"place":4,"model":"d1-omni-600m","company":"liquidai","family":"d1","version":"d1","score":74.7},{"place":5,"model":"apertus-v1.5-70b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":46.3},{"place":6,"model":"apertus-70b","company":"swissai","family":"Apertus","version":"Apertus","score":45.9},{"place":7,"model":"llama-3.1-8b-base","company":"meta","family":"Llama","version":"Llama 3.1","score":45.6},{"place":8,"model":"apertus-v1.5-8b-base","company":"swissai","family":"Apertus","version":"Apertus 1.5","score":45.3},{"place":9,"model":"apertus-v1.1-4b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":45.03},{"place":10,"model":"k2-v2","company":"mbzuai","family":"K2","version":"K2 V2","score":44.1},{"place":11,"model":"apertus-8b","company":"swissai","family":"Apertus","version":"Apertus","score":44.1},{"place":12,"model":"eurollm-22b-base","company":"eurollm","family":"EuroLLM","version":"EuroLLM","score":44.1},{"place":13,"model":"nemotron-3.5-lightning-30b-a3b-base","company":"nvidia","family":"Nemotron","version":"Nemotron 3.5","score":43.4},{"place":14,"model":"qwen3-4b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":43},{"place":15,"model":"apertus-v1.1-1.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":42.94},{"place":16,"model":"marin-8b-base","company":"marin","family":"Marin","version":"Marin 8B","score":42.4},{"place":17,"model":"olmo-3-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":42.4},{"place":18,"model":"marin-32b-base","company":"marin","family":"Marin","version":"Marin 32B","score":42.3},{"place":19,"model":"qwen3-1.7b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":41.66},{"place":20,"model":"apertus-v1.1-0.5b","company":"swissai","family":"Apertus","version":"Apertus 1.1","score":41.51},{"place":21,"model":"qwen3.5-9b-base","company":"qwen","family":"Qwen","version":"Qwen3.5","score":39.8},{"place":22,"model":"olmo-3-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":39.6},{"place":23,"model":"qwen3-0.6b-base","company":"qwen","family":"Qwen","version":"Qwen3","score":39.55},{"place":24,"model":"smollm2-1.7b-base","company":"huggingface","family":"SmolLM","version":"SmolLM2","score":37.57}]},{"id":"xorqa-in","name":"XorQA-IN","topic":"Indic languages","description":"Cross-lingual open-retrieval QA in Indian languages (IndicXTREME), F1.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"gnani-evon-v3.3-30B-A3B","top_percent":41.83,"top_model_id":"gnani-evon-v3.3-30b-a3b","top_generation":"gnani-evon-v3.3","top_model_base":"gnani-evon v3.3 30B A3B","top_model_family":"gnani-evon","top_company":"gnani","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gnani-evon-v3.3-30b-a3b","company":"gnani","family":"gnani-evon","version":"gnani-evon-v3.3","score":41.83},{"place":2,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":34.98},{"place":3,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":34.47},{"place":4,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":30.16},{"place":5,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":22.86}]},{"id":"xpertbench-edu","name":"XpertBench (Edu)","topic":"Economics/education","description":"XpertBench education domain subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":56.9,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":56.9},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":49.2},{"place":3,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.9},{"place":4,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":47.9},{"place":5,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.5}]},{"id":"xpertbench-fin","name":"XpertBench (Fin)","topic":"Economics/finance","description":"XpertBench finance domain subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":64.5,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":64.5},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":62},{"place":3,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":56.1},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":44.5},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":30.3}]},{"id":"xpertbench-humanities","name":"XpertBench (Humanities)","topic":"Economics/humanities","description":"XpertBench humanities domain subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":68.5,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":68.5},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":68.2},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":60.2},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":54.9},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":52.3}]},{"id":"xpertbench-law","name":"XpertBench (Law)","topic":"Economics/legal","description":"XpertBench legal domain subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Sonnet 4.5","top_percent":58.7,"top_model_id":"claude-sonnet-4.5","top_generation":"Claude 4.5","top_model_base":"Claude Sonnet 4.5","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":58.7},{"place":2,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":55.2},{"place":3,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":54.7},{"place":4,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":52.3},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":47.3}]},{"id":"xpertbench-research","name":"XpertBench (Research)","topic":"Economics/research","description":"XpertBench research domain subset.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":48.2,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":48.2},{"place":2,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":34.9},{"place":3,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":31.4},{"place":4,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":27.5},{"place":5,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":25.5}]},{"id":"xquad","name":"XQuAD","topic":"Multilingual QA","description":"Cross-lingual Question Answering Dataset: SQuAD v1.1 subset professionally translated into 10 languages.","url":"https://github.com/google-deepmind/xquad","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"T5Gemma 2 4B-4B","top_percent":70.6,"top_model_id":"t5gemma-2-4b-4b","top_generation":"T5Gemma 2","top_model_base":"T5Gemma 2 4B-4B","top_model_family":"Gemma","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":3,"total_models":3854,"placements":[{"place":1,"model":"t5gemma-2-4b-4b","company":"google","family":"Gemma","version":"T5Gemma 2","score":70.6},{"place":2,"model":"t5gemma-2-1b-1b","company":"google","family":"Gemma","version":"T5Gemma 2","score":63.1},{"place":3,"model":"t5gemma-2-270m-270m","company":"google","family":"Gemma","version":"T5Gemma 2","score":40.8}]},{"id":"xquad-in","name":"XQuAD-IN","topic":"Indic languages","description":"Extractive QA (XQuAD) in Indian languages (IndicXTREME), F1.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"gnani-evon-v3.3-30B-A3B","top_percent":64.59,"top_model_id":"gnani-evon-v3.3-30b-a3b","top_generation":"gnani-evon-v3.3","top_model_base":"gnani-evon v3.3 30B A3B","top_model_family":"gnani-evon","top_company":"gnani","top_open_source":1,"lower_is_better":false,"bench_models":5,"total_models":3854,"placements":[{"place":1,"model":"gnani-evon-v3.3-30b-a3b","company":"gnani","family":"gnani-evon","version":"gnani-evon-v3.3","score":64.59},{"place":2,"model":"sarvam-105b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":56.65},{"place":3,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":55.09},{"place":4,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":42.21},{"place":5,"model":"sarvam-30b","company":"sarvam","family":"Sarvam","version":"Sarvam","score":37.86}]},{"id":"xstest","name":"XSTest","topic":"Safety","description":"XSTest safety benchmark.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Qwen3.5-9B","top_percent":97.6,"top_model_id":"qwen3.5-9b","top_generation":"Qwen3.5","top_model_base":"Qwen3.5 9B","top_model_family":"Qwen","top_company":"qwen","top_open_source":1,"lower_is_better":false,"bench_models":17,"total_models":3854,"placements":[{"place":1,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":97.6},{"place":2,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":96.8},{"place":3,"model":"ministral-3-14b-reasoning","company":"mistral","family":"Ministral","version":"Ministral 3","score":96.8},{"place":4,"model":"ministral-3-14b-instruct","company":"mistral","family":"Ministral","version":"Ministral 3","score":96.8},{"place":5,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":95.6},{"place":6,"model":"gemma-4-e4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":95.2},{"place":7,"model":"iquest-coder-v1-40b-thinking","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":94.3},{"place":8,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":93.2},{"place":9,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":93.2},{"place":10,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":91.2},{"place":11,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":91.2},{"place":12,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":91.2},{"place":13,"model":"mellum2-12b-a2.5b-thinking-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":90.8},{"place":14,"model":"qwen2.5-coder-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":90.6},{"place":15,"model":"qwen3-coder-480b-a35b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":90.1},{"place":16,"model":"mellum2-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2","score":89.6},{"place":17,"model":"iquest-coder-v1-40b-instruct","company":"iquest","family":"IQuest Coder","version":"IQuest Coder V1","score":89.3},{"place":18,"model":"mellum2.1-12b-a2.5b-thinking","company":"jetbrains","family":"Mellum","version":"Mellum2.1","score":88.8},{"place":19,"model":"seed-coder-8b-instruct","company":"bytedance","family":"Seed","version":"Seed Coder","score":86.3},{"place":20,"model":"mellum2-12b-a2.5b-instruct","company":"jetbrains","family":"Mellum","version":"Mellum2","score":81.2},{"place":21,"model":"mellum2-12b-a2.5b-instruct-sft","company":"jetbrains","family":"Mellum","version":"Mellum2","score":78.3}]},{"id":"xstorycloze","name":"XStoryCloze","topic":"Commonsense reasoning (multilingual)","description":"Multilingual StoryCloze: choose the correct story ending in 11 languages.","url":"https://huggingface.co/datasets/juletxara/xstory_cloze","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2112.10668","metric":"percent","stars":"","top_model":"Zhipu GLM 4-9B-Chat","top_percent":90.7,"top_model_id":"glm-4-9b-chat","top_generation":"GLM 4","top_model_base":"GLM 4 9B","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":90.7},{"place":2,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":84.7}]},{"id":"xwinograd","name":"XWinograd","topic":"Coreference reasoning (multilingual)","description":"Multilingual Winograd schema benchmark (en, fr, jp, pt, ru, zh).","url":"https://huggingface.co/datasets/Muennighoff/xwinograd","leaderboard":"","github":"","paper":"https://arxiv.org/abs/2211.01786","metric":"percent","stars":"","top_model":"Zhipu GLM 4-9B-Chat","top_percent":73.1,"top_model_id":"glm-4-9b-chat","top_generation":"GLM 4","top_model_base":"GLM 4 9B","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":2,"total_models":3854,"placements":[{"place":1,"model":"glm-4-9b-chat","company":"zai","family":"GLM","version":"GLM 4","score":73.1},{"place":2,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":61.7}]},{"id":"yc-bench","name":"YC-Bench","topic":"Long-horizon business simulation","description":"YC-Bench: long-horizon startup-management simulation; metric is final assets of the fund in millions of USD.","url":"","leaderboard":"","github":"https://github.com/collinear-ai/yc-bench","paper":"","metric":"usd_millions","stars":"","top_model":"Claude Opus 4.7","top_percent":2.2,"top_model_id":"claude-opus-4.7","top_generation":"Claude 4.7","top_model_base":"Claude Opus 4.7","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":11,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":2.2},{"place":2,"model":"minimax-m3","company":"minimax","family":"MiniMax","version":"MiniMax M3","score":2.1},{"place":3,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":1.3},{"place":4,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":1.1},{"place":5,"model":"nanbeige4.3-33b","company":"boss","family":"Nanbeige","version":"Nanbeige4.3","score":1.025437},{"place":6,"model":"qwen3.8-27b","company":"qwen","family":"Qwen","version":"Qwen3.8","score":0.64129},{"place":7,"model":"muse-glimmer-30b","company":"meta","family":"Muse","version":"Muse Glimmer","score":0.513978},{"place":8,"model":"deepseek-v4-pro-thinking-max","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":0.5},{"place":9,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":0.265152},{"place":10,"model":"claude-sonnet-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":0.1},{"place":11,"model":"minimax-m2.7","company":"minimax","family":"MiniMax","version":"MiniMax M2.7","score":0}]},{"id":"zclawbench","name":"ZClawBench","topic":"Agent tasks (OpenClaw)","description":"Z.ai end-to-end benchmark for OpenClaw agent workflows (environment setup, software dev, retrieval, data analysis, content creation).","url":"https://docs.z.ai/guides/llm/glm-5-turbo","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Claude Opus 4.6","top_percent":62.3,"top_model_id":"claude-opus-4.6","top_generation":"Claude 4.6","top_model_base":"Claude Opus 4.6","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":4,"total_models":3854,"placements":[{"place":1,"model":"claude-opus-4.6","company":"anthropic","family":"Claude","version":"Claude 4.6","score":62.3},{"place":2,"model":"glm-5-turbo","company":"zai","family":"GLM","version":"GLM 5","score":60.6},{"place":3,"model":"glm-5v-turbo","company":"zai","family":"GLM","version":"GLM 5V","score":57.6},{"place":4,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":49.1}]},{"id":"zebralogic","name":"ZebraLogic","topic":"Logical reasoning","description":"Logical reasoning benchmark assessing complex pattern and rule inference.","url":"","leaderboard":"https://huggingface.co/spaces/allenai/ZeroEval","github":"","paper":"","metric":"percent","stars":"","top_model":"GPT-5 (high)","top_percent":98.8,"top_model_id":"gpt-5-high","top_generation":"GPT-5","top_model_base":"GPT-5","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":147,"total_models":3854,"placements":[{"place":1,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":98.8},{"place":2,"model":"deepseek-v3.2-thinking","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3.2","score":97.6},{"place":3,"model":"ernie-5.0","company":"baidu","family":"ERNIE","version":"ERNIE 5.0","score":96.5},{"place":4,"model":"qwen3-vl-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":96.1},{"place":5,"model":"o3","company":"openai","family":"o3","version":"o3","score":95.8},{"place":6,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":95.5},{"place":7,"model":"deepseek-r1-0528","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":95.1},{"place":8,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":95.1},{"place":9,"model":"qwen3-moe-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":94.2},{"place":10,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":92.9},{"place":11,"model":"grok-3-mini-fast-high-reasoning","company":"xai","family":"Grok","version":"Grok 3","score":92.6},{"place":12,"model":"o3-mini-2025-01-31-high","company":"openai","family":"o3","version":"o3","score":91.7},{"place":13,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":91.6},{"place":14,"model":"qwen3-vl-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":91.2},{"place":15,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":90.97},{"place":16,"model":"qwen3-30b-a3b-instruct-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":90},{"place":17,"model":"qwen3-30b-a3b-thinking-2507","company":"qwen","family":"Qwen","version":"Qwen3","score":89.5},{"place":18,"model":"kimi-k2-instruct","company":"moonshotai","family":"Kimi","version":"Kimi K2","score":89},{"place":19,"model":"llada2.1-flash-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":88.9},{"place":20,"model":"o3-mini-2025-01-31-med","company":"openai","family":"o3","version":"o3","score":88.9},{"place":21,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.8},{"place":22,"model":"qwen3-14b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.5},{"place":23,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":88.3},{"place":24,"model":"qwen3-32b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":88.3},{"place":25,"model":"ling-flash-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":87.6},{"place":26,"model":"minimax-m1-80k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":86.8},{"place":27,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":86.7},{"place":28,"model":"qwen3-8b-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":85.2},{"place":29,"model":"seed-thinking-v1.5","company":"bytedance","family":"Seed","version":"Seed 1.5","score":84.4},{"place":30,"model":"llada2.1-flash-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":84.2},{"place":31,"model":"deepseek-v3-0324","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":84},{"place":32,"model":"llada2.0-flash","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":82.3},{"place":33,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":81.8},{"place":34,"model":"o1-2024-12-17","company":"openai","family":"o1","version":"o1","score":81},{"place":35,"model":"grok-3-mini-fast-low-reasoning","company":"xai","family":"Grok","version":"Grok 3","score":80.7},{"place":36,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":80.3},{"place":37,"model":"minimax-m1-40k","company":"minimax","family":"MiniMax","version":"MiniMax M1","score":80.1},{"place":38,"model":"olmo-3.1-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":80.1},{"place":39,"model":"ling-mini-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":79.85},{"place":40,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":79.7},{"place":41,"model":"deepseek-r1","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":78.7},{"place":42,"model":"llada2.1-mini-q","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":77.1},{"place":43,"model":"motif-2-12.7b-reasoning","company":"motif","family":"Motif","version":"Motif 2","score":77},{"place":44,"model":"qwen3-omni-flash-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":76.1},{"place":45,"model":"qwen3-omni-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3","score":76},{"place":46,"model":"olmo-3-think-32b","company":"allenai","family":"OLMo","version":"OLMo 3","score":76},{"place":47,"model":"o3-mini-2025-01-31-low","company":"openai","family":"o3","version":"o3","score":74.8},{"place":48,"model":"olmo-3-think-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":74.5},{"place":49,"model":"o1-preview-2024-09-12","company":"openai","family":"o1","version":"o1","score":71.4},{"place":50,"model":"o1-preview","company":"openai","family":"o1","version":"o1","score":71.4},{"place":51,"model":"olmo-3-think-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":70.5},{"place":52,"model":"motif-2-12.7b-instruct","company":"motif","family":"Motif","version":"Motif 2","score":69.5},{"place":53,"model":"deepseek-r1-distill-qwen-32b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":69.4},{"place":54,"model":"llada2.1-mini-s","company":"antgroup","family":"LLaDA","version":"LLaDA 2.1","score":68.5},{"place":55,"model":"olmo-3-think-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":66.5},{"place":56,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":64.3},{"place":57,"model":"llada2.0-mini","company":"antgroup","family":"LLaDA","version":"LLaDA 2.0","score":64.2},{"place":58,"model":"olmo-3.1-instruct-32b","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":61.7},{"place":59,"model":"nvidia-nemotron-nano-9b-v2","company":"nvidia","family":"Nemotron","version":"Nemotron Nano v2","score":60.8},{"place":60,"model":"olmo-3-think-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":60.6},{"place":61,"model":"o1-mini-2024-09-12","company":"openai","family":"o1","version":"o1","score":59.7},{"place":62,"model":"claude-opus-4","company":"anthropic","family":"Claude","version":"Claude 4","score":59.3},{"place":63,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":58.5},{"place":64,"model":"ernie-4.5","company":"baidu","family":"ERNIE","version":"ERNIE 4.5","score":58.1},{"place":65,"model":"gemini-2.5-flash","company":"google","family":"Gemini","version":"Gemini 2.5","score":57.9},{"place":66,"model":"olmo-3-think-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":57.9},{"place":67,"model":"grok-3-beta","company":"xai","family":"Grok","version":"Grok 3","score":57.9},{"place":68,"model":"deepseek-r1-lite-preview","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":56.6},{"place":69,"model":"gpt-4.1","company":"openai","family":"GPT","version":"GPT-4.1","score":56.3},{"place":70,"model":"olmo-hybrid-think-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":55.1},{"place":71,"model":"gpt-4o-0327","company":"openai","family":"GPT","version":"GPT-4o","score":52.6},{"place":72,"model":"olmo-3.1-instruct-32b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":51.1},{"place":73,"model":"deepseek-v3","company":"deepseek","family":"DeepSeek","version":"DeepSeek V3","score":42.1},{"place":74,"model":"qwen3-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3","score":37.7},{"place":75,"model":"qwen-3-235b-a22b-nonthinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.7},{"place":76,"model":"qwen3-8b-non-thinking","company":"qwen","family":"Qwen","version":"Qwen3","score":37.48},{"place":77,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":36.2},{"place":78,"model":"openthinker3-7b","company":"openthinker","family":"OpenThinker","version":"OpenThinker3","score":34.9},{"place":79,"model":"claude-3.5-sonnet-20240620","company":"anthropic","family":"Claude","version":"Claude 3.5","score":33.4},{"place":80,"model":"claude-3.5-sonnet-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":33.4},{"place":81,"model":"qwen3-30b-a3b","company":"qwen","family":"Qwen","version":"Qwen3","score":33.2},{"place":82,"model":"qwen3-14b","company":"qwen","family":"Qwen","version":"Qwen3","score":33},{"place":83,"model":"olmo-3-instruct-7b","company":"allenai","family":"OLMo","version":"OLMo 3","score":32.9},{"place":84,"model":"llama-3.1-405b-instruct-fp8","company":"meta","family":"Llama","version":"Llama 3.1","score":32.6},{"place":85,"model":"gpt-4o-2024-08-06","company":"openai","family":"GPT","version":"GPT-4o","score":31.7},{"place":86,"model":"olmo-3.1-instruct-32b-sft","company":"allenai","family":"OLMo","version":"OLMo 3.1","score":30.6},{"place":87,"model":"gemini-1.5-pro-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":30.5},{"place":88,"model":"llama-3.1-405b-instruct-bf16","company":"meta","family":"Llama","version":"Llama 3.1","score":30.1},{"place":89,"model":"ling-2.6-1t-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":30},{"place":90,"model":"chatgpt-4o-latest-20240903","company":"openai","family":"GPT","version":"GPT-4o","score":29.9},{"place":91,"model":"qwen3-32b-nothinking","company":"qwen","family":"Qwen","version":"Qwen3","score":29.2},{"place":92,"model":"olmo-hybrid-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":29.1},{"place":93,"model":"mistral-large-2407","company":"mistral","family":"Mistral","version":"Mistral","score":29},{"place":94,"model":"qwen3-32b","company":"qwen","family":"Qwen","version":"Qwen3","score":28.4},{"place":95,"model":"olmo-3-instruct-7b-dpo","company":"allenai","family":"OLMo","version":"OLMo 3","score":28.4},{"place":96,"model":"gpt-4-turbo-2024-04-09","company":"openai","family":"GPT","version":"GPT-4","score":28.4},{"place":97,"model":"gpt-4o-2024-05-13","company":"openai","family":"GPT","version":"GPT-4o","score":28.2},{"place":98,"model":"gpt-4o","company":"openai","family":"GPT","version":"GPT-4o","score":28.2},{"place":99,"model":"grok-2-1212","company":"xai","family":"Grok","version":"Grok 2","score":27.7},{"place":100,"model":"gpt-4-0314","company":"openai","family":"GPT","version":"GPT-4","score":27.1},{"place":101,"model":"claude-3-opus-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":27},{"place":102,"model":"qwen2.5-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.6},{"place":103,"model":"deepseek-r1-distill-qwen-7b","company":"deepseek","family":"DeepSeek","version":"DeepSeek R1","score":26.1},{"place":104,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":26.1},{"place":105,"model":"ling-1t-base","company":"antgroup","family":"Ling","version":"Ling 1T","score":26},{"place":106,"model":"qwen3-8b","company":"qwen","family":"Qwen","version":"Qwen3","score":25.4},{"place":107,"model":"gemini-1.5-pro-exp-0801","company":"google","family":"Gemini","version":"Gemini 1.0","score":25.2},{"place":108,"model":"gemini-1.5-flash-exp-0827","company":"google","family":"Gemini","version":"Gemini 1.0","score":25},{"place":109,"model":"llama-3.1-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":24.9},{"place":110,"model":"gemma-3-27b-it","company":"google","family":"Gemma","version":"Gemma 3","score":24.8},{"place":111,"model":"qwen2.5-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":24.1},{"place":112,"model":"deepseek-v2-chat-0628","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder","score":22.7},{"place":113,"model":"openreasoning-nemotron-7b","company":"nvidia","family":"Nemotron","version":"Nemotron OpenReasoning","score":22.4},{"place":114,"model":"deepseek-v2.5","company":"deepseek","family":"DeepSeek","version":"DeepSeek V2.5","score":22.1},{"place":115,"model":"qwen2-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":21.4},{"place":116,"model":"deepseek-coder-v2-instruct","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":21.1},{"place":117,"model":"ling-2.6-flash-base","company":"antgroup","family":"Ling","version":"Ling 2.6","score":21},{"place":118,"model":"deepseek-coder-v2-instruct-0724","company":"deepseek","family":"DeepSeek","version":"DeepSeek Coder V2","score":20.5},{"place":119,"model":"ling-flash-base-2.0","company":"antgroup","family":"Ling","version":"Ling 2.0","score":20.1},{"place":120,"model":"gpt-4o-mini-2024-07-18","company":"openai","family":"GPT","version":"GPT-4o","score":20.1},{"place":121,"model":"gemini-1.5-flash","company":"google","family":"Gemini","version":"Gemini 1.5","score":19.4},{"place":122,"model":"gemini-1.5-pro","company":"google","family":"Gemini","version":"Gemini 1.5","score":19.4},{"place":123,"model":"yi-large-preview","company":"01ai","family":"Yi","version":"Yi Large","score":18.9},{"place":124,"model":"yi-large","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":18.8},{"place":125,"model":"claude-3.5-haiku-20241022","company":"anthropic","family":"Claude","version":"Claude 3.5","score":18.7},{"place":126,"model":"claude-3-sonnet-20240229","company":"anthropic","family":"Claude","version":"Claude 3","score":18.7},{"place":127,"model":"olmo-3-7b-sft","company":"allenai","family":"OLMo","version":"OLMo 3","score":18},{"place":128,"model":"granite-3.3-8b-instruct","company":"IBM","family":"Granite","version":"Granite 3.3","score":17.6},{"place":129,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":17.2},{"place":130,"model":"olmo-hybrid-instruct-7b-sft","company":"allenai","family":"OLMo","version":"Olmo Hybrid","score":17},{"place":131,"model":"llama-3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":16.8},{"place":132,"model":"athene-70b","company":"nvidia","family":"Athene","version":"Athene V2","score":16.7},{"place":133,"model":"gemma-2-27b-it","company":"google","family":"Gemma","version":"Gemma 2","score":16.3},{"place":134,"model":"claude-3-haiku-20240307","company":"anthropic","family":"Claude","version":"Claude 3","score":14.3},{"place":135,"model":"command-r-plus","company":"cohere","family":"Command","version":"Command","score":13.9},{"place":136,"model":"olmo-2-0325-32b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":13.3},{"place":137,"model":"reka-core-20240501","company":"reka","family":"Reka","version":"Reka Core","score":13},{"place":138,"model":"gemma-2-9b-it","company":"google","family":"Gemma","version":"Gemma 2","score":12.8},{"place":139,"model":"llama-3.1-8b-instruct","company":"meta","family":"Llama","version":"Llama 3.1","score":12.8},{"place":140,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":12},{"place":141,"model":"llama-3-8b-instruct","company":"meta","family":"Llama","version":"Llama 3","score":11.9},{"place":142,"model":"mistral-nemo-instruct-2407","company":"mistral","family":"Mistral","version":"Mistral","score":11.8},{"place":143,"model":"phi-3-mini-4k-instruct","company":"microsoft","family":"Phi-3-mini-4k-instruct","version":"Phi-3-mini-4k-instruct","score":11.6},{"place":144,"model":"yi-1.5-34b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":11.5},{"place":145,"model":"qwen2.5-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":10.7},{"place":146,"model":"gpt-3.5-turbo-0125","company":"openai","family":"GPT","version":"GPT-3.5","score":10.1},{"place":147,"model":"command-r","company":"cohere","family":"Command","version":"Command","score":9.9},{"place":148,"model":"reka-flash-21b-20240226","company":"reka","family":"Reka","version":"Reka Flash 21B 20240226","score":9.3},{"place":149,"model":"apertus-70b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":9},{"place":150,"model":"mathstral-7b","company":"mistral","family":"Mathstral","version":"Mathstral","score":9},{"place":151,"model":"mixtral-8x7b-instruct-v0.1","company":"mistral","family":"Mixtral","version":"Mixtral v0.1","score":8.7},{"place":152,"model":"qwen2-7b-instruct","company":"qwen","family":"Qwen","version":"Qwen2","score":8.4},{"place":153,"model":"llama-3.2-3b-instruct","company":"meta","family":"Llama","version":"Llama 3.2","score":7.4},{"place":154,"model":"phi-3.5-mini-instruct","company":"microsoft","family":"Phi","version":"Phi 3.5","score":6.4},{"place":155,"model":"olmo-2-1124-7b-instruct","company":"allenai","family":"OLMo","version":"OLMo 2","score":5.3},{"place":156,"model":"apertus-8b-instruct","company":"swissai","family":"Apertus","version":"Apertus","score":5.3},{"place":157,"model":"qwen-2.5-3b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5","score":4.8},{"place":158,"model":"gemma-2-2b-it","company":"google","family":"Gemma","version":"Gemma 2","score":4.2},{"place":159,"model":"yi-1.5-9b-chat","company":"01ai","family":"Yi 1.5","version":"Yi 1.5","score":2.3}]},{"id":"zerobench","name":"ZeroBench","topic":"Zero-shot generalization","description":"Evaluates zero-shot performance across diverse tasks without task-specific finetuning.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"GLM-4.5V","top_percent":23.4,"top_model_id":"glm-4.5v","top_generation":"GLM 4.5V","top_model_base":"GLM 4.5V","top_model_family":"GLM","top_company":"zai","top_open_source":1,"lower_is_better":false,"bench_models":48,"total_models":3854,"placements":[{"place":1,"model":"glm-4.5v","company":"zai","family":"GLM","version":"GLM 4.5V","score":23.4},{"place":2,"model":"step-3","company":"stepfun","family":"Step","version":"Step 3","score":23},{"place":3,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":23},{"place":4,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":23},{"place":5,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":22},{"place":6,"model":"glm-4.1v","company":"zai","family":"GLM","version":"GLM 4.1V","score":19.2},{"place":7,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":18},{"place":8,"model":"gemma-3-27b-vl","company":"google","family":"Gemma","version":"Gemma 3","score":17.7},{"place":9,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":17},{"place":10,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":17},{"place":11,"model":"kimi-vl-a3b-thinking-2506","company":"moonshotai","family":"Kimi","version":"Kimi VL","score":16.2},{"place":12,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":13},{"place":13,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12},{"place":14,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":12},{"place":15,"model":"seed1.8","company":"bytedance","family":"Seed","version":"Seed 1.8","score":11},{"place":16,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":11},{"place":17,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":10},{"place":18,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":10},{"place":19,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":10},{"place":20,"model":"kimi-k2.5-thinking","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":9},{"place":21,"model":"gpt-5.2-thinking-xhigh","company":"openai","family":"GPT","version":"GPT-5.2","score":9},{"place":22,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":9},{"place":23,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":9},{"place":24,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":9},{"place":25,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":8},{"place":26,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":8},{"place":27,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":8},{"place":28,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":6},{"place":29,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":5},{"place":30,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":5},{"place":31,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4},{"place":32,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":4},{"place":33,"model":"gpt-5-high","company":"openai","family":"GPT","version":"GPT-5","score":4},{"place":34,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4},{"place":35,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":4},{"place":36,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":4},{"place":37,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":3},{"place":38,"model":"claude-opus-4.5-thinking","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3},{"place":39,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":3},{"place":40,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":3},{"place":41,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":3},{"place":42,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":3},{"place":43,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":2},{"place":44,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":2},{"place":45,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":2},{"place":46,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":1},{"place":47,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":1},{"place":48,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":1},{"place":49,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":1},{"place":50,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":1},{"place":51,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":52,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":53,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":0},{"place":54,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":0}]},{"id":"zerobench-sub","name":"ZeroBench (sub)","topic":"Zero-shot generalization","description":"Subset of ZeroBench targeting harder zero-shot reasoning cases.","url":"","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Seed2.1 Pro","top_percent":49.4,"top_model_id":"seed2.1-pro","top_generation":"Seed 2.1","top_model_base":"Seed 2.1 Pro","top_model_family":"Seed","top_company":"bytedance","top_open_source":0,"lower_is_better":false,"bench_models":52,"total_models":3854,"placements":[{"place":1,"model":"seed2.1-pro","company":"bytedance","family":"Seed","version":"Seed 2.1","score":49.4},{"place":2,"model":"seed2.1-turbo","company":"bytedance","family":"Seed","version":"Seed 2.1","score":49.1},{"place":3,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":48.5},{"place":4,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":46.7},{"place":5,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":41.9},{"place":6,"model":"qwen3.5-397b-a17b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":41},{"place":7,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":41},{"place":8,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":41},{"place":9,"model":"gemini-3-pro","company":"google","family":"Gemini","version":"Gemini 3","score":39},{"place":10,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":37.1},{"place":11,"model":"claude-opus-4.7","company":"anthropic","family":"Claude","version":"Claude 4.7","score":37.1},{"place":12,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":36.5},{"place":13,"model":"qwen3.5-122b-a10b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.2},{"place":14,"model":"qwen3.5-27b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":36.2},{"place":15,"model":"qwen3.6-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.6","score":34.4},{"place":16,"model":"qwen3.5-omni-plus","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":34.4},{"place":17,"model":"qwen3.5-35b-a3b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":34.1},{"place":18,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":33.8},{"place":19,"model":"kimi-k2.5","company":"moonshotai","family":"Kimi","version":"Kimi K2.5","score":33.5},{"place":20,"model":"gpt-5.2","company":"openai","family":"GPT","version":"GPT-5.2","score":33.2},{"place":21,"model":"qwen3.5-9b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":31.1},{"place":22,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":31.1},{"place":23,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":30.8},{"place":24,"model":"gemini-2.5-pro","company":"google","family":"Gemini","version":"Gemini 2.5","score":30.24},{"place":25,"model":"claude-opus-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":28.4},{"place":26,"model":"qwen3-vl-235b-a22b","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":28.4},{"place":27,"model":"qwen3-vl-235b-a22b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":27.7},{"place":28,"model":"gpt-5-mini","company":"openai","family":"GPT","version":"GPT-5","score":27.3},{"place":29,"model":"dots-vlm1","company":"rednote","family":"dots","version":"dots.vlm1","score":26.65},{"place":30,"model":"claude-opus-4.1","company":"anthropic","family":"Claude","version":"Claude 4.1","score":26.3},{"place":31,"model":"claude-sonnet-4.5","company":"anthropic","family":"Claude","version":"Claude 4.5","score":26.3},{"place":32,"model":"qwen3.5-4b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":26.3},{"place":33,"model":"gemma-4-26b-a4b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26.3},{"place":34,"model":"gemma-4-31b-it","company":"google","family":"Gemma","version":"Gemma 4","score":26},{"place":35,"model":"qwen3.5-omni-flash","company":"qwen","family":"Qwen","version":"Qwen3.5 Omni","score":26},{"place":36,"model":"glm-4.6v","company":"zai","family":"GLM","version":"GLM 4.6V","score":25.8},{"place":37,"model":"seed1.5-vl-thinking","company":"bytedance","family":"Seed","version":"Seed 1.5","score":25.75},{"place":38,"model":"qwen3-vl-32b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":25.2},{"place":39,"model":"gpt-5-mini-minimal","company":"openai","family":"GPT","version":"GPT-5","score":24.9},{"place":40,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":24.9},{"place":41,"model":"gpt-5","company":"openai","family":"GPT","version":"GPT-5","score":24.6},{"place":42,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":24},{"place":43,"model":"qwen3-vl-30b-a3b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":23.7},{"place":44,"model":"claude-sonnet-4","company":"anthropic","family":"Claude","version":"Claude 4","score":23.1},{"place":45,"model":"qwen3-vl-8b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":22.8},{"place":46,"model":"glm-4.6v-flash","company":"zai","family":"GLM","version":"GLM 4.6V","score":22.5},{"place":47,"model":"gpt-5-nano","company":"openai","family":"GPT","version":"GPT-5","score":22.2},{"place":48,"model":"qwen3-vl-4b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":21},{"place":49,"model":"qwen2.5-vl-72b","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":20},{"place":50,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":19.2},{"place":51,"model":"qwen3-vl-4b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":18.9},{"place":52,"model":"qwen2.5-vl-72b-instruct","company":"qwen","family":"Qwen","version":"Qwen2.5 VL","score":18},{"place":53,"model":"qwen3.5-2b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":17.1},{"place":54,"model":"gpt-5-nano-minimal","company":"openai","family":"GPT","version":"GPT-5","score":15.9},{"place":55,"model":"gemini-2.5-flash-lite","company":"google","family":"Gemini","version":"Gemini 2.5","score":15.3},{"place":56,"model":"qwen3-vl-2b-instruct","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":13.2},{"place":57,"model":"qwen3-vl-2b-thinking","company":"qwen","family":"Qwen","version":"Qwen3 VL","score":13.2},{"place":58,"model":"qwen3.5-0.8b","company":"qwen","family":"Qwen","version":"Qwen3.5","score":12.9}]},{"id":"zerobench-with-tools","name":"ZeroBench (With Tools)","topic":"Visual reasoning","description":"ZeroBench main set evaluated with tool access in an agent harness (pass@5).","url":"https://zerobench.github.io/","leaderboard":"","github":"","paper":"","metric":"percent","stars":"","top_model":"Kimi-K3.1 Pro","top_percent":63,"top_model_id":"kimi-k3.1-pro","top_generation":"Kimi K3.1","top_model_base":"Kimi K3.1 Pro","top_model_family":"Kimi","top_company":"moonshotai","top_open_source":0,"lower_is_better":false,"bench_models":23,"total_models":3854,"placements":[{"place":1,"model":"kimi-k3.1-pro","company":"moonshotai","family":"Kimi","version":"Kimi K3.1","score":63},{"place":2,"model":"claude-opus-5.5","company":"anthropic","family":"Claude","version":"Claude 5.5","score":61},{"place":3,"model":"claude-fable-5.1","company":"anthropic","family":"Claude","version":"Claude 5.1","score":59},{"place":4,"model":"gpt-6-astra","company":"openai","family":"GPT","version":"GPT-6","score":58},{"place":5,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":54.6},{"place":6,"model":"muse-spark-1.2","company":"meta","family":"Muse","version":"Muse Spark","score":54},{"place":7,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":53},{"place":8,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":52},{"place":9,"model":"deepseek-v4.1-flash-1017","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":51},{"place":10,"model":"muse-spark-open","company":"meta","family":"Muse","version":"Muse Spark Open","score":50},{"place":11,"model":"deepseek-v4.1-flash","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4.1","score":49},{"place":12,"model":"qwen3.8-max","company":"qwen","family":"Qwen","version":"Qwen3.8","score":49},{"place":13,"model":"claude-opus-5","company":"anthropic","family":"Claude","version":"Claude 5","score":47.5},{"place":14,"model":"claude-fable-5","company":"anthropic","family":"Claude","version":"Claude 5","score":46},{"place":15,"model":"muse-spark-1.1","company":"meta","family":"Muse","version":"Muse Spark 1.1","score":46},{"place":16,"model":"kimi-k3","company":"moonshotai","family":"Kimi","version":"Kimi K3","score":41},{"place":17,"model":"gpt-5.4","company":"openai","family":"GPT","version":"GPT-5.4","score":41},{"place":18,"model":"gpt-5.5","company":"openai","family":"GPT","version":"GPT-5.5","score":41},{"place":19,"model":"deepseek-v4-flash-vision-exp","company":"deepseek","family":"DeepSeek","version":"DeepSeek V4","score":35},{"place":20,"model":"gpt-5.6-sol","company":"openai","family":"GPT","version":"GPT-5.6","score":35},{"place":21,"model":"claude-opus-4.8","company":"anthropic","family":"Claude","version":"Claude 4.8","score":34},{"place":22,"model":"muse-spark","company":"meta","family":"Muse","version":"Muse Spark","score":33},{"place":23,"model":"gemini-3.7-flash","company":"google","family":"Gemini","version":"Gemini 3.7","score":30},{"place":24,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":29},{"place":25,"model":"gemini-3.1-pro","company":"google","family":"Gemini","version":"Gemini 3.1","score":23},{"place":26,"model":"qwen3.7-plus","company":"qwen","family":"Qwen","version":"Qwen3.7","score":19},{"place":27,"model":"inkling","company":"thinkingmachines","family":"Inkling","version":"Inkling","score":14}]},{"id":"zeroscrolls-booksumsort","name":"ZeroSCROLLS BookSumSort","topic":"Long-context summarization","description":"ZeroSCROLLS split based on BookSumSort long-form summarization.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"cidx","stars":"","top_model":"GPT-4","top_percent":60.5,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":7,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":60.5},{"place":2,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":49.8},{"place":3,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":49.5},{"place":4,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":47.4},{"place":5,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":16.4},{"place":6,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":14},{"place":7,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":0}]},{"id":"zeroscrolls-govreport","name":"ZeroSCROLLS GovReport","topic":"Long-context summarization","description":"ZeroSCROLLS split based on the GovReport summarization benchmark.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"rgeo","stars":"","top_model":"CoLT5","top_percent":41,"top_model_id":"colt5","top_generation":"CoLT5","top_model_base":"CoLT5","top_model_family":"CoLT5","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"colt5","company":"google","family":"CoLT5","version":"CoLT5","score":41},{"place":2,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":26.3},{"place":3,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":24.2},{"place":4,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":21.7},{"place":5,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":21.3},{"place":6,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":17.6},{"place":7,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":16.1},{"place":8,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":7.1}]},{"id":"zeroscrolls-musique","name":"ZeroSCROLLS MuSiQue","topic":"Long-context reasoning","description":"ZeroSCROLLS split derived from MuSiQue multi-hop QA.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"f1","stars":"","top_model":"Llama 3.3 70B Instruct","top_percent":52.2,"top_model_id":"llama-3.3-70b-instruct","top_generation":"Llama 3.3","top_model_base":"Llama 3.3 70B","top_model_family":"Llama","top_company":"meta","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":52.2},{"place":2,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":51.3},{"place":3,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":46.8},{"place":4,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":45},{"place":5,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":41.1},{"place":6,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":36.1},{"place":7,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":35.3},{"place":8,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":33.5},{"place":9,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":27.1}]},{"id":"zeroscrolls-narrativeqa","name":"ZeroSCROLLS NarrativeQA","topic":"Long-context QA","description":"ZeroSCROLLS split based on the NarrativeQA reading comprehension benchmark.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"f1","stars":"","top_model":"Claude v1.3","top_percent":32.6,"top_model_id":"claude-v1.3","top_generation":"Claude v1.3","top_model_base":"Claude v1.3","top_model_family":"Claude","top_company":"anthropic","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":32.6},{"place":2,"model":"colt5","company":"google","family":"CoLT5","version":"CoLT5","score":31},{"place":3,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":27.6},{"place":4,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":25.5},{"place":5,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":25.1},{"place":6,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":24.6},{"place":7,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":19.3},{"place":8,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":18.7}]},{"id":"zeroscrolls-qasper","name":"ZeroSCROLLS Qasper","topic":"Long-context QA","description":"ZeroSCROLLS split based on the Qasper paper QA benchmark.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"f1","stars":"","top_model":"FLAN-UL2","top_percent":56.9,"top_model_id":"flan-ul2","top_generation":"FLAN-UL2","top_model_base":"FLAN-UL2","top_model_family":"FLAN-UL2","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":56.9},{"place":2,"model":"colt5","company":"google","family":"CoLT5","version":"CoLT5","score":53.1},{"place":3,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":52.7},{"place":4,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":52.3},{"place":5,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":50.7},{"place":6,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":49.3},{"place":7,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":48.3},{"place":8,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":25}]},{"id":"zeroscrolls-qmsum","name":"ZeroSCROLLS QMSum","topic":"Long-context summarization","description":"ZeroSCROLLS split based on the QMSum meeting summarization benchmark.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"rgeo","stars":"","top_model":"CoLT5","top_percent":22.5,"top_model_id":"colt5","top_generation":"CoLT5","top_model_base":"CoLT5","top_model_family":"CoLT5","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"colt5","company":"google","family":"CoLT5","version":"CoLT5","score":22.5},{"place":2,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":18.5},{"place":3,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":16.9},{"place":4,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":15.6},{"place":5,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":14.6},{"place":6,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":13.6},{"place":7,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":11},{"place":8,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":7.2}]},{"id":"zeroscrolls-quality","name":"ZeroSCROLLS QuALITY","topic":"Long-context QA","description":"ZeroSCROLLS split based on the QuALITY reading comprehension benchmark.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"ac","stars":"","top_model":"GPT-4","top_percent":89.2,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":89.2},{"place":2,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":84.8},{"place":3,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":75.6},{"place":4,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":75.2},{"place":5,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":69},{"place":6,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":66.6},{"place":7,"model":"colt5","company":"google","family":"CoLT5","version":"CoLT5","score":47},{"place":8,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":21.4}]},{"id":"zeroscrolls-spacedigest","name":"ZeroSCROLLS SpaceDigest","topic":"Long-context summarization","description":"ZeroSCROLLS SpaceDigest extractive summarization task.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"es","stars":"","top_model":"Llama-3_1-70B-TFree-HAT-SFT","top_percent":77.9,"top_model_id":"llama-3_1-70b-tfree-hat-sft","top_generation":"Llama TFree HAT","top_model_base":"Llama 3.1 70B TFree HAT","top_model_family":"Llama TFree HAT","top_company":"alephalpha","top_open_source":1,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":77.9},{"place":2,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":62.8},{"place":3,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":61.6},{"place":4,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":49.1},{"place":5,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":48.7},{"place":6,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":40.4},{"place":7,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":36},{"place":8,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":31.3},{"place":9,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":15.2}]},{"id":"zeroscrolls-squality","name":"ZeroSCROLLS SQuALITY","topic":"Long-context summarization","description":"ZeroSCROLLS split based on the SQuALITY long-form summarization benchmark.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"rouge_gm","stars":"","top_model":"GPT-4","top_percent":22.6,"top_model_id":"gpt-4","top_generation":"GPT-4","top_model_base":"GPT-4","top_model_family":"GPT","top_company":"openai","top_open_source":0,"lower_is_better":false,"bench_models":9,"total_models":3854,"placements":[{"place":1,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":22.6},{"place":2,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":22},{"place":3,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":21},{"place":4,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":20.4},{"place":5,"model":"llama-3_1-70b-tfree-hat-sft","company":"alephalpha","family":"Llama TFree HAT","version":"Llama TFree HAT","score":17},{"place":6,"model":"llama-3.3-70b-instruct","company":"meta","family":"Llama","version":"Llama 3.3","score":15.9},{"place":7,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":8},{"place":8,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":5.7},{"place":9,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":3.9}]},{"id":"zeroscrolls-summscreenfd","name":"ZeroSCROLLS SummScreenFD","topic":"Long-context summarization","description":"ZeroSCROLLS split based on the SummScreenFD summarization benchmark.","url":"https://github.com/allenai/scrolls","leaderboard":"","github":"","paper":"","metric":"rgeo","stars":"","top_model":"CoLT5","top_percent":20,"top_model_id":"colt5","top_generation":"CoLT5","top_model_base":"CoLT5","top_model_family":"CoLT5","top_company":"google","top_open_source":1,"lower_is_better":false,"bench_models":8,"total_models":3854,"placements":[{"place":1,"model":"colt5","company":"google","family":"CoLT5","version":"CoLT5","score":20},{"place":2,"model":"gpt-4","company":"openai","family":"GPT","version":"GPT-4","score":17.3},{"place":3,"model":"davinci-003","company":"openai","family":"Davinci","version":"Davinci","score":16.1},{"place":4,"model":"gpt-3.5-turbo-0301","company":"openai","family":"GPT","version":"GPT-3.5","score":16.1},{"place":5,"model":"claude-v1.3","company":"anthropic","family":"Claude","version":"Claude v1.3","score":16.1},{"place":6,"model":"flan-ul2","company":"google","family":"FLAN-UL2","version":"FLAN-UL2","score":11.5},{"place":7,"model":"t0pp","company":"bigscience","family":"T0","version":"T0pp","score":9.6},{"place":8,"model":"flan-t5","company":"google","family":"FLAN-T5","version":"FLAN-T5","score":7.8}]}]